{ "generatedAt": "2026-10-26T06:04:02.802154+00:00", "lastSyncTime": "2026-10-26T06:04:02.350707+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { "ascend_910-b3|vllm_tokenizer_patch|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-02T16:15:49.651187+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-10-03T16:15:49.651187+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "cyankiwi/Spark-X2.5-4B-AWQ-INT4" ], "sourceTaskIds": [ "5260113" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm_tokenizer_patch|text-generation|architectures:sseswamobaforcausallm": { "architectureSignature": "architectures:sseswamobaforcausallm", "architectures": [ "sseswamobaforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-02T16:15:49.351950+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-10-03T16:15:49.351950+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "Panyuqi/SpikingBrain-2.0-base-8k" ], "sourceTaskIds": [ "5260104" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 4, "expiresAt": "2026-11-07T11:06:58.772405+00:00", "framework": "vllm", "latestFailureAt": "2026-10-08T11:06:58.772405+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "nkkbr/Mini-K3-1H-decay-g64-v2_B", "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D" ], "sourceTaskIds": [ "5378777", "5378775", "5378776", "5378773" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b4|vllm|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-05T09:15:23.057114+00:00", "framework": "vllm", "latestFailureAt": "2026-10-06T09:15:23.057114+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "juspay/Xor-26B-A4B-NVFP4" ], "sourceTaskIds": [ "5320528" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "cambricon_mlu-370-x4|vllm-customized|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-07T08:24:54.847329+00:00", "framework": "vllm-customized", "latestFailureAt": "2026-10-08T08:24:54.847329+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-kda-kernel-0-v2" ], "sourceTaskIds": [ "5374818" ], "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-05T09:57:50.249551+00:00", "framework": "vllm-mlu", "latestFailureAt": "2026-10-06T09:57:50.249551+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "juspay/Xor-26B-A4B-NVFP4" ], "sourceTaskIds": [ "5321225" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-05T09:57:50.069956+00:00", "framework": "vllm-mlu", "latestFailureAt": "2026-10-06T09:57:50.069956+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "prithivMLmods/Nexus-9B-CodeCore-Merge" ], "sourceTaskIds": [ "5321221" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-05T09:35:45.771681+00:00", "framework": "vllm-patch-tokenizer", "latestFailureAt": "2026-10-06T09:35:45.771681+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "spark2_5", "sourceModelIds": [ "cyankiwi/Spark-X2.5-4B-AWQ-INT4" ], "sourceTaskIds": [ "5320872" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-05T09:15:23.045201+00:00", "framework": "vllm-patch-tokenizer", "latestFailureAt": "2026-10-06T09:15:23.045201+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw" ], "sourceTaskIds": [ "5320526" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-12T00:12:55.758955+00:00", "framework": "vllm", "latestFailureAt": "2026-10-13T00:12:55.758955+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "juspay/Xor-26B-A4B-NVFP4" ], "sourceTaskIds": [ "5499072" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|architectures:bananaallforcausallm": { "architectureSignature": "architectures:bananaallforcausallm", "architectures": [ "bananaallforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-06T11:46:58.861235+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "latestFailureAt": "2026-10-07T11:46:58.861235+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "BananaMind/TernaryBananaMind-10M" ], "sourceTaskIds": [ "5353401" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|architectures:cagliostroforcausallm": { "architectureSignature": "architectures:cagliostroforcausallm", "architectures": [ "cagliostroforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-06T19:30:29.971308+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "latestFailureAt": "2026-10-07T19:30:29.971308+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "bench-labs/tinctura-v1" ], "sourceTaskIds": [ "5360311" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|architectures:pulvisforcausallm": { "architectureSignature": "architectures:pulvisforcausallm", "architectures": [ "pulvisforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-06T11:46:59.077598+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "latestFailureAt": "2026-10-07T11:46:59.077598+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "bench-labs/pulvis-v1" ], "sourceTaskIds": [ "5353404" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-06T19:30:29.757524+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "latestFailureAt": "2026-10-07T19:30:29.757524+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "cyankiwi/Spark-X2.5-4B-AWQ-INT4" ], "sourceTaskIds": [ "5360301" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_mrv-100|vllm|text-generation|architectures:cagliostroforcausallm": { "architectureSignature": "architectures:cagliostroforcausallm", "architectures": [ "cagliostroforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-05T09:47:42.648710+00:00", "framework": "vllm", "latestFailureAt": "2026-10-06T09:47:42.648710+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "cagliostro", "sourceModelIds": [ "bench-labs/tinctura-v1" ], "sourceTaskIds": [ "5321081" ], "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation" }, "iluvatar_mrv-100|vllm|text-generation|architectures:plamo3forcausallm": { "architectureSignature": "architectures:plamo3forcausallm", "architectures": [ "plamo3forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-05T09:47:41.756287+00:00", "framework": "vllm", "latestFailureAt": "2026-10-06T09:47:41.756287+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "plamo3", "sourceModelIds": [ "pfnet/plamo-3-610m-fin-instruct" ], "sourceTaskIds": [ "5321052" ], "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation" }, "iluvatar_mrv-100|vllm|text-generation|model_type:gpt_oss": { "architectureSignature": "model_type:gpt_oss", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-05T09:47:42.556514+00:00", "framework": "vllm", "latestFailureAt": "2026-10-06T09:47:42.556514+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gpt_oss", "sourceModelIds": [ "mlx-community/gpt-oss-20b-OptiQ-4bit" ], "sourceTaskIds": [ "5321077" ], "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation" }, "iluvatar_mrv-100|vllm|text-generation|model_type:lfm2": { "architectureSignature": "model_type:lfm2", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-05T09:47:41.656436+00:00", "framework": "vllm", "latestFailureAt": "2026-10-06T09:47:41.656436+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "lfm2", "sourceModelIds": [ "mlabonne/LFM2.5-230M-Chess" ], "sourceTaskIds": [ "5321055" ], "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation" }, "iluvatar_mrv-100|vllm|text-generation|model_type:spark2_5": { "architectureSignature": "model_type:spark2_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-05T09:47:41.751476+00:00", "framework": "vllm", "latestFailureAt": "2026-10-06T09:47:41.751476+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "spark2_5", "sourceModelIds": [ "OsaurusAI/Raptor-0.6-4B-JANG_4M" ], "sourceTaskIds": [ "5321056" ], "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation" }, "metax_c-500|vllm_tokenizer_patch|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-05T08:52:25.966686+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-10-06T08:52:25.966686+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "spark2_5", "sourceModelIds": [ "cyankiwi/Spark-X2.5-4B-AWQ-INT4" ], "sourceTaskIds": [ "5319965" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "metax_c-500|vllm_tokenizer_patch|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-05T08:52:25.845437+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-10-06T08:52:25.845437+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-kda-kernel-0-v2" ], "sourceTaskIds": [ "5319959" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "metax_c-500|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-05T08:52:26.243503+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-10-06T08:52:26.243503+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw" ], "sourceTaskIds": [ "5319978" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "metax_c-500|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-05T08:52:25.882518+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-10-06T08:52:25.882518+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B" ], "sourceTaskIds": [ "5319960" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "metax_c-500|vllm|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-11-20T21:15:43+00:00", "framework": "vllm", "latestFailureAt": "2026-10-21T21:15:43+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "cyankiwi/Ornith-1.0-35B-AWQ-INT4" ], "sourceTaskIds": [ "5684052" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|architectures:cagliostroforcausallm": { "architectureSignature": "architectures:cagliostroforcausallm", "architectures": [ "cagliostroforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-06T18:27:23.565694+00:00", "framework": "vllm", "latestFailureAt": "2026-10-07T18:27:23.565694+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "cagliostro", "sourceModelIds": [ "bench-labs/tinctura-v1" ], "sourceTaskIds": [ "5359388" ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|architectures:pulvisforcausallm": { "architectureSignature": "architectures:pulvisforcausallm", "architectures": [ "pulvisforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-05T09:35:46.372146+00:00", "framework": "vllm", "latestFailureAt": "2026-10-06T09:35:46.372146+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "pulvis", "sourceModelIds": [ "bench-labs/pulvis-v1" ], "sourceTaskIds": [ "5320887" ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-11-11T05:07:18.656930+00:00", "framework": "vllm", "latestFailureAt": "2026-10-12T05:07:18.656930+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "spark2_5", "sourceModelIds": [ "XHToken/Spark-X2.5-4B-Base" ], "sourceTaskIds": [ "5481755" ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|model_type:qwen3_5_text": { "architectureSignature": "model_type:qwen3_5_text", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-11-05T08:52:27.660895+00:00", "framework": "vllm", "latestFailureAt": "2026-10-06T08:52:27.660895+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_text", "sourceModelIds": [ "TokenRhythm/NeoHorse-1-4B", "TokenRhythm/NeoHorse-1-9B" ], "sourceTaskIds": [ "5320023", "5320021" ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" } }, "architectureCompatibilitySummary": { "activeBlockCount": 28, "byGpuFramework": { "Ascend_910-b3|vllm": 1, "Ascend_910-b3|vllm_tokenizer_patch": 2, "Ascend_910-b4|vllm": 1, "Cambricon_mlu-370-x4|vllm-customized": 1, "Cambricon_mlu-370-x8|vllm-mlu": 2, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 4, "Iluvatar_mrv-100|vllm": 5, "MetaX_c-500|vllm": 1, "MetaX_c-500|vllm_tokenizer_patch": 4, "Mthreads_s4000|vllm": 4, "hygon_k100-ai|vllm": 1, "hygon_k100-ai|vllm-patch-tokenizer": 2 }, "ttlDays": 30 }, "combinationStats": { "Ascend_910-b3|llamacpp|text-generation": { "attributableFailureCount": 2, "decisionFailureRate": 0.6667, "decisionSuccessRate": 0.3333, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 2 }, "failureCount": 3, "failureRate": 0.75, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 1, "successRate": 0.25, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 1 }, "Ascend_910-b3|unknown|feature_emb": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "日志缺失": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "feature_emb", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|unknown|text-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 6, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 32, "日志缺失": 2, "验证失败": 26 }, "failureCount": 61, "failureRate": 0.9104, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 6, "successRate": 0.0896, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 67, "unresolvedFailureCount": 61 }, "Ascend_910-b3|unknown|visual-multi-modal": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "验证失败": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "visual-multi-modal", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 58, "decisionFailureRate": 0.9355, "decisionSuccessRate": 0.0645, "decisionTotal": 62, "failureBreakdown": { "ambiguous_runtime": 99, "context_length": 9, "framework_architecture_unsupported": 48, "memory_capacity": 1, "platform_infrastructure": 1, "参数/模板问题": 46 }, "failureCount": 204, "failureRate": 0.9808, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 4, "successRate": 0.0192, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 208, "unresolvedFailureCount": 145 }, "Ascend_910-b3|vllm|text-generation": { "attributableFailureCount": 75, "decisionFailureRate": 0.8721, "decisionSuccessRate": 0.1279, "decisionTotal": 86, "failureBreakdown": { "ambiguous_runtime": 67, "framework_architecture_unsupported": 70, "memory_capacity": 1, "repository_structure": 1, "tokenizer_compatibility": 3 }, "failureCount": 142, "failureRate": 0.9281, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 11, "successRate": 0.0719, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 153, "unresolvedFailureCount": 67 }, "Ascend_910-b3|vllm|visual-multi-modal": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "visual-multi-modal", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|llamacpp|text-generation": { "attributableFailureCount": 92, "decisionFailureRate": 0.9892, "decisionSuccessRate": 0.0108, "decisionTotal": 93, "failureBreakdown": { "ambiguous_runtime": 19, "memory_capacity": 9, "model_load": 83, "参数/模板问题": 1 }, "failureCount": 112, "failureRate": 0.9912, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 1, "successRate": 0.0088, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 113, "unresolvedFailureCount": 20 }, "Ascend_910-b4|llamacpp|unknown": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "unknown", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|llamacpp|visual-multi-modal": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "visual-multi-modal", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|unknown|text-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 60, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 254, "日志缺失": 11, "验证失败": 175 }, "failureCount": 442, "failureRate": 0.8805, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 60, "successRate": 0.1195, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 502, "unresolvedFailureCount": 442 }, "Ascend_910-b4|unknown|visual-multi-modal": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 6, "参数/模板问题": 8, "日志缺失": 3 }, "failureCount": 17, "failureRate": 0.8947, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 2, "successRate": 0.1053, "targetGpu": "Ascend_910-b4", "taskType": "visual-multi-modal", "total": 19, "unresolvedFailureCount": 17 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 41, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 41, "failureBreakdown": { "ambiguous_runtime": 107, "framework_architecture_unsupported": 40, "platform_infrastructure": 1, "repository_structure": 1, "参数/模板问题": 40 }, "failureCount": 189, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 189, "unresolvedFailureCount": 147 }, "Ascend_910-b4|vllm|text-generation": { "attributableFailureCount": 206, "decisionFailureRate": 0.9952, "decisionSuccessRate": 0.0048, "decisionTotal": 207, "failureBreakdown": { "ambiguous_runtime": 124, "context_length": 1, "framework_architecture_unsupported": 157, "memory_capacity": 10, "platform_infrastructure": 2, "repository_structure": 27, "tokenizer_compatibility": 11, "参数/模板问题": 1 }, "failureCount": 333, "failureRate": 0.997, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 1, "successRate": 0.003, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 334, "unresolvedFailureCount": 125 }, "Biren_166m|unknown|feature_emb": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "feature_emb", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|unknown|text-generation": { "attributableFailureCount": 141, "decisionFailureRate": 0.9338, "decisionSuccessRate": 0.0662, "decisionTotal": 151, "failureBreakdown": { "ambiguous_runtime": 130, "backend_operator": 4, "context_length": 10, "framework_architecture_unsupported": 88, "memory_capacity": 1, "model_load": 12, "platform_infrastructure": 2, "repository_structure": 18, "runtime_memory": 2, "tokenizer_compatibility": 6, "参数/模板问题": 213, "日志缺失": 62, "验证失败": 27 }, "failureCount": 575, "failureRate": 0.9829, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 10, "successRate": 0.0171, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 585, "unresolvedFailureCount": 432 }, "Biren_166m|unknown|visual-multi-modal": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "visual-multi-modal", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 163, "memory_capacity": 1, "参数/模板问题": 14 }, "failureCount": 178, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 178, "unresolvedFailureCount": 177 }, "Biren_166m|vllm|text-generation": { "attributableFailureCount": 51, "decisionFailureRate": 0.7727, "decisionSuccessRate": 0.2273, "decisionTotal": 66, "failureBreakdown": { "ambiguous_runtime": 14, "framework_architecture_unsupported": 37, "model_load": 12, "tokenizer_compatibility": 2, "参数/模板问题": 1 }, "failureCount": 66, "failureRate": 0.8148, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 15, "successRate": 0.1852, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 81, "unresolvedFailureCount": 15 }, "Cambricon_mlu-370-x4|unknown|text-generation": { "attributableFailureCount": 695, "decisionFailureRate": 0.9145, "decisionSuccessRate": 0.0855, "decisionTotal": 760, "failureBreakdown": { "ambiguous_runtime": 414, "architecture_compatibility": 51, "context_length": 48, "framework_architecture_unsupported": 258, "memory_capacity": 216, "model_load": 4, "platform_infrastructure": 15, "repository_structure": 84, "tokenizer_compatibility": 34, "参数/模板问题": 298, "日志缺失": 13, "验证失败": 39 }, "failureCount": 1474, "failureRate": 0.9578, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 15, "successCount": 65, "successRate": 0.0422, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1539, "unresolvedFailureCount": 764 }, "Cambricon_mlu-370-x4|unknown|unknown": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "repository_structure": 1, "tokenizer_compatibility": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "unknown", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|unknown|visual-multi-modal": { "attributableFailureCount": 8, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 8, "failureBreakdown": { "ambiguous_runtime": 1, "architecture_compatibility": 2, "framework_architecture_unsupported": 4, "memory_capacity": 2, "参数/模板问题": 4 }, "failureCount": 13, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "visual-multi-modal", "total": 13, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 4, "framework_architecture_unsupported": 4, "参数/模板问题": 7 }, "failureCount": 15, "failureRate": 1.0, "framework": "vllm-customized", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 15, "unresolvedFailureCount": 11 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation": { "attributableFailureCount": 38, "decisionFailureRate": 0.8085, "decisionSuccessRate": 0.1915, "decisionTotal": 47, "failureBreakdown": { "ambiguous_runtime": 60, "framework_architecture_unsupported": 34, "model_load": 4, "platform_infrastructure": 1, "参数/模板问题": 11, "验证失败": 3 }, "failureCount": 113, "failureRate": 0.9262, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 9, "successRate": 0.0738, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 122, "unresolvedFailureCount": 74 }, "Cambricon_mlu-370-x4|vllm|text-generation": { "attributableFailureCount": 25, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 25, "failureBreakdown": { "ambiguous_runtime": 46, "framework_architecture_unsupported": 24, "memory_capacity": 1, "参数/模板问题": 1 }, "failureCount": 72, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 72, "unresolvedFailureCount": 47 }, "Cambricon_mlu-370-x8|unknown|feature_emb": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "feature_emb", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|unknown|text-generation": { "attributableFailureCount": 12, "decisionFailureRate": 0.8571, "decisionSuccessRate": 0.1429, "decisionTotal": 14, "failureBreakdown": { "ambiguous_runtime": 40, "framework_architecture_unsupported": 8, "memory_capacity": 3, "tokenizer_compatibility": 1, "参数/模板问题": 21, "验证失败": 22 }, "failureCount": 95, "failureRate": 0.9794, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 2, "successRate": 0.0206, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 97, "unresolvedFailureCount": 83 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation": { "attributableFailureCount": 12, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 12, "failureBreakdown": { "ambiguous_runtime": 42, "framework_architecture_unsupported": 8, "model_load": 3, "platform_infrastructure": 2, "tokenizer_compatibility": 1, "参数/模板问题": 5 }, "failureCount": 61, "failureRate": 1.0, "framework": "vllm-customized", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 61, "unresolvedFailureCount": 47 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation": { "attributableFailureCount": 26, "decisionFailureRate": 0.6667, "decisionSuccessRate": 0.3333, "decisionTotal": 39, "failureBreakdown": { "ambiguous_runtime": 64, "framework_architecture_unsupported": 22, "model_load": 3, "tokenizer_compatibility": 1, "参数/模板问题": 48 }, "failureCount": 138, "failureRate": 0.9139, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 13, "successRate": 0.0861, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 151, "unresolvedFailureCount": 112 }, "Cambricon_mlu-370-x8|vllm|text-generation": { "attributableFailureCount": 22, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 22, "failureBreakdown": { "ambiguous_runtime": 21, "framework_architecture_unsupported": 21, "memory_capacity": 1, "参数/模板问题": 12 }, "failureCount": 55, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 55, "unresolvedFailureCount": 33 }, "Iluvatar_bi-100|transformers|text-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 55 }, "failureCount": 55, "failureRate": 1.0, "framework": "transformers", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 55, "unresolvedFailureCount": 55 }, "Iluvatar_bi-100|unknown|feature_emb": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "日志缺失": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "feature_emb", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-100|unknown|text-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 61, "failureBreakdown": { "ambiguous_runtime": 7, "platform_infrastructure": 16, "参数/模板问题": 206, "日志缺失": 93, "验证失败": 20 }, "failureCount": 342, "failureRate": 0.8486, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 16, "successCount": 61, "successRate": 0.1514, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 403, "unresolvedFailureCount": 326 }, "Iluvatar_bi-100|unknown|text-to-image-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 59, "platform_infrastructure": 1, "参数/模板问题": 13, "日志缺失": 13 }, "failureCount": 86, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-to-image-generation", "total": 86, "unresolvedFailureCount": 85 }, "Iluvatar_bi-100|unknown|unknown": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "参数/模板问题": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "unknown", "total": 4, "unresolvedFailureCount": 4 }, "Iluvatar_bi-100|unknown|visual-multi-modal": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 33, "参数/模板问题": 22, "日志缺失": 27 }, "failureCount": 82, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "visual-multi-modal", "total": 82, "unresolvedFailureCount": 82 }, "Iluvatar_bi-100|vllm|text-generation": { "attributableFailureCount": 192, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 192, "failureBreakdown": { "ambiguous_runtime": 18, "memory_capacity": 192, "platform_infrastructure": 611 }, "failureCount": 821, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 611, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 821, "unresolvedFailureCount": 18 }, "Iluvatar_bi-100|vllm|unknown": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "unknown", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-100|vllm|visual-multi-modal": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "memory_capacity": 2, "platform_infrastructure": 5 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 5, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "visual-multi-modal", "total": 7, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|llamacpp|reinforcement_learning": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "reinforcement_learning", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|llamacpp|text-generation": { "attributableFailureCount": 92, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 92, "failureBreakdown": { "ambiguous_runtime": 69, "memory_capacity": 11, "model_load": 81, "参数/模板问题": 1 }, "failureCount": 162, "failureRate": 1.0, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 162, "unresolvedFailureCount": 70 }, "Iluvatar_bi-150|llamacpp|unknown": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "unknown", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|llamacpp|visual-multi-modal": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "visual-multi-modal", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation": { "attributableFailureCount": 26, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 26, "failureBreakdown": { "ambiguous_runtime": 20, "framework_architecture_unsupported": 7, "memory_capacity": 5, "model_load": 2, "tokenizer_compatibility": 12 }, "failureCount": 46, "failureRate": 1.0, "framework": "transformers", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 46, "unresolvedFailureCount": 20 }, "Iluvatar_bi-150|unknown|asr": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 36, "参数/模板问题": 9, "日志缺失": 12 }, "failureCount": 57, "failureRate": 0.9828, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 1, "successRate": 0.0172, "targetGpu": "Iluvatar_bi-150", "taskType": "asr", "total": 58, "unresolvedFailureCount": 57 }, "Iluvatar_bi-150|unknown|feature_emb": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "日志缺失": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "feature_emb", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|unknown|question_answering": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "日志缺失": 1 }, "failureCount": 2, "failureRate": 0.6667, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 1, "successRate": 0.3333, "targetGpu": "Iluvatar_bi-150", "taskType": "question_answering", "total": 3, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|unknown|reinforcement_learning": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 6, "参数/模板问题": 6, "日志缺失": 11 }, "failureCount": 23, "failureRate": 0.8846, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 3, "successRate": 0.1154, "targetGpu": "Iluvatar_bi-150", "taskType": "reinforcement_learning", "total": 26, "unresolvedFailureCount": 23 }, "Iluvatar_bi-150|unknown|text-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 126, "failureBreakdown": { "ambiguous_runtime": 71, "参数/模板问题": 261, "日志缺失": 95, "验证失败": 30 }, "failureCount": 457, "failureRate": 0.7839, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 126, "successRate": 0.2161, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 583, "unresolvedFailureCount": 457 }, "Iluvatar_bi-150|unknown|text-to-image-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 59, "参数/模板问题": 13, "日志缺失": 10 }, "failureCount": 82, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-to-image-generation", "total": 82, "unresolvedFailureCount": 82 }, "Iluvatar_bi-150|unknown|unknown": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "参数/模板问题": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "unknown", "total": 4, "unresolvedFailureCount": 4 }, "Iluvatar_bi-150|unknown|vision_classification": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 39, "参数/模板问题": 6, "日志缺失": 9 }, "failureCount": 54, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "vision_classification", "total": 54, "unresolvedFailureCount": 54 }, "Iluvatar_bi-150|unknown|visual-multi-modal": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 43, "参数/模板问题": 23, "日志缺失": 16 }, "failureCount": 82, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "visual-multi-modal", "total": 82, "unresolvedFailureCount": 82 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": { "attributableFailureCount": 59, "decisionFailureRate": 0.7564, "decisionSuccessRate": 0.2436, "decisionTotal": 78, "failureBreakdown": { "ambiguous_runtime": 38, "backend_operator": 6, "framework_architecture_unsupported": 33, "memory_capacity": 1, "model_load": 9, "runtime_memory": 10, "参数/模板问题": 29 }, "failureCount": 126, "failureRate": 0.869, "framework": "vllm_0_17_0_corex_4_4_0", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, "successRate": 0.131, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 145, "unresolvedFailureCount": 67 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 9, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 9, "failureBreakdown": { "ambiguous_runtime": 53, "memory_capacity": 9, "参数/模板问题": 2 }, "failureCount": 64, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 64, "unresolvedFailureCount": 55 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 10, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 10, "failureBreakdown": { "ambiguous_runtime": 4, "framework_architecture_unsupported": 5, "model_load": 3, "tokenizer_compatibility": 2 }, "failureCount": 14, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 14, "unresolvedFailureCount": 4 }, "Iluvatar_bi-150|vllm|reinforcement_learning": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 14, "platform_infrastructure": 6 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 6, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "reinforcement_learning", "total": 20, "unresolvedFailureCount": 14 }, "Iluvatar_bi-150|vllm|text-generation": { "attributableFailureCount": 573, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 573, "failureBreakdown": { "ambiguous_runtime": 211, "architecture_compatibility": 14, "backend_operator": 6, "context_length": 29, "framework_architecture_unsupported": 220, "memory_capacity": 125, "model_load": 32, "platform_infrastructure": 15, "repository_structure": 98, "runtime_memory": 3, "tokenizer_compatibility": 46 }, "failureCount": 799, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 15, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 799, "unresolvedFailureCount": 211 }, "Iluvatar_bi-150|vllm|unknown": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "repository_structure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "unknown", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm|visual-multi-modal": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 1, "architecture_compatibility": 1, "framework_architecture_unsupported": 1, "memory_capacity": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "visual-multi-modal", "total": 5, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|transformers|text-generation": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|unknown|asr": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 44, "参数/模板问题": 10 }, "failureCount": 54, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "asr", "total": 54, "unresolvedFailureCount": 54 }, "Iluvatar_mrv-100|unknown|text-generation": { "attributableFailureCount": 943, "decisionFailureRate": 0.8542, "decisionSuccessRate": 0.1458, "decisionTotal": 1104, "failureBreakdown": { "ambiguous_runtime": 187, "architecture_compatibility": 45, "backend_operator": 1, "context_length": 77, "framework_architecture_unsupported": 270, "memory_capacity": 217, "model_load": 84, "platform_infrastructure": 6, "repository_structure": 132, "runtime_memory": 1, "tokenizer_compatibility": 116, "参数/模板问题": 293, "日志缺失": 5, "验证失败": 47 }, "failureCount": 1481, "failureRate": 0.9019, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 6, "successCount": 161, "successRate": 0.0981, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1642, "unresolvedFailureCount": 532 }, "Iluvatar_mrv-100|unknown|text-to-image-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 69, "参数/模板问题": 13, "日志缺失": 1 }, "failureCount": 83, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-to-image-generation", "total": 83, "unresolvedFailureCount": 83 }, "Iluvatar_mrv-100|unknown|unknown": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 3, "platform_infrastructure": 1, "repository_structure": 1, "参数/模板问题": 1 }, "failureCount": 6, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "unknown", "total": 6, "unresolvedFailureCount": 4 }, "Iluvatar_mrv-100|unknown|visual-multi-modal": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "ambiguous_runtime": 37, "architecture_compatibility": 2, "framework_architecture_unsupported": 1, "memory_capacity": 2, "参数/模板问题": 20 }, "failureCount": 62, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "visual-multi-modal", "total": 62, "unresolvedFailureCount": 57 }, "Iluvatar_mrv-100|vllm|text-generation": { "attributableFailureCount": 48, "decisionFailureRate": 0.75, "decisionSuccessRate": 0.25, "decisionTotal": 64, "failureBreakdown": { "ambiguous_runtime": 16, "framework_architecture_unsupported": 39, "model_load": 7, "tokenizer_compatibility": 2, "参数/模板问题": 31 }, "failureCount": 95, "failureRate": 0.8559, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 16, "successRate": 0.1441, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 111, "unresolvedFailureCount": 47 }, "Kunlunxin_p-800|unknown|text-generation": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 76, "memory_capacity": 1, "参数/模板问题": 25, "日志缺失": 1, "验证失败": 22 }, "failureCount": 125, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 125, "unresolvedFailureCount": 124 }, "Kunlunxin_p-800|unknown|visual-multi-modal": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "验证失败": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "visual-multi-modal", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 205, "参数/模板问题": 17 }, "failureCount": 222, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 222, "unresolvedFailureCount": 222 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 61, "decisionFailureRate": 0.9104, "decisionSuccessRate": 0.0896, "decisionTotal": 67, "failureBreakdown": { "ambiguous_runtime": 10, "backend_operator": 15, "framework_architecture_unsupported": 20, "memory_capacity": 1, "model_load": 20, "platform_infrastructure": 1, "repository_structure": 2, "runtime_memory": 3, "参数/模板问题": 15 }, "failureCount": 87, "failureRate": 0.9355, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 6, "successRate": 0.0645, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 93, "unresolvedFailureCount": 25 }, "Kunlunxin_p-800|vllm|text-generation": { "attributableFailureCount": 37, "decisionFailureRate": 0.9737, "decisionSuccessRate": 0.0263, "decisionTotal": 38, "failureBreakdown": { "ambiguous_runtime": 2, "backend_operator": 8, "framework_architecture_unsupported": 17, "memory_capacity": 1, "model_load": 10, "tokenizer_compatibility": 1, "参数/模板问题": 4 }, "failureCount": 43, "failureRate": 0.9773, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 1, "successRate": 0.0227, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 44, "unresolvedFailureCount": 6 }, "Kunlunxin_r-200-8f|unknown|text-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 140, "日志缺失": 30 }, "failureCount": 170, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_r-200-8f", "taskType": "text-generation", "total": 170, "unresolvedFailureCount": 170 }, "MetaX_c-500|unknown|feature_emb": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 5, "failureBreakdown": { "ambiguous_runtime": 26, "platform_infrastructure": 1, "参数/模板问题": 12, "日志缺失": 12 }, "failureCount": 51, "failureRate": 0.9107, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 5, "successRate": 0.0893, "targetGpu": "MetaX_c-500", "taskType": "feature_emb", "total": 56, "unresolvedFailureCount": 50 }, "MetaX_c-500|unknown|text-generation": { "attributableFailureCount": 28, "decisionFailureRate": 0.1944, "decisionSuccessRate": 0.8056, "decisionTotal": 144, "failureBreakdown": { "ambiguous_runtime": 103, "context_length": 13, "memory_capacity": 1, "repository_structure": 14, "参数/模板问题": 363, "日志缺失": 1, "验证失败": 48 }, "failureCount": 543, "failureRate": 0.824, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 116, "successRate": 0.176, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 659, "unresolvedFailureCount": 515 }, "MetaX_c-500|unknown|unknown": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "参数/模板问题": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "unknown", "total": 4, "unresolvedFailureCount": 4 }, "MetaX_c-500|unknown|visual-multi-modal": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 39, "参数/模板问题": 25, "日志缺失": 2 }, "failureCount": 66, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "visual-multi-modal", "total": 66, "unresolvedFailureCount": 66 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 14, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 14, "failureBreakdown": { "ambiguous_runtime": 3, "backend_operator": 2, "context_length": 1, "framework_architecture_unsupported": 7, "model_load": 4, "参数/模板问题": 45 }, "failureCount": 62, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 62, "unresolvedFailureCount": 48 }, "MetaX_c-500|vllm|feature_emb": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "feature_emb", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation": { "attributableFailureCount": 641, "decisionFailureRate": 0.961, "decisionSuccessRate": 0.039, "decisionTotal": 667, "failureBreakdown": { "ambiguous_runtime": 135, "architecture_compatibility": 20, "backend_operator": 43, "context_length": 46, "framework_architecture_unsupported": 204, "memory_capacity": 84, "model_load": 65, "platform_infrastructure": 3, "repository_structure": 98, "runtime_memory": 2, "tokenizer_compatibility": 79, "参数/模板问题": 16 }, "failureCount": 795, "failureRate": 0.9683, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 26, "successRate": 0.0317, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 821, "unresolvedFailureCount": 151 }, "MetaX_c-500|vllm|unknown": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "platform_infrastructure": 1, "repository_structure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "unknown", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|visual-multi-modal": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "ambiguous_runtime": 1, "architecture_compatibility": 1, "framework_architecture_unsupported": 4 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "visual-multi-modal", "total": 6, "unresolvedFailureCount": 1 }, "Mthreads_s4000|llamacpp|text-generation": { "attributableFailureCount": 3, "decisionFailureRate": 0.75, "decisionSuccessRate": 0.25, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 3 }, "failureCount": 4, "failureRate": 0.8, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 1, "successRate": 0.2, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 1 }, "Mthreads_s4000|unknown|text-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 20, "failureBreakdown": { "参数/模板问题": 33, "日志缺失": 6, "验证失败": 25 }, "failureCount": 64, "failureRate": 0.7619, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 20, "successRate": 0.2381, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 84, "unresolvedFailureCount": 64 }, "Mthreads_s4000|unknown|unknown": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "unknown", "total": 3, "unresolvedFailureCount": 3 }, "Mthreads_s4000|unknown|visual-multi-modal": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 43, "参数/模板问题": 24, "日志缺失": 90, "验证失败": 1 }, "failureCount": 158, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "visual-multi-modal", "total": 158, "unresolvedFailureCount": 158 }, "Mthreads_s4000|vllm|text-generation": { "attributableFailureCount": 95, "decisionFailureRate": 0.7983, "decisionSuccessRate": 0.2017, "decisionTotal": 119, "failureBreakdown": { "ambiguous_runtime": 82, "attention_backend": 2, "backend_operator": 8, "framework_architecture_unsupported": 66, "memory_capacity": 1, "model_load": 6, "platform_infrastructure": 1, "repository_structure": 1, "runtime_memory": 5, "tokenizer_compatibility": 6, "参数/模板问题": 33 }, "failureCount": 211, "failureRate": 0.8979, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 24, "successRate": 0.1021, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 235, "unresolvedFailureCount": 115 }, "Mthreads_s4000|vllm|visual-multi-modal": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "visual-multi-modal", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|unknown|feature_emb": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "feature_emb", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|unknown|text-generation": { "attributableFailureCount": 13, "decisionFailureRate": 0.1226, "decisionSuccessRate": 0.8774, "decisionTotal": 106, "failureBreakdown": { "ambiguous_runtime": 52, "context_length": 5, "repository_structure": 8, "参数/模板问题": 212, "验证失败": 32 }, "failureCount": 309, "failureRate": 0.7687, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 93, "successRate": 0.2313, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 402, "unresolvedFailureCount": 296 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 148, "decisionFailureRate": 0.9867, "decisionSuccessRate": 0.0133, "decisionTotal": 150, "failureBreakdown": { "ambiguous_runtime": 4, "backend_operator": 11, "framework_architecture_unsupported": 33, "memory_capacity": 1, "platform_infrastructure": 37, "tokenizer_compatibility": 103, "参数/模板问题": 15 }, "failureCount": 204, "failureRate": 0.9903, "framework": "vllm_fix_tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 37, "successCount": 2, "successRate": 0.0097, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 206, "unresolvedFailureCount": 19 }, "Sunrise_pt-200-x1|vllm|text-generation": { "attributableFailureCount": 637, "decisionFailureRate": 0.9815, "decisionSuccessRate": 0.0185, "decisionTotal": 649, "failureBreakdown": { "ambiguous_runtime": 110, "architecture_compatibility": 43, "backend_operator": 33, "context_length": 34, "framework_architecture_unsupported": 155, "memory_capacity": 113, "platform_infrastructure": 224, "repository_structure": 75, "runtime_memory": 1, "tokenizer_compatibility": 183, "参数/模板问题": 12 }, "failureCount": 983, "failureRate": 0.9879, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 224, "successCount": 12, "successRate": 0.0121, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 995, "unresolvedFailureCount": 122 }, "Sunrise_pt-200-x1|vllm|unknown": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "unknown", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|visual-multi-modal": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 1, "architecture_compatibility": 1, "framework_architecture_unsupported": 2, "tokenizer_compatibility": 1 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "visual-multi-modal", "total": 5, "unresolvedFailureCount": 1 }, "Vastai_va16|unknown|feature_emb": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "日志缺失": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "feature_emb", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|unknown|text-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 52, "failureBreakdown": { "ambiguous_runtime": 214, "参数/模板问题": 253, "日志缺失": 123, "验证失败": 130 }, "failureCount": 720, "failureRate": 0.9326, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 52, "successRate": 0.0674, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 772, "unresolvedFailureCount": 720 }, "Vastai_va16|unknown|unknown": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "unknown", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|unknown|visual-multi-modal": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "visual-multi-modal", "total": 3, "unresolvedFailureCount": 3 }, "Vastai_va16|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 39, "decisionFailureRate": 0.8864, "decisionSuccessRate": 0.1136, "decisionTotal": 44, "failureBreakdown": { "ambiguous_runtime": 29, "framework_architecture_unsupported": 26, "model_load": 13, "参数/模板问题": 6 }, "failureCount": 74, "failureRate": 0.9367, "framework": "vllm_fix_tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 5, "successRate": 0.0633, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 79, "unresolvedFailureCount": 35 }, "Vastai_va16|vllm|text-generation": { "attributableFailureCount": 430, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 430, "failureBreakdown": { "ambiguous_runtime": 581, "context_length": 9, "framework_architecture_unsupported": 178, "memory_capacity": 133, "model_load": 42, "platform_infrastructure": 14, "repository_structure": 56, "tokenizer_compatibility": 12 }, "failureCount": 1025, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 14, "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1025, "unresolvedFailureCount": 581 }, "Vastai_va16|vllm|unknown": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "unknown", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm|visual-multi-modal": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 2, "framework_architecture_unsupported": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "visual-multi-modal", "total": 3, "unresolvedFailureCount": 2 }, "hygon_k100-ai|llamacpp|text-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 27 }, "failureCount": 27, "failureRate": 1.0, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 27, "unresolvedFailureCount": 27 }, "hygon_k100-ai|unknown|text-generation": { "attributableFailureCount": 10, "decisionFailureRate": 0.25, "decisionSuccessRate": 0.75, "decisionTotal": 40, "failureBreakdown": { "ambiguous_runtime": 64, "context_length": 4, "repository_structure": 6, "参数/模板问题": 357, "日志缺失": 60, "验证失败": 27 }, "failureCount": 518, "failureRate": 0.9453, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 30, "successRate": 0.0547, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 548, "unresolvedFailureCount": 508 }, "hygon_k100-ai|unknown|unknown": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "unknown", "total": 3, "unresolvedFailureCount": 3 }, "hygon_k100-ai|unknown|visual-multi-modal": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 45, "参数/模板问题": 21, "日志缺失": 6 }, "failureCount": 72, "failureRate": 1.0, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "visual-multi-modal", "total": 72, "unresolvedFailureCount": 72 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation": { "attributableFailureCount": 71, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 71, "failureBreakdown": { "ambiguous_runtime": 54, "framework_architecture_unsupported": 29, "model_load": 18, "repository_structure": 5, "runtime_memory": 19, "参数/模板问题": 62 }, "failureCount": 187, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 187, "unresolvedFailureCount": 116 }, "hygon_k100-ai|vllm|text-generation": { "attributableFailureCount": 666, "decisionFailureRate": 0.9911, "decisionSuccessRate": 0.0089, "decisionTotal": 672, "failureBreakdown": { "ambiguous_runtime": 163, "architecture_compatibility": 30, "attention_backend": 1, "context_length": 42, "framework_architecture_unsupported": 231, "memory_capacity": 59, "model_load": 60, "platform_infrastructure": 3, "repository_structure": 109, "runtime_memory": 55, "tokenizer_compatibility": 79, "参数/模板问题": 5 }, "failureCount": 837, "failureRate": 0.9929, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 6, "successRate": 0.0071, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 843, "unresolvedFailureCount": 168 }, "hygon_k100-ai|vllm|unknown": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "platform_infrastructure": 1, "repository_structure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "unknown", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|visual-multi-modal": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 1, "architecture_compatibility": 2, "framework_architecture_unsupported": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "visual-multi-modal", "total": 5, "unresolvedFailureCount": 1 } }, "frameworkSummaries": { "llamacpp": { "attributableFailureCount": 193, "decisionFailureRate": 0.9847, "decisionSuccessRate": 0.0153, "decisionTotal": 196, "failureBreakdown": { "ambiguous_runtime": 120, "memory_capacity": 20, "model_load": 173, "参数/模板问题": 2 }, "failureCount": 315, "failureRate": 0.9906, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 3, "successRate": 0.0094, "total": 318, "unresolvedFailureCount": 122 }, "transformers": { "attributableFailureCount": 27, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 27, "failureBreakdown": { "ambiguous_runtime": 75, "framework_architecture_unsupported": 8, "memory_capacity": 5, "model_load": 2, "tokenizer_compatibility": 12 }, "failureCount": 102, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "total": 102, "unresolvedFailureCount": 75 }, "unknown": { "attributableFailureCount": 1860, "decisionFailureRate": 0.6956, "decisionSuccessRate": 0.3044, "decisionTotal": 2674, "failureBreakdown": { "ambiguous_runtime": 1968, "architecture_compatibility": 100, "backend_operator": 5, "context_length": 157, "framework_architecture_unsupported": 630, "memory_capacity": 443, "model_load": 100, "platform_infrastructure": 42, "repository_structure": 264, "runtime_memory": 3, "tokenizer_compatibility": 158, "参数/模板问题": 3199, "日志缺失": 719, "验证失败": 673 }, "failureCount": 8461, "failureRate": 0.9122, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 42, "successCount": 814, "successRate": 0.0878, "total": 9275, "unresolvedFailureCount": 6559 }, "vllm": { "attributableFailureCount": 3727, "decisionFailureRate": 0.9708, "decisionSuccessRate": 0.0292, "decisionTotal": 3839, "failureBreakdown": { "ambiguous_runtime": 1611, "architecture_compatibility": 112, "attention_backend": 3, "backend_operator": 98, "context_length": 161, "framework_architecture_unsupported": 1431, "memory_capacity": 725, "model_load": 234, "platform_infrastructure": 888, "repository_structure": 470, "runtime_memory": 66, "tokenizer_compatibility": 427, "参数/模板问题": 116 }, "failureCount": 6342, "failureRate": 0.9826, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 888, "successCount": 112, "successRate": 0.0174, "total": 6454, "unresolvedFailureCount": 1727 }, "vllm-customized": { "attributableFailureCount": 16, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 16, "failureBreakdown": { "ambiguous_runtime": 46, "framework_architecture_unsupported": 12, "model_load": 3, "platform_infrastructure": 2, "tokenizer_compatibility": 1, "参数/模板问题": 12 }, "failureCount": 76, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 0, "successRate": 0.0, "total": 76, "unresolvedFailureCount": 58 }, "vllm-mlu": { "attributableFailureCount": 64, "decisionFailureRate": 