{ "generatedAt": "2026-10-10T18:42:58.221167+00:00", "lastSyncTime": "2026-10-10T18:42:58.165451+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { "ascend_910-b3|vllm_tokenizer_patch|text-generation|architectures:bailingmoev2_5forcausallm": { "architectureSignature": "architectures:bailingmoev2_5forcausallm", "architectures": [ "bailingmoev2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-21T11:00:23.698765+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-21T11:00:23.698765+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "JANGQ-AI/Ling-2.6-flash-JANGTQ" ], "sourceTaskIds": [ "4999567" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm_tokenizer_patch|text-generation|architectures:phi3smallforcausallm": { "architectureSignature": "architectures:phi3smallforcausallm", "architectures": [ "phi3smallforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-21T11:18:21.960935+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-21T11:18:21.960935+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "phi3small", "sourceModelIds": [ "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16" ], "sourceTaskIds": [ "4999762" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "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_tokenizer_patch|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-14T20:36:23.395422+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-14T20:36:23.395422+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ "4856934" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 5, "expiresAt": "2026-10-21T19:37:12.459191+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-21T19:37:12.459191+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-decay-g2-v2_C", "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "nkkbr/Mini-K3-1H-decay-g16-v2_B" ], "sourceTaskIds": [ "5006360", "5006359", "5006364", "5006357", "5006356" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:muse_glimmer": { "architectureSignature": "model_type:muse_glimmer", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:51.840741+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T02:52:51.840741+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "muse_glimmer", "sourceModelIds": [ "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit" ], "sourceTaskIds": [ "4969068" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:51.846373+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T02:52:51.846373+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU" ], "sourceTaskIds": [ "4969063" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:09:18.238662+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T03:09:18.238662+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit" ], "sourceTaskIds": [ "4969344" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:qwen3_vl": { "architectureSignature": "model_type:qwen3_vl", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:51.740561+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T02:52:51.740561+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_vl", "sourceModelIds": [ "BAAI/RoboBrain2.5-8B-MT" ], "sourceTaskIds": [ "4969062" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm|text-generation|architectures:nanbeigeforcausallm": { "architectureSignature": "architectures:nanbeigeforcausallm", "architectures": [ "nanbeigeforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-14T17:25:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-14T17:25:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "nanbeige/Nanbeige4.2-3B-GPTQ-Int8" ], "sourceTaskIds": [ "4589952" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-13T03:21:22+00:00", "framework": "vllm", "latestFailureAt": "2026-09-13T03:21:22+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "XHToken/Spark-X2.5-1.7B" ], "sourceTaskIds": [ "4558358" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm|text-generation|model_type:deepseek_v4_dspark": { "architectureSignature": "model_type:deepseek_v4_dspark", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-15T15:57:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-15T15:57:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "deepseek_v4_dspark", "sourceModelIds": [ "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX" ], "sourceTaskIds": [ "4580781" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-20T03:09:18.043058+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:09:18.043058+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ "4969336", "4969334" ], "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-b3|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-12T13:37:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-12T13:37:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4546528" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-21T16:37:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T16:37:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality" ], "sourceTaskIds": [ "4332638" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-15T19:37:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-15T19:37:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit" ], "sourceTaskIds": [ "4588681" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm|text-generation|model_type:rwkv7": { "architectureSignature": "model_type:rwkv7", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-14T23:57:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-14T23:57:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "rwkv7", "sourceModelIds": [ "RWKV/RWKV7-7.2B-20260805" ], "sourceTaskIds": [ "4591876" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:09:18.038960+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:09:18.038960+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M" ], "sourceTaskIds": [ "4969337" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b4|vllm_tokenizer_patch|text-generation|architectures:phi3smallforcausallm": { "architectureSignature": "architectures:phi3smallforcausallm", "architectures": [ "phi3smallforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-20T18:09:15.239723+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T18:09:15.239723+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "phi3small", "sourceModelIds": [ "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16" ], "sourceTaskIds": [ "4985114" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm_tokenizer_patch|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-23T15:05:50.784052+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-23T15:05:50.784052+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "cyankiwi/Spark-X2.5-4B-AWQ-INT4" ], "sourceTaskIds": [ "5042147" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm_tokenizer_patch|text-generation|architectures:sseswamobaforcausallm": { "architectureSignature": "architectures:sseswamobaforcausallm", "architectures": [ "sseswamobaforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-22T03:14:37.507855+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-22T03:14:37.507855+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "Panyuqi/SpikingBrain-2.0-base-8k" ], "sourceTaskIds": [ "5011473" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:51.042323+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T02:52:51.042323+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ "4969022" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:gemma4_unified": { "architectureSignature": "model_type:gemma4_unified", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:43.767336+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T02:52:43.767336+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4_unified", "sourceModelIds": [ "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ "4969004" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-21T19:05:50.437924+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-21T19:05:50.437924+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-decay-g16-v2_B", "nkkbr/Mini-K3-1H-attnres-block6-v1_C" ], "sourceTaskIds": [ "5006050", "5006054" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:43.745571+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T02:52:43.745571+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4" ], "sourceTaskIds": [ "4969000" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:43.746995+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T02:52:43.746995+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed" ], "sourceTaskIds": [ "4968998" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:50.869403+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T02:52:50.869403+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit" ], "sourceTaskIds": [ "4969009" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm|text-generation|architectures:nanbeigeforcausallm": { "architectureSignature": "architectures:nanbeigeforcausallm", "architectures": [ "nanbeigeforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-14T16:03:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-14T16:03:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "nanbeige/Nanbeige4.2-3B-GPTQ-Int8" ], "sourceTaskIds": [ "4332392" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-13T02:47:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-13T02:47:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "XHToken/Spark-X2.5-1.7B" ], "sourceTaskIds": [ "4557197" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm|text-generation|model_type:deepseek_v4_dspark": { "architectureSignature": "model_type:deepseek_v4_dspark", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-15T20:09:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-15T20:09:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "deepseek_v4_dspark", "sourceModelIds": [ "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX" ], "sourceTaskIds": [ "4579078" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-12T14:11:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-12T14:11:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4543480" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-17T03:21:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-17T03:21:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121" ], "sourceTaskIds": [ "4610340" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-15T20:57:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-15T20:57:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit" ], "sourceTaskIds": [ "4576625" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm|text-generation|model_type:qwen3_vl": { "architectureSignature": "model_type:qwen3_vl", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:25:33.083868+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:25:33.083868+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_vl", "sourceModelIds": [ "BAAI/RoboBrain2.5-8B-MT" ], "sourceTaskIds": [ "4969694" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm|text-generation|model_type:rwkv7": { "architectureSignature": "model_type:rwkv7", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-14T23:09:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-14T23:09:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "rwkv7", "sourceModelIds": [ "RWKV/RWKV7-7.2B-20260805" ], "sourceTaskIds": [ "4588001" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "biren_166m|vllm|text-generation|architectures:sophiaforcausallm": { "architectureSignature": "architectures:sophiaforcausallm", "architectures": [ "sophiaforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-19T17:18:17.894388+00:00", "framework": "vllm", "latestFailureAt": "2026-09-19T17:18:17.894388+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "Arain119/Sophia" ], "sourceTaskIds": [ "4960871" ], "targetGpu": "Biren_166m", "taskType": "text-generation" }, "biren_166m|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:41:49.061655+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:41:49.061655+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4" ], "sourceTaskIds": [ "4970007" ], "targetGpu": "Biren_166m", "taskType": "text-generation" }, "biren_166m|vllm|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T04:02:45.346171+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T04:02:45.346171+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M" ], "sourceTaskIds": [ "4970445" ], "targetGpu": "Biren_166m", "taskType": "text-generation" }, "cambricon_mlu-370-x4|vllm-customized|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-22T05:27:11.098010+00:00", "framework": "vllm-customized", "latestFailureAt": "2026-09-22T05:27:11.098010+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed" ], "sourceTaskIds": [ "5012909" ], "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation" }, "cambricon_mlu-370-x4|vllm-mlu|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-21T23:42:59.367573+00:00", "framework": "vllm-mlu", "latestFailureAt": "2026-09-21T23:42:59.367573+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-decay-g1-v2_B", "nkkbr/Mini-K3-1H-attnres-standard-v1_B" ], "sourceTaskIds": [ "5009080", "5009079" ], "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation" }, "cambricon_mlu-370-x4|vllm|text-generation|model_type:lfm2": { "architectureSignature": "model_type:lfm2", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-22T05:27:11.087107+00:00", "framework": "vllm", "latestFailureAt": "2026-09-22T05:27:11.087107+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "lfm2", "sourceModelIds": [ "mlx-community/LFM2.5-1.2B-Thinking-6bit" ], "sourceTaskIds": [ "5012911" ], "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation" }, "cambricon_mlu-370-x4|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:52.152592+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T02:52:52.152592+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4969082" ], "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation" }, "cambricon_mlu-370-x4|vllm|text-generation|model_type:qwen3_5_text": { "architectureSignature": "model_type:qwen3_5_text", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:52.089383+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T02:52:52.089383+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_text", "sourceModelIds": [ "TokenRhythm/NeoHorse-1-9B" ], "sourceTaskIds": [ "4969078" ], "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation" }, "cambricon_mlu-370-x4|vllm|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-21T17:14:32.848203+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T17:14:32.848203+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/AppleScript-8B-JANG_4M" ], "sourceTaskIds": [ "5004582" ], "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-customized|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T12:30:15.535777+00:00", "framework": "vllm-customized", "latestFailureAt": "2026-09-20T12:30:15.535777+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "mlx-community/gemma-4-e2b-it-OptiQ-4bit" ], "sourceTaskIds": [ "4978792" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-customized|text-generation|model_type:gemma4_unified": { "architectureSignature": "model_type:gemma4_unified", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-21T07:04:01.182302+00:00", "framework": "vllm-customized", "latestFailureAt": "2026-09-21T07:04:01.182302+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4_unified", "sourceModelIds": [ "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ "4995699" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-customized|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-21T08:37:39.043820+00:00", "framework": "vllm-customized", "latestFailureAt": "2026-09-21T08:37:39.043820+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4997240" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-customized|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-20T03:41:49.651764+00:00", "framework": "vllm-customized", "latestFailureAt": "2026-09-20T03:41:49.651764+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "ornith-ai/Ornith-1.5-9B-NVFP4" ], "sourceTaskIds": [ "4970045", "4970040" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-customized|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:57:37.896737+00:00", "framework": "vllm-customized", "latestFailureAt": "2026-09-20T03:57:37.896737+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B" ], "sourceTaskIds": [ "4970334" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-customized|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T09:50:15.447427+00:00", "framework": "vllm-customized", "latestFailureAt": "2026-09-20T09:50:15.447427+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M" ], "sourceTaskIds": [ "4976743" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-mlu|text-generation|architectures:sseswamobaforcausallm": { "architectureSignature": "architectures:sseswamobaforcausallm", "architectures": [ "sseswamobaforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-22T05:48:17.265295+00:00", "framework": "vllm-mlu", "latestFailureAt": "2026-09-22T05:48:17.265295+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "Panyuqi/SpikingBrain-2.0-base-8k" ], "sourceTaskIds": [ "5013248" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 5, "expiresAt": "2026-10-21T19:52:49.757664+00:00", "framework": "vllm-mlu", "latestFailureAt": "2026-09-21T19:52:49.757664+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-decay-g16-v2_B", "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "nkkbr/Mini-K3-1H-decay-g2-v2_C", "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "nkkbr/Mini-K3-1H-attnres-standard-v1_B" ], "sourceTaskIds": [ "5006516", "5006518", "5006512", "5006511", "5006510" ], "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" }, "cambricon_mlu-370-x8|vllm|text-generation|architectures:cohere2forcausallm": { "architectureSignature": "architectures:cohere2forcausallm", "architectures": [ "cohere2forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:51.937617+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T02:52:51.937617+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "CohereLabs/tiny-aya-en-thinker" ], "sourceTaskIds": [ "4969071" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|architectures:nemotronhforcausallm": { "architectureSignature": "architectures:nemotronhforcausallm", "architectures": [ "nemotronhforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-20T03:57:37.815898+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:57:37.815898+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4" ], "sourceTaskIds": [ "4970328" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 2, "expiresAt": "2026-10-20T03:41:49.149678+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:41:49.149678+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "XHToken/Spark-X2.5-1.7B", "XHToken/Spark-X2.5-4B-FP8" ], "sourceTaskIds": [ "4970015", "4970013" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T04:26:51.246271+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T04:26:51.246271+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "mlx-community/gemma-4-e4b-it-OptiQ-4bit" ], "sourceTaskIds": [ "4970731" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:gemma4_unified": { "architectureSignature": "model_type:gemma4_unified", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T04:42:19.135971+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T04:42:19.135971+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4_unified", "sourceModelIds": [ "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ "4970924" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:lfm2": { "architectureSignature": "model_type:lfm2", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:57:37.773695+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:57:37.773695+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "lfm2", "sourceModelIds": [ "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit" ], "sourceTaskIds": [ "4970322" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:lfm2_moe": { "architectureSignature": "model_type:lfm2_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T04:09:56.546014+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T04:09:56.546014+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "lfm2_moe", "sourceModelIds": [ "LiquidAI/LFM2.5-8B-A1B" ], "sourceTaskIds": [ "4970502" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:mistral3": { "architectureSignature": "model_type:mistral3", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T04:42:19.140494+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T04:42:19.140494+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mistral3", "sourceModelIds": [ "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit" ], "sourceTaskIds": [ "4970923" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:muse_glimmer": { "architectureSignature": "model_type:muse_glimmer", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T04:02:52.182815+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T04:02:52.182815+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "muse_glimmer", "sourceModelIds": [ "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit" ], "sourceTaskIds": [ "4970446" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:25:32.355365+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:25:32.355365+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4969654" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3": { "architectureSignature": "model_type:qwen3", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T04:02:52.200512+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T04:02:52.200512+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3", "sourceModelIds": [ "whcl412/mlx-LycheeAI-coder-1.7b" ], "sourceTaskIds": [ "4970447" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3_5_text": { "architectureSignature": "model_type:qwen3_5_text", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-20T03:25:32.347313+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:25:32.347313+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_text", "sourceModelIds": [ "TokenRhythm/NeoHorse-1-4B", "TokenRhythm/NeoHorse-1-9B" ], "sourceTaskIds": [ "4969653", "4969652" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3_vl": { "architectureSignature": "model_type:qwen3_vl", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:58:35.455197+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:58:35.455197+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_vl", "sourceModelIds": [ "BAAI/RoboBrain2.5-8B-MT" ], "sourceTaskIds": [ "4970358" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:25:32.350531+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:25:32.350531+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M" ], "sourceTaskIds": [ "4969656" ], "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:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:41:49.472121+00:00", "framework": "vllm-patch-tokenizer", "latestFailureAt": "2026-09-20T03:41:49.472121+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "mlx-community/gemma-4-e2b-it-OptiQ-4bit" ], "sourceTaskIds": [ "4970033" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-22T00:42:42.844085+00:00", "framework": "vllm-patch-tokenizer", "latestFailureAt": "2026-09-22T00:42:42.844085+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-attnres-standard-v1_B" ], "sourceTaskIds": [ "5009809" ], "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": 2, "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", "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX" ], "sourceTaskIds": [ "5320526", "5320018" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:52.043508+00:00", "framework": "vllm-patch-tokenizer", "latestFailureAt": "2026-09-20T02:52:52.043508+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "mlx-community/XYZ-Aquila-mini-OptiQ-4bit" ], "sourceTaskIds": [ "4969075" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-20T03:09:18.999314+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:09:18.999314+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "spark2_5", "sourceModelIds": [ "XHToken/Spark-X2.5-4B-FP8" ], "sourceTaskIds": [ "4969388" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-13T00:07:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-13T00:07:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "nv-community/Gemma-4-31B-IT-NVFP4" ], "sourceTaskIds": [ "4079956" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-12T08:13:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-12T08:13:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4543517" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-21T14:47:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T14:47:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality" ], "sourceTaskIds": [ "4586965", "4584252" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-21T10:23:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T10:23:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit" ], "sourceTaskIds": [ "4609105" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm|text-generation|model_type:qwen3_vl": { "architectureSignature": "model_type:qwen3_vl", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-22T05:27:11.085801+00:00", "framework": "vllm", "latestFailureAt": "2026-09-22T05:27:11.085801+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_vl", "sourceModelIds": [ "BAAI/RoboBrain2.5-8B-MT" ], "sourceTaskIds": [ "5012910" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm|text-generation|model_type:rwkv7": { "architectureSignature": "model_type:rwkv7", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-15T15:26:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-15T15:26:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "rwkv7", "sourceModelIds": [ "RWKV/RWKV7-7.2B-20260805" ], "sourceTaskIds": [ "4609108" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:09:19.035946+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:09:19.035946+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/AppleScript-8B-JANG_4M" ], "sourceTaskIds": [ "4969390" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "iluvatar_bi-150|transformers|text-generation|architectures:nemotronhforcausallm": { "architectureSignature": "architectures:nemotronhforcausallm", "architectures": [ "nemotronhforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-20T09:13:31.862874+00:00", "framework": "transformers", "latestFailureAt": "2026-09-20T09:13:31.862874+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4974770" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|transformers|text-generation|architectures:qwen3_5forconditionalgeneration": { "architectureSignature": "architectures:qwen3_5forconditionalgeneration", "architectures": [ "qwen3_5forconditionalgeneration" ], "evidenceCount": 1, "expiresAt": "2026-10-20T09:04:12.649418+00:00", "framework": "transformers", "latestFailureAt": "2026-09-20T09:04:12.649418+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "qwen3_5", "sourceModelIds": [ "ornith-ai/Ornith-1.5-9B-NVFP4" ], "sourceTaskIds": [ "4974501" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|transformers|text-generation|architectures:qwen3_5moeforconditionalgeneration": { "architectureSignature": "architectures:qwen3_5moeforconditionalgeneration", "architectures": [ "qwen3_5moeforconditionalgeneration" ], "evidenceCount": 1, "expiresAt": "2026-10-20T08:53:34.985766+00:00", "framework": "transformers", "latestFailureAt": "2026-09-20T08:53:34.985766+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "qwen3_5_moe", "sourceModelIds": [ "ornith-ai/Ornith-1.5-35B-A3B-NVFP4" ], "sourceTaskIds": [ "4974282" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|transformers|text-generation|architectures:qwen3vlforconditionalgeneration": { "architectureSignature": "architectures:qwen3vlforconditionalgeneration", "architectures": [ "qwen3vlforconditionalgeneration" ], "evidenceCount": 1, "expiresAt": "2026-10-20T04:15:36.954828+00:00", "framework": "transformers", "latestFailureAt": "2026-09-20T04:15:36.954828+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "qwen3_vl", "sourceModelIds": [ "BAAI/RoboBrain2.5-8B-MT" ], "sourceTaskIds": [ "4970615" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|transformers|text-generation|architectures:zayaforcausallm": { "architectureSignature": "architectures:zayaforcausallm", "architectures": [ "zayaforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-21T14:20:21.627234+00:00", "framework": "transformers", "latestFailureAt": "2026-09-21T14:20:21.627234+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/AppleScript-8B-JANG_4M" ], "sourceTaskIds": [ "5002168" ], "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_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-20T03:58:35.464742+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "latestFailureAt": "2026-09-20T03:58:35.464742+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit", "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ "4970359", "4970350" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|model_type:gemma4_unified": { "architectureSignature": "model_type:gemma4_unified", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T04:26:45.138158+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "latestFailureAt": "2026-09-20T04:26:45.138158+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4_unified", "sourceModelIds": [ "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ "4970728" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-22T02:44:31.355275+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "latestFailureAt": "2026-09-22T02:44:31.355275+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-decay-g1-v2_B" ], "sourceTaskIds": [ "5011150" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:46:35.783924+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "latestFailureAt": "2026-09-20T03:46:35.783924+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M" ], "sourceTaskIds": [ "4970117" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm_tokenizer_patch|text-generation|architectures:gemma4forconditionalgeneration": { "architectureSignature": "architectures:gemma4forconditionalgeneration", "architectures": [ "gemma4forconditionalgeneration" ], "evidenceCount": 2, "expiresAt": "2026-10-21T12:10:32.451262+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-21T12:10:32.451262+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "gemma4", "sourceModelIds": [ "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "mlx-community/gemma-4-e4b-it-OptiQ-4bit" ], "sourceTaskIds": [ "5000554", "5000551" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm_tokenizer_patch|text-generation|architectures:qwen3_5moeforconditionalgeneration": { "architectureSignature": "architectures:qwen3_5moeforconditionalgeneration", "architectures": [ "qwen3_5moeforconditionalgeneration" ], "evidenceCount": 1, "expiresAt": "2026-10-21T18:14:20.635969+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-21T18:14:20.635969+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "qwen3_5_moe", "sourceModelIds": [ "ornith-ai/Ornith-1.5-35B-A3B-NVFP4" ], "sourceTaskIds": [ "5005325" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm|text-generation|architectures:qwen3_5forconditionalgeneration": { "architectureSignature": "architectures:qwen3_5forconditionalgeneration", "architectures": [ "qwen3_5forconditionalgeneration" ], "evidenceCount": 1, "expiresAt": "2026-10-20T03:09:19.100832+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:09:19.100832+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "qwen3_5", "sourceModelIds": [ "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8" ], "sourceTaskIds": [ "4969395" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm|text-generation|architectures:qwen3_5moeforconditionalgeneration": { "architectureSignature": "architectures:qwen3_5moeforconditionalgeneration", "architectures": [ "qwen3_5moeforconditionalgeneration" ], "evidenceCount": 