0.7442, "decisionSuccessRate": 0.2558, "decisionTotal": 86, "failureBreakdown": { "ambiguous_runtime": 124, "framework_architecture_unsupported": 56, "model_load": 7, "platform_infrastructure": 1, "tokenizer_compatibility": 1, "参数/模板问题": 59, "验证失败": 3 }, "failureCount": 251, "failureRate": 0.9194, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, "successRate": 0.0806, "total": 273, "unresolvedFailureCount": 186 }, "vllm-patch-tokenizer": { "attributableFailureCount": 71, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 71, "failureBreakdown": { "ambiguous_runtime": 54, "framework_architecture_unsupported": 29, "model_load": 18, "repository_structure": 5, "runtime_memory": 19, "参数/模板问题": 62 }, "failureCount": 187, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "total": 187, "unresolvedFailureCount": 116 }, "vllm_0_17_0_corex_4_4_0": { "attributableFailureCount": 59, "decisionFailureRate": 0.7564, "decisionSuccessRate": 0.2436, "decisionTotal": 78, "failureBreakdown": { "ambiguous_runtime": 38, "backend_operator": 6, "framework_architecture_unsupported": 33, "memory_capacity": 1, "model_load": 9, "runtime_memory": 10, "参数/模板问题": 29 }, "failureCount": 126, "failureRate": 0.869, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, "successRate": 0.131, "total": 145, "unresolvedFailureCount": 67 }, "vllm_fix_tokenizer": { "attributableFailureCount": 197, "decisionFailureRate": 0.9657, "decisionSuccessRate": 0.0343, "decisionTotal": 204, "failureBreakdown": { "ambiguous_runtime": 454, "backend_operator": 11, "framework_architecture_unsupported": 59, "memory_capacity": 11, "model_load": 13, "platform_infrastructure": 37, "tokenizer_compatibility": 103, "参数/模板问题": 54 }, "failureCount": 742, "failureRate": 0.9907, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 37, "successCount": 7, "successRate": 0.0093, "total": 749, "unresolvedFailureCount": 508 }, "vllm_tokenizer_patch": { "attributableFailureCount": 184, "decisionFailureRate": 0.9485, "decisionSuccessRate": 0.0515, "decisionTotal": 194, "failureBreakdown": { "ambiguous_runtime": 223, "backend_operator": 17, "context_length": 10, "framework_architecture_unsupported": 120, "memory_capacity": 2, "model_load": 27, "platform_infrastructure": 3, "repository_structure": 3, "runtime_memory": 3, "tokenizer_compatibility": 2, "参数/模板问题": 146 }, "failureCount": 556, "failureRate": 0.9823, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 10, "successRate": 0.0177, "total": 566, "unresolvedFailureCount": 369 } }, "generatedAt": "2026-10-26T06:04:02.785128+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 136, "decisionFailureRate": 0.8608, "decisionSuccessRate": 0.1392, "decisionTotal": 158, "failureBreakdown": { "ambiguous_runtime": 168, "context_length": 9, "framework_architecture_unsupported": 119, "memory_capacity": 2, "model_load": 2, "platform_infrastructure": 1, "repository_structure": 1, "tokenizer_compatibility": 3, "参数/模板问题": 78, "日志缺失": 3, "验证失败": 27 }, "failureCount": 413, "failureRate": 0.9494, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, "successRate": 0.0506, "total": 435, "unresolvedFailureCount": 276 }, "Ascend_910-b4": { "attributableFailureCount": 341, "decisionFailureRate": 0.842, "decisionSuccessRate": 0.158, "decisionTotal": 405, "failureBreakdown": { "ambiguous_runtime": 258, "context_length": 1, "framework_architecture_unsupported": 197, "memory_capacity": 19, "model_load": 85, "platform_infrastructure": 3, "repository_structure": 28, "tokenizer_compatibility": 11, "参数/模板问题": 304, "日志缺失": 14, "验证失败": 175 }, "failureCount": 1095, "failureRate": 0.9448, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 64, "successRate": 0.0552, "total": 1159, "unresolvedFailureCount": 751 }, "Biren_166m": { "attributableFailureCount": 194, "decisionFailureRate": 0.8858, "decisionSuccessRate": 0.1142, "decisionTotal": 219, "failureBreakdown": { "ambiguous_runtime": 307, "backend_operator": 4, "context_length": 10, "framework_architecture_unsupported": 126, "memory_capacity": 2, "model_load": 24, "platform_infrastructure": 2, "repository_structure": 18, "runtime_memory": 2, "tokenizer_compatibility": 8, "参数/模板问题": 229, "日志缺失": 62, "验证失败": 27 }, "failureCount": 821, "failureRate": 0.9704, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 25, "successRate": 0.0296, "total": 846, "unresolvedFailureCount": 625 }, "Cambricon_mlu-370-x4": { "attributableFailureCount": 772, "decisionFailureRate": 0.9125, "decisionSuccessRate": 0.0875, "decisionTotal": 846, "failureBreakdown": { "ambiguous_runtime": 525, "architecture_compatibility": 53, "context_length": 48, "framework_architecture_unsupported": 324, "memory_capacity": 219, "model_load": 8, "platform_infrastructure": 16, "repository_structure": 85, "tokenizer_compatibility": 35, "参数/模板问题": 321, "日志缺失": 13, "验证失败": 42 }, "failureCount": 1689, "failureRate": 0.958, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 16, "successCount": 74, "successRate": 0.042, "total": 1763, "unresolvedFailureCount": 901 }, "Cambricon_mlu-370-x8": { "attributableFailureCount": 72, "decisionFailureRate": 0.8276, "decisionSuccessRate": 0.1724, "decisionTotal": 87, "failureBreakdown": { "ambiguous_runtime": 168, "framework_architecture_unsupported": 59, "memory_capacity": 4, "model_load": 6, "platform_infrastructure": 2, "tokenizer_compatibility": 3, "参数/模板问题": 86, "验证失败": 22 }, "failureCount": 350, "failureRate": 0.9589, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 15, "successRate": 0.0411, "total": 365, "unresolvedFailureCount": 276 }, "Iluvatar_bi-100": { "attributableFailureCount": 194, "decisionFailureRate": 0.7608, "decisionSuccessRate": 0.2392, "decisionTotal": 255, "failureBreakdown": { "ambiguous_runtime": 175, "memory_capacity": 194, "platform_infrastructure": 635, "参数/模板问题": 242, "日志缺失": 134, "验证失败": 20 }, "failureCount": 1400, "failureRate": 0.9582, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 635, "successCount": 61, "successRate": 0.0418, "total": 1461, "unresolvedFailureCount": 571 }, "Iluvatar_bi-150": { "attributableFailureCount": 776, "decisionFailureRate": 0.838, "decisionSuccessRate": 0.162, "decisionTotal": 926, "failureBreakdown": { "ambiguous_runtime": 672, "architecture_compatibility": 15, "backend_operator": 12, "context_length": 29, "framework_architecture_unsupported": 266, "memory_capacity": 153, "model_load": 129, "platform_infrastructure": 21, "repository_structure": 99, "runtime_memory": 13, "tokenizer_compatibility": 60, "参数/模板问题": 351, "日志缺失": 155, "验证失败": 30 }, "failureCount": 2005, "failureRate": 0.9304, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 21, "successCount": 150, "successRate": 0.0696, "total": 2155, "unresolvedFailureCount": 1208 }, "Iluvatar_mrv-100": { "attributableFailureCount": 998, "decisionFailureRate": 0.8494, "decisionSuccessRate": 0.1506, "decisionTotal": 1175, "failureBreakdown": { "ambiguous_runtime": 356, "architecture_compatibility": 47, "backend_operator": 1, "context_length": 77, "framework_architecture_unsupported": 311, "memory_capacity": 219, "model_load": 91, "platform_infrastructure": 7, "repository_structure": 133, "runtime_memory": 1, "tokenizer_compatibility": 118, "参数/模板问题": 368, "日志缺失": 6, "验证失败": 47 }, "failureCount": 1782, "failureRate": 0.9096, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 7, "successCount": 177, "successRate": 0.0904, "total": 1959, "unresolvedFailureCount": 777 }, "Kunlunxin_p-800": { "attributableFailureCount": 99, "decisionFailureRate": 0.934, "decisionSuccessRate": 0.066, "decisionTotal": 106, "failureBreakdown": { "ambiguous_runtime": 294, "backend_operator": 23, "framework_architecture_unsupported": 37, "memory_capacity": 3, "model_load": 30, "platform_infrastructure": 1, "repository_structure": 2, "runtime_memory": 3, "tokenizer_compatibility": 1, "参数/模板问题": 61, "日志缺失": 1, "验证失败": 23 }, "failureCount": 479, "failureRate": 0.9856, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 7, "successRate": 0.0144, "total": 486, "unresolvedFailureCount": 379 }, "Kunlunxin_r-200-8f": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 140, "日志缺失": 30 }, "failureCount": 170, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "total": 170, "unresolvedFailureCount": 170 }, "MetaX_c-500": { "attributableFailureCount": 690, "decisionFailureRate": 0.8244, "decisionSuccessRate": 0.1756, "decisionTotal": 837, "failureBreakdown": { "ambiguous_runtime": 310, "architecture_compatibility": 21, "backend_operator": 45, "context_length": 60, "framework_architecture_unsupported": 215, "memory_capacity": 85, "model_load": 69, "platform_infrastructure": 5, "repository_structure": 114, "runtime_memory": 2, "tokenizer_compatibility": 79, "参数/模板问题": 462, "日志缺失": 15, "验证失败": 48 }, "failureCount": 1530, "failureRate": 0.9123, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 5, "successCount": 147, "successRate": 0.0877, "total": 1677, "unresolvedFailureCount": 835 }, "Mthreads_s4000": { "attributableFailureCount": 99, "decisionFailureRate": 0.6875, "decisionSuccessRate": 0.3125, "decisionTotal": 144, "failureBreakdown": { "ambiguous_runtime": 128, "attention_backend": 2, "backend_operator": 8, "framework_architecture_unsupported": 67, "memory_capacity": 1, "model_load": 9, "platform_infrastructure": 1, "repository_structure": 1, "runtime_memory": 5, "tokenizer_compatibility": 6, "参数/模板问题": 91, "日志缺失": 96, "验证失败": 26 }, "failureCount": 441, "failureRate": 0.9074, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 45, "successRate": 0.0926, "total": 486, "unresolvedFailureCount": 341 }, "Sunrise_pt-200-x1": { "attributableFailureCount": 804, "decisionFailureRate": 0.8825, "decisionSuccessRate": 0.1175, "decisionTotal": 911, "failureBreakdown": { "ambiguous_runtime": 167, "architecture_compatibility": 44, "backend_operator": 44, "context_length": 39, "framework_architecture_unsupported": 190, "memory_capacity": 114, "platform_infrastructure": 261, "repository_structure": 83, "runtime_memory": 1, "tokenizer_compatibility": 289, "参数/模板问题": 240, "验证失败": 32 }, "failureCount": 1504, "failureRate": 0.9336, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 261, "successCount": 107, "successRate": 0.0664, "total": 1611, "unresolvedFailureCount": 439 }, "Vastai_va16": { "attributableFailureCount": 471, "decisionFailureRate": 0.892, "decisionSuccessRate": 0.108, "decisionTotal": 528, "failureBreakdown": { "ambiguous_runtime": 829, "context_length": 9, "framework_architecture_unsupported": 205, "memory_capacity": 133, "model_load": 55, "platform_infrastructure": 14, "repository_structure": 57, "tokenizer_compatibility": 12, "参数/模板问题": 260, "日志缺失": 124, "验证失败": 130 }, "failureCount": 1828, "failureRate": 0.9698, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 14, "successCount": 57, "successRate": 0.0302, "total": 1885, "unresolvedFailureCount": 1343 }, "hygon_k100-ai": { "attributableFailureCount": 752, "decisionFailureRate": 0.9543, "decisionSuccessRate": 0.0457, "decisionTotal": 788, "failureBreakdown": { "ambiguous_runtime": 356, "architecture_compatibility": 32, "attention_backend": 1, "context_length": 46, "framework_architecture_unsupported": 262, "memory_capacity": 59, "model_load": 78, "platform_infrastructure": 4, "repository_structure": 121, "runtime_memory": 74, "tokenizer_compatibility": 79, "参数/模板问题": 446, "日志缺失": 66, "验证失败": 27 }, "failureCount": 1651, "failureRate": 0.9787, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 4, "successCount": 36, "successRate": 0.0213, "total": 1687, "unresolvedFailureCount": 895 } }, "observedGpuMemoryGiB": { "Ascend_910-b3": 64.0, "Ascend_910-b4": 32.0, "Biren_166m": 64.0, "Cambricon_mlu-370-x4": 24.0, "Cambricon_mlu-370-x8": 24.0, "Iluvatar_bi-100": 32.0, "Iluvatar_bi-150": 32.0, "Iluvatar_mrv-100": 32.0, "Kunlunxin_p-800": 100.0, "MetaX_c-500": 64.0, "Mthreads_s4000": 48.0, "Sunrise_pt-200-x1": 64.0, "Vastai_va16": 32.0, "hygon_k100-ai": 64.0 }, "pendingRecords": 0, "policyCancelledRecords": 544, "profileCombinationStats": { "Ascend_910-b3|llamacpp|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "llamacpp", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|bailing_hybrid|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 1, "memory_capacity": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|bananaall|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|cagliostro|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_tokenizer_patch", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|deepseek_v3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 14 }, "failureCount": 14, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 14, "unresolvedFailureCount": 14 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4_unified|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4|none": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gpt_oss|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gpt_oss|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|hrm_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|jais2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "参数/模板问题": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|k2_horizon|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": { "attributableFailureCount": 7, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "ambiguous_runtime": 17, "context_length": 7 }, "failureCount": 24, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 24, "unresolvedFailureCount": 17 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 0.75, "framework": "vllm_tokenizer_patch", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.25, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 3 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mini_k3|none": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "framework_architecture_unsupported": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mpt|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 2, "context_length": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|nemotron_h|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|nemotron_h|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|phi3small|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 9 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 9 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|plamo3|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|pulvis|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "platform_infrastructure": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 3 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|exl3": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none": { "attributableFailureCount": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "framework_architecture_unsupported": 6, "参数/模板问题": 1 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|torchao": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|sse_swa_moba|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|stablelm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 17 }, "failureCount": 17, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 17, "unresolvedFailureCount": 17 }, "Ascend_910-b3|vllm|text-generation|bailing_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm|text-generation|gemma4|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|gpt_oss|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Ascend_910-b3|vllm|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm|text-generation|llama|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.25, "decisionSuccessRate": 0.75, "decisionTotal": 4, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 0.25, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 3, "successRate": 0.75, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|mini_k3|none": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|muse_glimmer|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|param2moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "param2moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 8, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.1111, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 8, "successRate": 0.8889, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|zaya|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|llamacpp|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "llamacpp", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|bananaall|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|cagliostro|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4|none": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gpt_oss|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|granite|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|jais2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "参数/模板问题": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 9 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 9 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 34 }, "failureCount": 34, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 34, "unresolvedFailureCount": 34 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6, "参数/模板问题": 1 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|mini_k3|none": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|mpt|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "repository_structure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|nemotron_h|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3small|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|plamo3|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "platform_infrastructure": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 3 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|exl3": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4, "参数/模板问题": 1 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 9 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 9 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|torchao": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|sse_swa_moba|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 12 }, "failureCount": 12, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 12, "unresolvedFailureCount": 12 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|zaya|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|bailing_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm|text-generation|gemma4_unified|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|gemma4|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|gemma4|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|k2_horizon|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b4|vllm|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Ascend_910-b4|vllm|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b4|vllm|text-generation|llama|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|qwen3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Biren_166m|vllm_fix_tokenizer|text-generation|bailing_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "memory_capacity": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|bananaall|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|cagliostro|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|deepseek_v3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma4_unified|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|modelopt": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gpt_oss|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|granite|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|hrm_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|jais2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Biren_166m|vllm_fix_tokenizer|text-generation|k2_horizon|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|lfm2_moe|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 11 }, "failureCount": 11, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 11, "unresolvedFailureCount": 11 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 10 }, "failureCount": 10, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 10 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm_fix_tokenizer|text-generation|mini_k3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 17 }, "failureCount": 17, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 17, "unresolvedFailureCount": 17 }, "Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|mpt|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|muse_glimmer|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|nemotron_h|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|param2moe|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "param2moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Biren_166m|vllm_fix_tokenizer|text-generation|plamo3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|pulvis|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|gptq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 11, "参数/模板问题": 1 }, "failureCount": 12, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 12, "unresolvedFailureCount": 12 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|auto-round": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|escha": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|exl3": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 21, "参数/模板问题": 3 }, "failureCount": 24, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 24, "unresolvedFailureCount": 24 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|fp8": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 8 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 8 }, "Biren_166m|vllm_fix_tokenizer|text-generation|zaya|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm|text-generation|gemma3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|gemma4_unified|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|gpt_oss|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|lfm2|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "model_load": 2, "tokenizer_compatibility": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|llama|awq": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "model_load": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm|text-generation|llama|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.2, "decisionSuccessRate": 0.8, "decisionTotal": 5, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 0.2, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 0.8, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|mistral|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|mpt|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|muse_glimmer|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|nanbeige|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|nemotron_h|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|plamo3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|escha": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|exl3": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|gptq": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|none": { "attributableFailureCount": 7, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "framework_architecture_unsupported": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 10, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 10, "successRate": 1.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|rwkv7|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|sophia_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|spark2_5|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm|text-generation|zaya|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|lfm2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|mini_k3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|mpt|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|nemotron_h|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|qwen3_5|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|stablelm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|cagliostro|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|cohere2|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4_unified|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "验证失败": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|granite|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|jais2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "参数/模板问题": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|k2_horizon|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|lfm2_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 10 }, "failureCount": 10, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 10 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5, "参数/模板问题": 1 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|mini_k3|none": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|minicpm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|mistral|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|mpt|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|plamo3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "platform_infrastructure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm-mlu", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "framework_architecture_unsupported": 6, "参数/模板问题": 1 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|exl3": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none": { "attributableFailureCount": 11, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 11, "failureBreakdown": { "framework_architecture_unsupported": 11, "参数/模板问题": 3, "验证失败": 1 }, "failureCount": 15, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 15, "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.1111, "decisionSuccessRate": 0.8889, "decisionTotal": 9, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 0.2, "framework": "vllm-mlu", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 8, "successRate": 0.8, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|sse_swa_moba|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|stablelm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|zaya|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "验证失败": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|aquila3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|bailing_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|cohere2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Cambricon_mlu-370-x4|vllm|text-generation|gemma2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|lfm2|none": { "attributableFailureCount": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "framework_architecture_unsupported": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 10 }, "failureCount": 10, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 10 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|minicpm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|mistral|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|mpt|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x4|vllm|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|nemotron_h|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5|escha": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5|exl3": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5|none": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|spark2_5|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 11 }, "failureCount": 11, "failureRate": 1.0, "framework": "vllm", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 11, "unresolvedFailureCount": 11 }, "Cambricon_mlu-370-x4|vllm|text-generation|zaya|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|aquila3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma4|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|granite|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|hrm_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|lfm2_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|lfm2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 7, "model_load": 1 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 7 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 8 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 8 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|minicpm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|nemotron_h|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|plamo3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "platform_infrastructure": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_5|exl3": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_5|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|spark2_5|fp8": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|spark2_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|stablelm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|zaya|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|bananaall|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|cagliostro|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|cohere2|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|deepseek_v4_dspark|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma4_unified|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma4|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|jais2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "参数/模板问题": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|k2_horizon|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 0.3333, "framework": "vllm-mlu", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 0.6667, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|mini_k3|none": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "framework_architecture_unsupported": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|mistral|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|nanbeige|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3small|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|plamo3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|pulvis|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.5, "framework": "vllm-mlu", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.5, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_mtp|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5_mtp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|auto-round": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none": { "attributableFailureCount": 2, "decisionFailureRate": 0.2, "decisionSuccessRate": 0.8, "decisionTotal": 10, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1, "tokenizer_compatibility": 1 }, "failureCount": 3, "failureRate": 0.2727, "framework": "vllm-mlu", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 8, "successRate": 0.7273, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 11, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|rwkv7|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|fp8": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|sse_swa_moba|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 8 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 8 }, "Cambricon_mlu-370-x8|vllm|text-generation|aquila3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|bailing_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|cohere2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|gemma4|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|hrm_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|lfm2_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|lfm2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Cambricon_mlu-370-x8|vllm|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|minicpm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|mistral3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|mistral|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|mpt|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|nemotron_h|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|nemotron_h|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "eschamoe", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|qwen3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|stablelm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm|text-generation|zaya|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-100|transformers|text-generation|gemma4_unified|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-100|transformers|text-generation|gemma4|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "transformers", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Iluvatar_bi-100|transformers|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "transformers", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-100|transformers|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-100|transformers|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-100|transformers|text-generation|qwen3_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "transformers", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-100|transformers|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-100|transformers|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|aquila3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|bailing_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|gemma4|none": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "tokenizer_compatibility": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "transformers", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|hrm_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|lfm2_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "transformers", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Iluvatar_bi-150|transformers|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "transformers", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|transformers|text-generation|llama|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|mistral3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|mistral|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|mpt|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|nemotron_h|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|nemotron_h|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|plamo3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_5|exl3": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_5|none": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "framework_architecture_unsupported": 1, "memory_capacity": 4 }, "failureCount": 5, "failureRate": 1.0, "framework": "transformers", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|sophia_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|spark2_5|fp8": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|spark2_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|transformers|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "transformers", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|transformers|text-generation|zaya|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|bailing_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|bananaall|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|cagliostro|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.5, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.5, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|deepseek_v4_dspark|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gemma4|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gpt_oss|mxfp4": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "mxfp4", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|granite|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "参数/模板问题": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|lfm2|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|awq": { "attributableFailureCount": 5, "decisionFailureRate": 0.8333, "decisionSuccessRate": 0.1667, "decisionTotal": 6, "failureBreakdown": { "runtime_memory": 5 }, "failureCount": 5, "failureRate": 0.8333, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 1, "successRate": 0.1667, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors": { "attributableFailureCount": 3, "decisionFailureRate": 0.75, "decisionSuccessRate": 0.25, "decisionTotal": 4, "failureBreakdown": { "backend_operator": 3 }, "failureCount": 3, "failureRate": 0.75, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 0.25, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.2, "decisionSuccessRate": 0.8, "decisionTotal": 5, "failureBreakdown": { "model_load": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 0.3333, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 0.6667, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mini_k3|none": { "attributableFailureCount": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "framework_architecture_unsupported": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mpt|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|nanbeige|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|nemotron_h|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 1.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|plamo3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|pulvis|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 7, "runtime_memory": 1, "参数/模板问题": 1 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 8 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|compressed-tensors": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 1, "backend_operator": 1, "runtime_memory": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|escha": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|exl3": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|gptq": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 1, "runtime_memory": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 10, "参数/模板问题": 3 }, "failureCount": 13, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 13, "unresolvedFailureCount": 13 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.1, "decisionSuccessRate": 0.9, "decisionTotal": 10, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 0.1818, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 9, "successRate": 0.8182, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 11, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|torchao": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|sse_swa_moba|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 2, "backend_operator": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|zaya|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|aquila3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|bailing_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4_unified|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4_unified|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4|modelopt": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|jais2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|mini_k3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|modelopt": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_moe|gptq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 3, "memory_capacity": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|escha": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|exl3": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|none": { "attributableFailureCount": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "ambiguous_runtime": 1, "memory_capacity": 6 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|fp8": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|zaya|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|gemma4|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|hrm_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|lfm2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 3, "model_load": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|mpt|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|qwen3_5_moe|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm|text-generation|mpt|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm|text-generation|qwen3_5|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm|text-generation|qwen3_5|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm|text-generation|zaya|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|cagliostro|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.5, "framework": "vllm", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.5, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|gemma4_unified|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|gemma4|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|gemma4|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|gpt_oss|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|hrm_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "model_load": 3, "参数/模板问题": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 2 }, "Iluvatar_mrv-100|vllm|text-generation|k2_horizon|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|lfm2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.5, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 1, "successRate": 0.5, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 1.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 0.4286, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 0.5714, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 3 }, "Iluvatar_mrv-100|vllm|text-generation|mini_k3|none": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|plamo3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3, "参数/模板问题": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "framework_architecture_unsupported": 6, "参数/模板问题": 1 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|auto-round": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|exl3": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none": { "attributableFailureCount": 9, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 9, "failureBreakdown": { "framework_architecture_unsupported": 9 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.1111, "decisionSuccessRate": 0.8889, "decisionTotal": 9, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 0.2, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 8, "successRate": 0.8, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|rwkv7|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|smollm3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "tokenizer_compatibility": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|fp8": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 2, "framework_architecture_unsupported": 1, "tokenizer_compatibility": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 2 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_mrv-100|vllm|text-generation|sse_swa_moba|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|zaya|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|aquila3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|bailing_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|bananaall|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cagliostro|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|deepseek_v3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4_unified|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|modelopt": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|mxfp4": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "mxfp4", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|hrm_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|hy_v3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "hy_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|hyperclovax_vision_v2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "hyperclovax_vision_v2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|jais2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "参数/模板问题": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|k2_horizon|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2_moe|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 11 }, "failureCount": 11, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 11, "unresolvedFailureCount": 11 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 22 }, "failureCount": 22, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 22, "unresolvedFailureCount": 22 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6, "参数/模板问题": 1 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|mini_k3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 17 }, "failureCount": 17, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 17, "unresolvedFailureCount": 17 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|muse_glimmer|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|nemotron_h|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|param2moe|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "param2moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|plamo3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|pulvis|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 12, "参数/模板问题": 2 }, "failureCount": 14, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 14, "unresolvedFailureCount": 14 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_mtp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|exl3": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|gptq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 24, "参数/模板问题": 4 }, "failureCount": 28, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 28, "unresolvedFailureCount": 28 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_moe|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 12 }, "failureCount": 12, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 12, "unresolvedFailureCount": 12 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|fp8": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|sse_swa_moba|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 9 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 9 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|zaya|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|aquila3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|bailing_hybrid|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 1, "memory_capacity": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 8, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 8, "failureBreakdown": { "model_load": 7, "runtime_memory": 1 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gemma4|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gpt_oss|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|hrm_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|lfm2|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "model_load": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 5, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.1667, "framework": "vllm_tokenizer_patch", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 5, "successRate": 0.8333, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 1, "backend_operator": 4 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 1, "runtime_memory": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 1, "runtime_memory": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mistral|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mpt|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 1, "repository_structure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|nemotron_h|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|param2moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "param2moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|phi3small|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 1, "backend_operator": 2, "model_load": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|plamo3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_moe|gptq": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_tokenizer_patch", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|sophia_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|spark2_5|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|stablelm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 7, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "ambiguous_runtime": 3, "backend_operator": 7 }, "failureCount": 10, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm|text-generation|aquila3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm|text-generation|bailing_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|deepseek_v4|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "deepseek_v4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|hy_v3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "hy_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|hyperclovax_vision_v2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "hyperclovax_vision_v2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|lfm2_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|lfm2|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 1, "tokenizer_compatibility": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 1, "successRate": 1.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|llama|compressed-tensors": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "backend_operator": 3, "model_load": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|minicpm|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|mpt|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|nemotron_h|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|plamo3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_5_moe|gptq": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_5_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_5|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_5|escha": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_5|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|spark2_5|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "ambiguous_runtime": 1, "backend_operator": 5 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm|text-generation|zaya|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|cagliostro|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "context_length": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|gemma4|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|gemma4|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|gpt_oss|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|granite|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2, "参数/模板问题": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 2 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|k2_horizon|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|mini_k3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|plamo3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|seed_oss|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "seed_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|aquila3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|bailing_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "memory_capacity": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|deepseek_v3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|deepseek_v4_dspark|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "backend_operator": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|gemma3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|gpt_oss|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|gpt_oss|mxfp4": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "mxfp4", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|jais2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|lfm2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 6, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 6, "successRate": 1.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|compressed-tensors": { "attributableFailureCount": 15, "decisionFailureRate": 0.9375, "decisionSuccessRate": 0.0625, "decisionTotal": 16, "failureBreakdown": { "backend_operator": 15 }, "failureCount": 15, "failureRate": 0.9375, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 0.0625, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 16, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.2, "decisionSuccessRate": 0.8, "decisionTotal": 5, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 0.2, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 0.8, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|mini_k3|none": { "attributableFailureCount": 7, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "framework_architecture_unsupported": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|muse_glimmer|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 0.6667, "decisionSuccessRate": 0.3333, "decisionTotal": 3, "failureBreakdown": { "backend_operator": 2 }, "failureCount": 2, "failureRate": 0.6667, "framework": "vllm", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 0.3333, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_5_moe_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_5_mtp|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_mtp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_5_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_5|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 9, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 0.1818, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 9, "successRate": 0.8182, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 11, "unresolvedFailureCount": 2 }, "MetaX_c-500|vllm|text-generation|rwkv7|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|spark2_5|none": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 2, "model_load": 1, "tokenizer_compatibility": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|sse_swa_moba|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 7, "decisionFailureRate": 0.875, "decisionSuccessRate": 0.125, "decisionTotal": 8, "failureBreakdown": { "backend_operator": 7 }, "failureCount": 7, "failureRate": 0.875, "framework": "vllm", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 0.125, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 0 }, "Mthreads_s4000|llamacpp|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "llamacpp", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|bailing_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|cagliostro|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|deepseek_v4_dspark|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Mthreads_s4000|vllm|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|gemma4_unified|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|gemma4|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "glm_ocr", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|gpt_oss|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|granite|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|jais2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "model_load": 3, "参数/模板问题": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 2 }, "Mthreads_s4000|vllm|text-generation|k2_horizon|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|lfm2|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 5, "tokenizer_compatibility": 2 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 5 }, "Mthreads_s4000|vllm|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 5, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 0.2857, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 5, "successRate": 0.7143, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 2 }, "Mthreads_s4000|vllm|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Mthreads_s4000|vllm|text-generation|llama|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.1667, "decisionSuccessRate": 0.8333, "decisionTotal": 6, "failureBreakdown": { "ambiguous_runtime": 1, "attention_backend": 1, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 0.375, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 5, "successRate": 0.625, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 2 }, "Mthreads_s4000|vllm|text-generation|mini_k3|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|mistral|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "attention_backend": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|mpt|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|muse_glimmer|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|nanbeige|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|plamo3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|pulvis|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3_5_moe|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.0909, "decisionSuccessRate": 0.9091, "decisionTotal": 11, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 0.0909, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 10, "successRate": 0.9091, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 11, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 1, "tokenizer_compatibility": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|spark2_5|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 2, "tokenizer_compatibility": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Mthreads_s4000|vllm|text-generation|sse_swa_moba|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|zaya|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|bailing_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|bailing_moe|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "bailing_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|deepseek_v3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "tokenizer_compatibility": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4_unified|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "platform_infrastructure": 3 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|hrm_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|lfm2|none": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "tokenizer_compatibility": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|awq": { "attributableFailureCount": 7, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "backend_operator": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": { "attributableFailureCount": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "backend_operator": 2, "tokenizer_compatibility": 4 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.3333, "decisionSuccessRate": 0.6667, "decisionTotal": 3, "failureBreakdown": { "tokenizer_compatibility": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 0.5, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 0.5, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|mini_k3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "platform_infrastructure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|mistral3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|muse_glimmer|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|param2moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "param2moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "platform_infrastructure": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 9, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 9, "failureBreakdown": { "framework_architecture_unsupported": 9, "platform_infrastructure": 3, "参数/模板问题": 1 }, "failureCount": 13, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 13, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "platform_infrastructure": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_mtp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_text|auto-round": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_moe|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|spark2_5|fp8": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|spark2_5|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|stablelm|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "tokenizer_compatibility": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|aquila3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm|text-generation|cohere2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|deepseek_v4_dspark|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|gemma2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|awq": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "backend_operator": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|bitsandbytes": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "bitsandbytes", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors": { "attributableFailureCount": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "tokenizer_compatibility": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|nanbeige|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5_moe_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5_text|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "platform_infrastructure": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|gptq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "platform_infrastructure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none": { "attributableFailureCount": 9, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 9, "failureBreakdown": { "framework_architecture_unsupported": 9, "platform_infrastructure": 8, "参数/模板问题": 3 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 8, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 20, "unresolvedFailureCount": 3 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 10, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 10, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "platform_infrastructure": 3 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|zaya|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "platform_infrastructure": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.5, "framework": "vllm_fix_tokenizer", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.5, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|gemma4_unified|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|gemma4|none": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "framework_architecture_unsupported": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|granite|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|hrm_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|jais2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|lfm2_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|lfm2|none": { "attributableFailureCount": 8, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 8, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 8 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|llama|awq": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|llama|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.3333, "decisionSuccessRate": 0.6667, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 3, "model_load": 1, "参数/模板问题": 1 }, "failureCount": 5, "failureRate": 0.7143, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 0.2857, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 4 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|mini_k3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 2, "framework_architecture_unsupported": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 2 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|minicpm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|exl3": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.3333, "decisionSuccessRate": 0.6667, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 7, "model_load": 1 }, "failureCount": 8, "failureRate": 0.8, "framework": "vllm_fix_tokenizer", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 0.2, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 7 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|torchao": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|zaya|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|llamacpp|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "llamacpp", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|aquila3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|bailing_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|cagliostro|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|cohere2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "runtime_memory": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|deepseek_v3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|deepseek_v4_dspark|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 4, "runtime_memory": 1 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4_unified|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4_unified|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gpt_oss|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gpt_oss|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|hrm_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|jais2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 2, "参数/模板问题": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 3 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|k2_horizon|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none": { "attributableFailureCount": 10, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 10, "failureBreakdown": { "ambiguous_runtime": 2, "model_load": 10 }, "failureCount": 12, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 12, "unresolvedFailureCount": 2 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|awq": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 3, "runtime_memory": 2 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 3 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|compressed-tensors": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "ambiguous_runtime": 7, "runtime_memory": 5 }, "failureCount": 12, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 12, "unresolvedFailureCount": 7 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 6, "model_load": 1, "runtime_memory": 1, "参数/模板问题": 1 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 7 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|mini_k3|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|mistral3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|mistral|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|mpt|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "repository_structure": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|muse_glimmer|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|nanbeige|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|nanochat|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|phi3small|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|plamo3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "repository_structure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|prism_hadamard_qwen35|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|pulvis|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "runtime_memory": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe_text|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|auto-round": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_vl|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 7, "runtime_memory": 3 }, "failureCount": 10, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 7 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|rwkv7|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|smollm3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|torchao": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|sse_swa_moba|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|stablelm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 3, "runtime_memory": 3 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 3 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|zaya|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|bailing_hybrid|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|gemma2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|gemma4|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|gemma4|modelopt": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|llama|awq": { "attributableFailureCount": 1, "decisionFailureRate": 0.1667, "decisionSuccessRate": 0.8333, "decisionTotal": 6, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 0.1667, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 5, "successRate": 0.8333, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|llama|none": { "attributableFailureCount": 1, "decisionFailureRate": 0.5, "decisionSuccessRate": 0.5, "decisionTotal": 2, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 0.5, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.5, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|minicpm|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|mpt|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "hygon_k100-ai|vllm|text-generation|muse_glimmer|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|qwen2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|qwen3_vl|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|qwen3|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|zaya|none": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 } }, "recentCombinationStats": { "Ascend_910-b3|llamacpp|text-generation": { "attributableFailureCount": 2, "consecutiveFailures": 2, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "llamacpp", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-19T02:18:02.861795+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 3 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-25T04:12:56.440372+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Ascend_910-b3|vllm|text-generation": { "attributableFailureCount": 4, "consecutiveFailures": 4, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-09T03:34:27.161494+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-22T11:48:09.066588+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x4|unknown|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 17 }, "failureCount": 17, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-08T13:49:20.758722+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 17, "unresolvedFailureCount": 17 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation": { "attributableFailureCount": 1, "consecutiveFailures": 1, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "参数/模板问题": 7 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm-customized", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-11T07:33:18.947585+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 7 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3, "参数/模板问题": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-mlu", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-26T04:01:53.066133+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6, "参数/模板问题": 14 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm-mlu", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-08T02:21:33.753289+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 20, "unresolvedFailureCount": 20 }, "Iluvatar_bi-150|unknown|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-21T22:50:14.367494+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": { "attributableFailureCount": 2, "consecutiveFailures": 2, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 4, "framework_architecture_unsupported": 2, "参数/模板问题": 14 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-08T06:08:00.557028+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 20, "unresolvedFailureCount": 18 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-22T00:14:09.777758+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_mrv-100|unknown|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 20 }, "failureCount": 20, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-23T14:45:02.363525+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 20, "unresolvedFailureCount": 20 }, "Iluvatar_mrv-100|vllm|text-generation": { "attributableFailureCount": 6, "consecutiveFailures": 6, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 2, "model_load": 3, "tokenizer_compatibility": 1, "参数/模板问题": 13 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-23T04:21:41.197036+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 20, "unresolvedFailureCount": 14 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 13, "参数/模板问题": 6 }, "failureCount": 19, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-24T18:37:46.581678+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 19, "unresolvedFailureCount": 19 }, "MetaX_c-500|unknown|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 12 }, "failureCount": 12, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-25T07:12:33.440912+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 12, "unresolvedFailureCount": 12 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 2, "consecutiveFailures": 2, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "backend_operator": 2, "参数/模板问题": 4 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-23T01:38:31.560801+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 4 }, "MetaX_c-500|vllm|text-generation": { "attributableFailureCount": 1, "consecutiveFailures": 1, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "参数/模板问题": 5 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-21T21:16:24.481139+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 5 }, "Mthreads_s4000|unknown|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 14 }, "failureCount": 14, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-22T17:13:40.774233+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 14, "unresolvedFailureCount": 14 }, "Mthreads_s4000|vllm|text-generation": { "attributableFailureCount": 7, "consecutiveFailures": 7, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 2, "model_load": 3, "tokenizer_compatibility": 2, "参数/模板问题": 12 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-22T17:51:56.066631+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 20, "unresolvedFailureCount": 13 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1, "参数/模板问题": 6 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": "2026-10-13T21:53:36.757661+00:00", "lastTerminalAt": "2026-10-24T12:21:40.061478+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 6 }, "Sunrise_pt-200-x1|vllm|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-24T08:34:54.442493+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Vastai_va16|unknown|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 16 }, "failureCount": 16, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-08T12:56:53.956596+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 16, "unresolvedFailureCount": 16 }, "hygon_k100-ai|llamacpp|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "llamacpp", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-18T23:11:19.047759+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "hygon_k100-ai|unknown|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-11T00:13:59.966347+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-13T22:17:18.970452+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "hygon_k100-ai|vllm|text-generation": { "attributableFailureCount": 1, "consecutiveFailures": 1, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "参数/模板问题": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-22T00:14:09.777792+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 2 } }, "recentProfileCombinationStats": { "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-25T07:12:33.440966+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-25T04:12:56.440372+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|mini_k3|none": { "attributableFailureCount": 4, "consecutiveFailures": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-09T03:34:27.161494+00:00", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-25T07:12:33.441018+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-22T11:48:09.066588+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|mini_k3|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-10-10T23:28:05.253041+00:00", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|lfm2|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-10T08:03:32.765493+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-26T05:02:56.978015+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-26T04:01:53.066133+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-10T13:57:15.079577+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|bananaall|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-26T03:16:49.245755+00:00", "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|cagliostro|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-21T18:04:37.541467+00:00", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma4|modelopt": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-22T02:38:51.957756+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-24T18:37:46.581618+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|k2_horizon|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-21T01:51:56.458998+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|lfm2|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-09T19:18:55.559723+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-26T05:02:56.977978+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|nanochat|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-24T12:21:40.061449+00:00", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|plamo3|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-25T04:58:45.843600+00:00", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|pulvis|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-25T22:04:33.140633+00:00", "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-08T05:42:37.051740+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-12T18:40:58.271044+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|auto-round": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-25T18:17:13.464603+00:00", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-07T18:18:51.743140+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|smollm3|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-26T00:00:53.366349+00:00", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-10T02:14:39.447322+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-10-21T14:12:22.544249+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|bananaall|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-25T21:44:22.633947+00:00", "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|cagliostro|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-21T14:48:45.557072+00:00", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|granite|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-25T15:11:03.242666+00:00", "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-24T21:54:31.454355+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|lfm2|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-09T17:21:37.653573+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-26T05:02:56.978001+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|nanochat|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-24T12:21:40.061371+00:00", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|plamo3|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-25T01:29:02.231191+00:00", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|pulvis|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-25T19:47:09.645385+00:00", "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-12T18:40:58.271099+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-21T12:36:20.265435+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-10T00:51:39.858999+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-22T00:14:09.777758+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4|modelopt": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-21T20:36:05.464876+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|cagliostro|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-23T13:26:41.959821+00:00", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|gpt_oss|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-07T06:48:39.066266+00:00", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2, "参数/模板问题": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-25T10:51:54.257573+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 2 }, "Iluvatar_mrv-100|vllm|text-generation|k2_horizon|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-21T16:11:20.642704+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|lfm2|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-10T01:23:27.856116+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|llama|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-26T05:02:56.977985+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|nanochat|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-24T12:21:40.061430+00:00", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|plamo3|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-26T01:22:16.738778+00:00", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|smollm3|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-26T00:00:53.366362+00:00", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-11T05:28:07.648769+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-23T04:21:41.197036+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-21T16:14:40.355809+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|bananaall|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-26T02:03:00.157922+00:00", "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cagliostro|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-21T20:05:26.166988+00:00", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-22T00:14:09.777777+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|modelopt": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-22T00:35:04.572903+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-24T18:37:46.581678+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|k2_horizon|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-21T02:39:23.457372+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-10T09:26:43.784462+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-26T05:02:56.977949+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|mini_k3|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-10T08:31:17.760249+00:00", "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|nanochat|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-24T12:21:40.061459+00:00", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|plamo3|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-25T04:12:56.440398+00:00", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|pulvis|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-25T23:15:11.158495+00:00", "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-12T18:40:58.271114+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-10T18:12:14.470925+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-21T15:21:43.282221+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-23T01:38:31.560801+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|seed_oss|compressed-tensors": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-22T15:19:19.077489+00:00", "modelType": "seed_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|cagliostro|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-22T08:49:57.564469+00:00", "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|gpt_oss|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-10T08:46:52.988162+00:00", "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2, "参数/模板问题": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-24T18:37:46.581708+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 2 }, "Mthreads_s4000|vllm|text-generation|k2_horizon|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-21T13:05:59.174747+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|lfm2|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-10T00:08:25.360761+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|llama|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-26T05:02:56.977881+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|nanochat|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-24T12:21:40.061410+00:00", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|plamo3|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-25T13:59:15.965472+00:00", "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-11T01:48:37.879732+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|spark2_5|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-22T17:51:56.066631+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|spark2_5|torchao": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-22T02:28:38.939550+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|bailing_moe|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-16T17:41:11.941285+00:00", "modelType": "bailing_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-24T15:31:00.652278+00:00", "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-26T05:02:56.977902+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|nanochat|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-24T12:21:40.061478+00:00", "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_text|auto-round": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-25T18:17:13.464669+00:00", "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|smollm3|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-26T00:00:53.366285+00:00", "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|spark2_5|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-26T06:04:02.350707+00:00", "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-24T08:34:54.442493+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "hygon_k100-ai|vllm|text-generation|gemma4|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-22T00:14:09.777792+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|gemma4|modelopt": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-22T01:48:35.534554+00:00", "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 } }, "sizedProfileCombinationStats": { "Ascend_910-b3|llamacpp|text-generation|smollm3|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "llamacpp", "loadSizeLog2Bucket": 31, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|bailing_hybrid|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|bananaall|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 12, "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|cagliostro|none|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 28, "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|deepseek_v3|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 8 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 8 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma3|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4_unified|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gpt_oss|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gpt_oss|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|hrm_text|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|jais2|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|k2_horizon|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 12, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|awq|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|27": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "context_length": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 27, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "context_length": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 28, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|29": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "context_length": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 29, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 2, "context_length": 3 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 10 }, "failureCount": 10, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 10 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 0.6667, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.3333, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mini_k3|none|30": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "framework_architecture_unsupported": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mpt|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mpt|none|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 1, "context_length": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|nemotron_h|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|nemotron_h|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|phi3small|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|plamo3|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|plamo3|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|pulvis|none|23": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 23, "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 29, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "platform_infrastructure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe_text|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 12, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none|34": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 29, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|sse_swa_moba|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|stablelm|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Ascend_910-b3|vllm|text-generation|bailing_hybrid|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm|text-generation|gemma4|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|gpt_oss|compressed-tensors|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|lfm2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Ascend_910-b3|vllm|text-generation|llama|awq|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|llama|compressed-tensors|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|llama|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 3, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 3, "successRate": 1.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|mini_k3|none|30": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|muse_glimmer|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|param2moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "param2moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|qwen2|compressed-tensors|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|qwen3|none|13": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm|text-generation|qwen3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 7, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.125, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 7, "successRate": 0.875, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|zaya|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|llamacpp|text-generation|smollm3|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "llamacpp", "loadSizeLog2Bucket": 31, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|bananaall|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 12, "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|cagliostro|none|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 28, "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma2|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4|none|32": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|gpt_oss|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|granite|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|jais2|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 12, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|27": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 27, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 28, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 29, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 8 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 8 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 16 }, "failureCount": 16, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 16, "unresolvedFailureCount": 16 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5, "参数/模板问题": 1 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|mini_k3|none|30": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|mpt|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|mpt|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|nemotron_h|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3small|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|plamo3|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|plamo3|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 29, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 12, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 9 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 9 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|sse_swa_moba|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|zaya|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|gemma4_unified|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|gemma4|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|gemma4|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|k2_horizon|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Ascend_910-b4|vllm|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Ascend_910-b4|vllm|text-generation|llama|awq|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|llama|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|qwen2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|qwen3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|qwen3|none|29": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b4|vllm|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b4|vllm|text-generation|starcoder2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Ascend_910-b4|vllm|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm_fix_tokenizer|text-generation|bailing_hybrid|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|bananaall|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 12, "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|cagliostro|none|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 28, "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|deepseek_v3|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|modelopt|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gpt_oss|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|granite|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|hrm_text|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|jais2|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|k2_horizon|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|lfm2_moe|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|lfm2|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 12, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Biren_166m|vllm_fix_tokenizer|text-generation|lfm2|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|lfm2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|awq|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|27": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 27, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|mini_k3|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 17 }, "failureCount": 17, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 17, "unresolvedFailureCount": 17 }, "Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|mpt|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|muse_glimmer|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|nemotron_h|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|param2moe|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "param2moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|plamo3|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|plamo3|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|pulvis|none|23": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 23, "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen2|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe_text|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|gptq|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5, "参数/模板问题": 1 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|auto-round|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|escha|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6, "参数/模板问题": 1 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 11, "参数/模板问题": 1 }, "failureCount": 12, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 12, "unresolvedFailureCount": 12 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 29, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|torchao|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm_fix_tokenizer|text-generation|zaya|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm|text-generation|gemma3|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|gemma4_unified|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|gpt_oss|compressed-tensors|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|lfm2|none|29": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|lfm2|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|llama|awq|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|llama|awq|32": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "model_load": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm|text-generation|llama|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 4, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 1.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|mistral|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|mpt|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|mpt|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|muse_glimmer|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|nanbeige|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|nemotron_h|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|plamo3|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen2|compressed-tensors|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5_moe|compressed-tensors|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5_moe|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|escha|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|gptq|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 12, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|none|33": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3_5|none|34": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3|none|13": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 8, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 8, "successRate": 1.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|qwen3|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|rwkv7|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|spark2_5|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Biren_166m|vllm|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm|text-generation|zaya|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|lfm2|none|29": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|mini_k3|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|mpt|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|nemotron_h|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|qwen3_5|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-customized|text-generation|stablelm|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 31, "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|cagliostro|none|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 28, "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|cohere2|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4_unified|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|gemma4|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "验证失败": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|granite|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|jais2|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|k2_horizon|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|lfm2_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|lfm2|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 12, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|lfm2|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|awq|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|compressed-tensors|27": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 27, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4, "参数/模板问题": 1 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|mini_k3|none|30": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|minicpm|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|mistral|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|mpt|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|plamo3|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|plamo3|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 12, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|33": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "framework_architecture_unsupported": 5, "参数/模板问题": 1, "验证失败": 1 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|34": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3, "参数/模板问题": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|none|13": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 0.125, "decisionSuccessRate": 0.875, "decisionTotal": 8, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 0.2222, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 7, "successRate": 0.7778, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|torchao|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|sse_swa_moba|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|stablelm|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|zaya|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "验证失败": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|aquila3|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 12, "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|cohere2|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|gemma2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x4|vllm|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm|text-generation|gemma2|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|lfm2|none|29": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|lfm2|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|lfm2|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|awq|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|compressed-tensors|27": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 27, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|compressed-tensors|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 28, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Cambricon_mlu-370-x4|vllm|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|minicpm|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|mistral|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|mpt|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|mpt|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|nemotron_h|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen2|compressed-tensors|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5|escha|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5|none|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3_5|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|qwen3|none|29": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|spark2_5|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|spark2_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x4|vllm|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x4|vllm|text-generation|starcoder2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x4|vllm|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x4|vllm|text-generation|zaya|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|aquila3|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 12, "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 31, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma4|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|granite|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|hrm_text|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|lfm2_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|lfm2|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|lfm2|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 31, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|awq|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors|27": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 27, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|minicpm|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|nemotron_h|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|plamo3|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen2|compressed-tensors|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 29, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "platform_infrastructure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_5|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|spark2_5|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|spark2_5|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|stablelm|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 31, "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|zaya|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|bananaall|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 12, "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|cagliostro|none|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 28, "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|cohere2|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|deepseek_v4_dspark|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma4_unified|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma4|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|jais2|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|k2_horizon|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|lfm2|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 12, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|lfm2|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 4, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 0.2, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 0.8, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|mini_k3|none|30": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "framework_architecture_unsupported": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|mistral|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|nanbeige|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3small|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|plamo3|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|plamo3|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|pulvis|none|23": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 23, "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 30, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.5, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.5, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_mtp|none|27": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 27, "modelType": "qwen3_5_mtp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|auto-round|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none|13": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none|24": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 24, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 0.125, "decisionSuccessRate": 0.875, "decisionTotal": 8, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 0.2222, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 7, "successRate": 0.7778, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|rwkv7|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|torchao|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|sse_swa_moba|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 33, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x8|vllm|text-generation|aquila3|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 12, "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|cohere2|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|gemma4|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|hrm_text|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|lfm2_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|lfm2|none|29": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Cambricon_mlu-370-x8|vllm|text-generation|llama|awq|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|minicpm|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|mistral3|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|mistral|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|mpt|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|nemotron_h|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|nemotron_h|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_moe|eschamoe|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "eschamoe", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|qwen3_5|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|qwen3|none|29": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x8|vllm|text-generation|stablelm|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm|text-generation|zaya|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-100|transformers|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-100|transformers|text-generation|gemma4|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-100|transformers|text-generation|gemma4|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-100|transformers|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-100|transformers|text-generation|lfm2|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-100|transformers|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-100|transformers|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-100|transformers|text-generation|qwen3_5|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-100|transformers|text-generation|qwen3_5|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-100|transformers|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-100|transformers|text-generation|qwen3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-100|transformers|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|aquila3|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 12, "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|gemma4|none|32": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "tokenizer_compatibility": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|gemma4|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|hrm_text|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|lfm2_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Iluvatar_bi-150|transformers|text-generation|lfm2|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|transformers|text-generation|llama|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|mistral3|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|mistral|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|mpt|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|nemotron_h|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|nemotron_h|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|plamo3|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_5|none|33": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 1, "memory_capacity": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_5|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "memory_capacity": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|transformers|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|spark2_5|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|spark2_5|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|transformers|text-generation|zaya|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|bananaall|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 12, "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|cagliostro|none|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 28, "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.5, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.5, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|deepseek_v4_dspark|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gemma4|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gemma4|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|gpt_oss|mxfp4|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "mxfp4", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|granite|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|lfm2|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 12, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|lfm2|none|29": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|lfm2|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 1, "successRate": 1.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|awq|32": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "runtime_memory": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 28, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 1.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "backend_operator": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 4, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 0.2, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 0.8, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mini_k3|none|30": { "attributableFailureCount": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "framework_architecture_unsupported": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|mpt|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|nanbeige|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|nemotron_h|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 1.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|plamo3|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 30, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|pulvis|none|23": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 23, "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 3, "runtime_memory": 1, "参数/模板问题": 1 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|compressed-tensors|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "backend_operator": 1, "runtime_memory": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "runtime_memory": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|escha|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|gptq|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 12, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6, "参数/模板问题": 1 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none|13": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none|24": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 24, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 0.1111, "decisionSuccessRate": 0.8889, "decisionTotal": 9, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 0.1111, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 8, "successRate": 0.8889, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 31, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|sse_swa_moba|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 33, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|zaya|none|32": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|aquila3|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 12, "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4_unified|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4|modelopt|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|gemma4|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|jais2|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|lfm2|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|lfm2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|mini_k3|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|modelopt|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_moe|gptq|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "memory_capacity": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|escha|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|none|33": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "memory_capacity": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|qwen3_5|none|34": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 1, "memory_capacity": 3 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|zaya|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|gemma4|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|hrm_text|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|lfm2|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|mpt|none|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|qwen3_5_moe|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm|text-generation|mpt|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm|text-generation|qwen3_5|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm|text-generation|qwen3_5|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm|text-generation|zaya|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|cagliostro|none|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 28, "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.5, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.5, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|gemma4_unified|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|gemma4|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|gemma4|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|gpt_oss|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|hrm_text|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|k2_horizon|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|lfm2|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 12, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 1, "successRate": 1.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 1.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 4, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 0.2, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 0.8, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|llama|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|mini_k3|none|30": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|plamo3|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3, "参数/模板问题": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|auto-round|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 12, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|33": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|34": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3|none|13": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|qwen3|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 0.125, "decisionSuccessRate": 0.875, "decisionTotal": 8, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 0.2222, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 7, "successRate": 0.7778, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|rwkv7|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|smollm3|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "tokenizer_compatibility": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|torchao|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|sse_swa_moba|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_mrv-100|vllm|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|text-generation|zaya|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|aquila3|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 12, "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|bailing_hybrid|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|bananaall|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 12, "modelType": "bananaall", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cagliostro|none|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 28, "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|deepseek_v3|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma3|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|modelopt|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma4|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|mxfp4|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "mxfp4", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gpt_oss|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|hrm_text|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|hy_v3|none|36": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 36, "modelType": "hy_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|hyperclovax_vision_v2|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "hyperclovax_vision_v2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|jais2|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|k2_horizon|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2_moe|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 12, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|lfm2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 28, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 29, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 12 }, "failureCount": 12, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 12, "unresolvedFailureCount": 12 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4, "参数/模板问题": 1 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|none|36": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 36, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|mini_k3|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 17 }, "failureCount": 17, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 17, "unresolvedFailureCount": 17 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|muse_glimmer|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|nemotron_h|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|param2moe|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "param2moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|plamo3|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|pulvis|none|23": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 23, "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe_text|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5, "参数/模板问题": 1 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|36": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 36, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none|27": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 27, "modelType": "qwen3_5_mtp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|gptq|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 12, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 9, "参数/模板问题": 1 }, "failureCount": 10, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 10 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 11, "参数/模板问题": 2 }, "failureCount": 13, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 13, "unresolvedFailureCount": 13 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_moe|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|13": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|24": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 24, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 9 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 9 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|torchao|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|sse_swa_moba|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|zaya|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|aquila3|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 12, "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|bailing_hybrid|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "model_load": 4, "runtime_memory": 1 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gemma4|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gemma4|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gpt_oss|compressed-tensors|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|hrm_text|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|lfm2|none|29": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|lfm2|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 1, "successRate": 1.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.2, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 4, "successRate": 0.8, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|none|36": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 36, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 1, "runtime_memory": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mistral|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mpt|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|mpt|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|nemotron_h|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|param2moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "param2moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|phi3small|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "backend_operator": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "backend_operator": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|plamo3|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen2|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_moe|gptq|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3_5|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|qwen3|none|29": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 29, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|spark2_5|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|spark2_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|stablelm|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "backend_operator": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 1, "backend_operator": 3 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 1, "backend_operator": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm|text-generation|aquila3|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 12, "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|deepseek_v4|none|36": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 36, "modelType": "deepseek_v4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|gemma2|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|hy_v3|none|36": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 36, "modelType": "hy_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|hyperclovax_vision_v2|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "hyperclovax_vision_v2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|lfm2_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|lfm2|none|29": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|lfm2|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 1, "successRate": 1.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "backend_operator": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|llama|compressed-tensors|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|minicpm|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|mpt|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|mpt|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|nemotron_h|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "nemotron_h", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|plamo3|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_5_moe|gptq|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_5|compressed-tensors|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_5|escha|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "escha", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_5|none|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_5|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|spark2_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 1, "backend_operator": 3 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|zaya|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|cagliostro|none|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "context_length": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 28, "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|gemma4|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|gemma4|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|gpt_oss|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|granite|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|k2_horizon|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|lfm2|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 12, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|mini_k3|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|plamo3|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_text|auto-round|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|seed_oss|compressed-tensors|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 35, "modelType": "seed_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|aquila3|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 12, "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|bailing_hybrid|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|deepseek_v3|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|deepseek_v4_dspark|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|gemma3|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|gpt_oss|compressed-tensors|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|gpt_oss|mxfp4|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "mxfp4", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|jais2|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|lfm2|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 1, "successRate": 1.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 5, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 5, "successRate": 1.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|compressed-tensors|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 28, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 1.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "backend_operator": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "backend_operator": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 7, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "backend_operator": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 4, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 1.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|mini_k3|none|30": { "attributableFailureCount": 7, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "framework_architecture_unsupported": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|muse_glimmer|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 2, "decisionFailureRate": 0.6667, "decisionSuccessRate": 0.3333, "decisionTotal": 3, "failureBreakdown": { "backend_operator": 2 }, "failureCount": 2, "failureRate": 0.6667, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 0.3333, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_5_moe_text|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_5_mtp|none|27": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 27, "modelType": "qwen3_5_mtp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_5_text|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_5|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_5|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|qwen3|none|13": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|qwen3|none|24": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 24, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|qwen3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 8, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.1111, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 8, "successRate": 0.8889, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|rwkv7|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|rwkv7|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|spark2_5|none|31": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|spark2_5|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 1, "tokenizer_compatibility": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|sse_swa_moba|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "backend_operator": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "backend_operator": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 2, "decisionFailureRate": 0.6667, "decisionSuccessRate": 0.3333, "decisionTotal": 3, "failureBreakdown": { "backend_operator": 2 }, "failureCount": 2, "failureRate": 0.6667, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 1, "successRate": 0.3333, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Mthreads_s4000|llamacpp|text-generation|smollm3|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "llamacpp", "loadSizeLog2Bucket": 31, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|bailing_hybrid|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|cagliostro|none|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 28, "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|deepseek_v4_dspark|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Mthreads_s4000|vllm|text-generation|gemma2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|gemma4_unified|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|gemma4|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|gemma4|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|glm_ocr|fp8|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "glm_ocr", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|gpt_oss|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|granite|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|jais2|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|k2_horizon|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|lfm2|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 12, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|lfm2|none|29": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Mthreads_s4000|vllm|text-generation|lfm2|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 1, "successRate": 1.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.2, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 4, "successRate": 0.8, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|llama|awq|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Mthreads_s4000|vllm|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Mthreads_s4000|vllm|text-generation|llama|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|llama|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 0.2, "decisionSuccessRate": 0.8, "decisionTotal": 5, "failureBreakdown": { "attention_backend": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 0.3333, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 0.6667, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|llama|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|mini_k3|none|30": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|mistral|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "attention_backend": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|mpt|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|muse_glimmer|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|nanbeige|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|plamo3|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|pulvis|none|23": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 23, "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3_5_moe|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3_5_moe|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3|none|13": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 0.1111, "decisionSuccessRate": 0.8889, "decisionTotal": 9, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 0.1111, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 8, "successRate": 0.8889, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|qwen3|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|spark2_5|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|spark2_5|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|spark2_5|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 1, "tokenizer_compatibility": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Mthreads_s4000|vllm|text-generation|spark2_5|torchao|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|sse_swa_moba|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|zaya|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|bailing_moe|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "bailing_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|deepseek_v3|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "tokenizer_compatibility": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma3|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4_unified|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "platform_infrastructure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|hrm_text|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|lfm2|none|29": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|lfm2|none|30": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|lfm2|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|awq|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|awq|32": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "backend_operator": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|awq|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|29": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 29, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 0.3333, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 0.6667, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|mini_k3|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "platform_infrastructure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|mistral3|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|muse_glimmer|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|param2moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "param2moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen2|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "platform_infrastructure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|33": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4, "platform_infrastructure": 1 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4, "platform_infrastructure": 2, "参数/模板问题": 1 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none|27": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 27, "modelType": "qwen3_5_mtp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "platform_infrastructure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 28, "modelType": "qwen3_5_mtp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_text|auto-round|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_moe|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3|none|24": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 24, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|spark2_5|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|spark2_5|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|stablelm|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|aquila3|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 12, "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm|text-generation|cohere2|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|deepseek_v4_dspark|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|gemma2|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|lfm2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|awq|32": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "backend_operator": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|awq|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|bitsandbytes|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "bitsandbytes", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors|27": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 27, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 28, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "tokenizer_compatibility": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|nanbeige|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5_moe_text|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "platform_infrastructure": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|gptq|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "gptq", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 12, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|33": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3, "platform_infrastructure": 4, "参数/模板问题": 1 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 4, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|34": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "framework_architecture_unsupported": 5, "platform_infrastructure": 3, "参数/模板问题": 1 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3|none|13": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 8, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 8, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|zaya|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "platform_infrastructure": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.5, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.5, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|gemma4_unified|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|gemma4|none|32": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|gemma4|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|granite|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "granite", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|hrm_text|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|jais2|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|lfm2_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|lfm2|none|29": { "attributableFailureCount": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "model_load": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|lfm2|none|30": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|lfm2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|llama|awq|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|llama|awq|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|llama|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|llama|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 3, "参数/模板问题": 1 }, "failureCount": 4, "failureRate": 0.8, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.2, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|llama|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|mini_k3|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 2, "framework_architecture_unsupported": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 2 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|minicpm|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|exl3|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "exl3", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 12, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3|none|13": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 0.3333, "decisionSuccessRate": 0.6667, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 6, "model_load": 1 }, "failureCount": 7, "failureRate": 0.7778, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 0.2222, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 6 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|zaya|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|llamacpp|text-generation|smollm3|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "llamacpp", "loadSizeLog2Bucket": 31, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|aquila3|none|12": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 12, "modelType": "aquila3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|bailing_hybrid|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|cagliostro|none|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 28, "modelType": "cagliostro", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|cohere2|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "runtime_memory": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|deepseek_v3|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 35, "modelType": "deepseek_v3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|deepseek_v4_dspark|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "deepseek_v4_dspark", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma2|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 2, "runtime_memory": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 2 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma2|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma3|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 35, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4_unified|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4_unified|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gemma4_unified", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gemma4|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gpt_oss|compressed-tensors|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 35, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gpt_oss|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "gpt_oss", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|hrm_text|none|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 31, "modelType": "hrm_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|jais2|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "jais2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|k2_horizon|compressed-tensors|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|k2_horizon|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, "参数/模板问题": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|k2_horizon|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "k2_horizon", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2_moe|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "lfm2_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none|12": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 12, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none|29": { "attributableFailureCount": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "model_load": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 29, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none|30": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 30, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none|31": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 31, "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|awq|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|awq|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 3, "runtime_memory": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 3 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|compressed-tensors|27": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 27, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|compressed-tensors|28": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 28, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|compressed-tensors|30": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "runtime_memory": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "runtime_memory": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|compressed-tensors|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 2, "runtime_memory": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 2 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|compressed-tensors|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 35, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 31, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 4, "runtime_memory": 1, "参数/模板问题": 1 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 5 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|mini_k3|none|30": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 30, "modelType": "mini_k3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|mistral3|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "mistral3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|mistral|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "mistral", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|mpt|none|33": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "repository_structure": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|muse_glimmer|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 35, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|nanbeige|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "nanbeige", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|nanochat|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "nanochat", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|phi3small|compressed-tensors|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "phi3small", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|phi3|compressed-tensors|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 31, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|phi3|compressed-tensors|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|phi3|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "phi3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|plamo3|none|30": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 30, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|plamo3|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|prism_hadamard_qwen35|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "prism_hadamard_qwen35", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|pulvis|none|23": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 23, "modelType": "pulvis", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen2|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 31, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen2|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe_text|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|compressed-tensors|34": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_moe|none|35": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|auto-round|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "auto-round", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5_text|none|35": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 35, "modelType": "qwen3_5_text", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none|33": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3|none|13": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 13, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 7, "runtime_memory": 2 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 7 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|rwkv7|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "rwkv7", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|smollm3|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "smollm3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|compressed-tensors|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 31, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|spark2_5|torchao|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "torchao", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|sse_swa_moba|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "sse_swa_moba", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|stablelm|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 31, "modelType": "stablelm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 1, "runtime_memory": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|starcoder2|compressed-tensors|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|starcoder2|compressed-tensors|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "runtime_memory": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 34, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|zaya|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|bailing_hybrid|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "bailing_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|gemma2|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|gemma3|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|gemma4|compressed-tensors|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|gemma4|modelopt|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "gemma4", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "modelopt", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|llama|awq|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|llama|awq|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 5, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 5, "successRate": 1.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|llama|none|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 30, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|llama|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 1.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|minicpm|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "minicpm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|mpt|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|mpt|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "mpt", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|muse_glimmer|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "muse_glimmer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|qwen2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, "modelType": "qwen3_vl", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|qwen3|none|29": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 29, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|qwen3|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 33, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|sophia_hybrid|none|31": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "spark2_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "fp8", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|starcoder2|compressed-tensors|31": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 31, "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm|text-generation|zaya|none|32": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 } }, "terminalRecords": 18145, "totalRecords": 18689, "totals": { "attributableFailureCount": 6398, "decisionFailureRate": 0.8664, "decisionSuccessRate": 0.1336, "decisionTotal": 7385, "failureBreakdown": { "ambiguous_runtime": 4713, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 137, "context_length": 328, "framework_architecture_unsupported": 2378, "memory_capacity": 1207, "model_load": 586, "platform_infrastructure": 973, "repository_structure": 742, "runtime_memory": 101, "tokenizer_compatibility": 704, "参数/模板问题": 3679, "日志缺失": 719, "验证失败": 676 }, "failureCount": 17158, "failureRate": 0.9456, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 973, "successCount": 987, "successRate": 0.0544, "total": 18145, "unresolvedFailureCount": 9787 }, "warnings": [ "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b3|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 MetaX_c-500|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" ] }, "storageMode": "decision_state_only", "summarizedRecords": 18689, "version": 1 }