1, "expiresAt": "2026-10-20T03:09:19.090425+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T03:09:19.090425+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "qwen3_5_moe", "sourceModelIds": [ "cyankiwi/Apodex-1.1-mini-AWQ-INT4" ], "sourceTaskIds": [ "4969392" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm|text-generation|architectures:qwen3vlforconditionalgeneration": { "architectureSignature": "architectures:qwen3vlforconditionalgeneration", "architectures": [ "qwen3vlforconditionalgeneration" ], "evidenceCount": 1, "expiresAt": "2026-10-20T05:16:13.351034+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T05:16:13.351034+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "qwen3_vl", "sourceModelIds": [ "BAAI/RoboBrain2.5-8B-MT" ], "sourceTaskIds": [ "4971313" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-13T01:11:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-13T01:11:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "XHToken/Spark-X2.5-1.7B" ], "sourceTaskIds": [ "4557834" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm|text-generation|architectures:zayaforcausallm": { "architectureSignature": "architectures:zayaforcausallm", "architectures": [ "zayaforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-21T10:50:31.253072+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T10:50:31.253072+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M" ], "sourceTaskIds": [ "4999408" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-12T07:33:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-12T07:33:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4547660" ], "targetGpu": "Iluvatar_bi-150", "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:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 3, "expiresAt": "2026-10-22T00:12:27.760772+00:00", "framework": "vllm", "latestFailureAt": "2026-09-22T00:12:27.760772+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "nkkbr/Mini-K3-1H-decay-g2-v2_C", "nkkbr/Mini-K3-1H-decay-g16-v2_B" ], "sourceTaskIds": [ "5009428", "5009242", "5009101" ], "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation" }, "iluvatar_mrv-100|vllm|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-21T19:52:49.754157+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T19:52:49.754157+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "prithivMLmods/Nexus-9B-CodeCore-Merge" ], "sourceTaskIds": [ "5006513" ], "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation" }, "kunlunxin_p-800|vllm_tokenizer_patch|text-generation|architectures:bailingmoev2_5forcausallm": { "architectureSignature": "architectures:bailingmoev2_5forcausallm", "architectures": [ "bailingmoev2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-21T11:40:34.995530+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-21T11:40:34.995530+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "JANGQ-AI/Ling-2.6-flash-JANGTQ" ], "sourceTaskIds": [ "5000087" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm_tokenizer_patch|text-generation|architectures:phi3smallforcausallm": { "architectureSignature": "architectures:phi3smallforcausallm", "architectures": [ "phi3smallforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-21T17:45:40.883654+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-21T17:45:40.883654+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": "phi3small", "sourceModelIds": [ "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16" ], "sourceTaskIds": [ "5004954" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm_tokenizer_patch|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-20T03:25:31.991647+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T03:25:31.991647+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "XHToken/Spark-X2.5-1.7B" ], "sourceTaskIds": [ "4969636" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm_tokenizer_patch|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-21T05:25:16.382748+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-21T05:25:16.382748+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "mlx-community/gemma-4-e2b-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ "4994588", "4994586" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm_tokenizer_patch|text-generation|model_type:muse_glimmer": { "architectureSignature": "model_type:muse_glimmer", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:46:29.643802+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T03:46:29.643802+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "muse_glimmer", "sourceModelIds": [ "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit" ], "sourceTaskIds": [ "4970111" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm_tokenizer_patch|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:09:17.944560+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T03:09:17.944560+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4969327" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-20T02:52:51.336010+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T02:52:51.336010+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired" ], "sourceTaskIds": [ "4969039", "4969036" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:09:17.939093+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T03:09:17.939093+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "mlx-community/XYZ-Aquila-mini-OptiQ-4bit" ], "sourceTaskIds": [ "4969329" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_text": { "architectureSignature": "model_type:qwen3_5_text", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:09:17.849368+00:00", "framework": "vllm_tokenizer_patch", "latestFailureAt": "2026-09-20T03:09:17.849368+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_text", "sourceModelIds": [ "TokenRhythm/NeoHorse-1-4B" ], "sourceTaskIds": [ "4969324" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm|text-generation|architectures:plamo3forcausallm": { "architectureSignature": "architectures:plamo3forcausallm", "architectures": [ "plamo3forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-21T16:28:23.653856+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T16:28:23.653856+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "pfnet/plamo-3-nict-8b-base" ], "sourceTaskIds": [ "5003786" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-21T04:55:59.063595+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T04:55:59.063595+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "XHToken/Spark-X2.5-4B" ], "sourceTaskIds": [ "4994203" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm|text-generation|model_type:deepseek_v4": { "architectureSignature": "model_type:deepseek_v4", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T02:52:51.889837+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T02:52:51.889837+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "deepseek_v4", "sourceModelIds": [ "JANGQ-AI/DeepSeek-V4-Flash-JANGTQ-K" ], "sourceTaskIds": [ "4969069" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm|text-generation|model_type:lfm2_moe": { "architectureSignature": "model_type:lfm2_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-21T12:49:01.246640+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T12:49:01.246640+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "lfm2_moe", "sourceModelIds": [ "LiquidAI/LFM2.5-8B-A1B" ], "sourceTaskIds": [ "5001066" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm|text-generation|model_type:muse_glimmer": { "architectureSignature": "model_type:muse_glimmer", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-21T11:00:43.861933+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T11:00:43.861933+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "muse_glimmer", "sourceModelIds": [ "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit" ], "sourceTaskIds": [ "4999589" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-21T04:55:59.067045+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T04:55:59.067045+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4" ], "sourceTaskIds": [ "4994201" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T21:37:47.183318+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T21:37:47.183318+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "EschaLabs/Qwen3.8-27B-Escha-W2" ], "sourceTaskIds": [ "4988062" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T12:50:08.335394+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T12:50:08.335394+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "apodex/Apodex-1.1-mini-GPTQ-Int4" ], "sourceTaskIds": [ "4979143" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm|text-generation|model_type:qwen3_5_text": { "architectureSignature": "model_type:qwen3_5_text", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T20:51:02.382902+00:00", "framework": "vllm", "latestFailureAt": "2026-09-20T20:51:02.382902+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_text", "sourceModelIds": [ "TokenRhythm/NeoHorse-1-4B" ], "sourceTaskIds": [ "4987487" ], "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation" }, "kunlunxin_p-800|vllm|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-21T11:40:35.210780+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T11:40:35.210780+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M" ], "sourceTaskIds": [ "5000137" ], "targetGpu": "Kunlunxin_p-800", "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": 3, "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", "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8" ], "sourceTaskIds": [ "5319960", "5319943", "5319932" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "metax_c-500|vllm|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-22T02:29:17.944417+00:00", "framework": "vllm", "latestFailureAt": "2026-09-22T02:29:17.944417+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-decay-g1-v2_B" ], "sourceTaskIds": [ "5011010" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|model_type:gemma4": { "architectureSignature": "model_type:gemma4", "architectures": [], "evidenceCount": 3, "expiresAt": "2026-10-15T07:13:14.150584+00:00", "framework": "vllm", "latestFailureAt": "2026-09-15T07:13:14.150584+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "gemma4", "sourceModelIds": [ "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit", "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit" ], "sourceTaskIds": [ "4868223", "4868225", "4868229" ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 3, "expiresAt": "2026-10-21T20:29:00.353829+00:00", "framework": "vllm", "latestFailureAt": "2026-09-21T20:29:00.353829+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-decay-g2-v2_C", "nkkbr/Mini-K3-1H-decay-g16-v2_B", "nkkbr/Mini-K3-1H-attnres-block6-v1_C" ], "sourceTaskIds": [ "5006904", "5006868", "5006850" ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-13T02:09:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-13T02:09:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4543931" ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-22T18:06:08+00:00", "framework": "vllm", "latestFailureAt": "2026-09-22T18:06:08+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16" ], "sourceTaskIds": [ "4592052" ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-15T07:13:14.093936+00:00", "framework": "vllm", "latestFailureAt": "2026-09-15T07:13:14.093936+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit" ], "sourceTaskIds": [ "4868226" ], "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" }, "sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|architectures:plamo3forcausallm": { "architectureSignature": "architectures:plamo3forcausallm", "architectures": [ "plamo3forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-24T01:54:08+00:00", "framework": "vllm_fix_tokenizer", "latestFailureAt": "2026-09-24T01:54:08+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "pfnet/plamo-3-nict-8b-base" ], "sourceTaskIds": [ "4458019" ], "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation" }, "sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:mellum": { "architectureSignature": "model_type:mellum", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-13T21:09:21+00:00", "framework": "vllm_fix_tokenizer", "latestFailureAt": "2026-09-13T21:09:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mellum", "sourceModelIds": [ "JetBrains/Mellum2-12B-A2.5B-Instruct" ], "sourceTaskIds": [ "4152538" ], "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation" }, "sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-12T02:51:21+00:00", "framework": "vllm_fix_tokenizer", "latestFailureAt": "2026-09-12T02:51:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4" ], "sourceTaskIds": [ "4134178" ], "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation" }, "sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-16T01:37:21+00:00", "framework": "vllm_fix_tokenizer", "latestFailureAt": "2026-09-16T01:37:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed" ], "sourceTaskIds": [ "4337531" ], "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation" }, "sunrise_pt-200-x1|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-15T06:23:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-15T06:23:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4544266" ], "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation" }, "sunrise_pt-200-x1|vllm|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-14T00:43:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-14T00:43:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "apodex/Apodex-1.1-mini-GPTQ-Int4" ], "sourceTaskIds": [ "4490280" ], "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation" }, "vastai_va16|vllm_fix_tokenizer|text-generation|model_type:mini_k3": { "architectureSignature": "model_type:mini_k3", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-22T03:16:30.263298+00:00", "framework": "vllm_fix_tokenizer", "latestFailureAt": "2026-09-22T03:16:30.263298+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mini_k3", "sourceModelIds": [ "nkkbr/Mini-K3-1H-attnres-standard-v1_B" ], "sourceTaskIds": [ "5011485" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm_fix_tokenizer|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-20T03:41:42.245581+00:00", "framework": "vllm_fix_tokenizer", "latestFailureAt": "2026-09-20T03:41:42.245581+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed" ], "sourceTaskIds": [ "4969995" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm|text-generation|architectures:nanbeigeforcausallm": { "architectureSignature": "architectures:nanbeigeforcausallm", "architectures": [ "nanbeigeforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-15T22:45:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-15T22:45:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "nanbeige/Nanbeige4.2-3B-GPTQ-Int8" ], "sourceTaskIds": [ "4609091" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm|text-generation|architectures:plamo3forcausallm": { "architectureSignature": "architectures:plamo3forcausallm", "architectures": [ "plamo3forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-19T01:47:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-19T01:47:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "pfnet/plamo-3-nict-8b-base" ], "sourceTaskIds": [ "4460346" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm|text-generation|architectures:spark2_5forcausallm": { "architectureSignature": "architectures:spark2_5forcausallm", "architectures": [ "spark2_5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-13T09:33:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-13T09:33:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "XHToken/Spark-X2.5-1.7B" ], "sourceTaskIds": [ "4557415" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-12T17:15:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-12T17:15:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8" ], "sourceTaskIds": [ "4543650" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 3, "expiresAt": "2026-10-19T23:03:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-19T23:03:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "ornith-ai/Ornith-1.5-9B-MLX-8bit" ], "sourceTaskIds": [ "4609086", "4609094", "4609081" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm|text-generation|model_type:rwkv7": { "architectureSignature": "model_type:rwkv7", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-15T03:17:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-15T03:17:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "rwkv7", "sourceModelIds": [ "RWKV/RWKV7-7.2B-20260805", "RWKV/RWKV7-13.3B-20260805" ], "sourceTaskIds": [ "4531335", "4609085" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" } }, "architectureCompatibilitySummary": { "activeBlockCount": 148, "byGpuFramework": { "Ascend_910-b3|vllm": 10, "Ascend_910-b3|vllm_tokenizer_patch": 10, "Ascend_910-b4|vllm": 8, "Ascend_910-b4|vllm_tokenizer_patch": 9, "Biren_166m|vllm": 3, "Cambricon_mlu-370-x4|vllm": 4, "Cambricon_mlu-370-x4|vllm-customized": 1, "Cambricon_mlu-370-x4|vllm-mlu": 1, "Cambricon_mlu-370-x8|vllm": 14, "Cambricon_mlu-370-x8|vllm-customized": 6, "Cambricon_mlu-370-x8|vllm-mlu": 3, "Iluvatar_bi-150|transformers": 5, "Iluvatar_bi-150|vllm": 6, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 5, "Iluvatar_bi-150|vllm_tokenizer_patch": 2, "Iluvatar_mrv-100|vllm": 4, "Kunlunxin_p-800|vllm": 10, "Kunlunxin_p-800|vllm_tokenizer_patch": 9, "MetaX_c-500|vllm": 1, "MetaX_c-500|vllm_tokenizer_patch": 4, "Mthreads_s4000|vllm": 6, "Sunrise_pt-200-x1|vllm": 2, "Sunrise_pt-200-x1|vllm_fix_tokenizer": 4, "Vastai_va16|vllm": 6, "Vastai_va16|vllm_fix_tokenizer": 2, "hygon_k100-ai|vllm": 8, "hygon_k100-ai|vllm-patch-tokenizer": 5 }, "ttlDays": 30 }, "combinationStats": { "Ascend_910-b3|llamacpp|text-generation": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.5, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 1, "successRate": 0.5, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "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": 54, "decisionFailureRate": 0.931, "decisionSuccessRate": 0.069, "decisionTotal": 58, "failureBreakdown": { "ambiguous_runtime": 95, "context_length": 9, "framework_architecture_unsupported": 44, "memory_capacity": 1, "platform_infrastructure": 1, "参数/模板问题": 36 }, "failureCount": 186, "failureRate": 0.9789, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 4, "successRate": 0.0211, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 190, "unresolvedFailureCount": 131 }, "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": 38, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 38, "failureBreakdown": { "ambiguous_runtime": 102, "framework_architecture_unsupported": 37, "platform_infrastructure": 1, "repository_structure": 1, "参数/模板问题": 32 }, "failureCount": 173, "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": 173, "unresolvedFailureCount": 134 }, "Ascend_910-b4|vllm|text-generation": { "attributableFailureCount": 205, "decisionFailureRate": 0.9951, "decisionSuccessRate": 0.0049, "decisionTotal": 206, "failureBreakdown": { "ambiguous_runtime": 123, "context_length": 1, "framework_architecture_unsupported": 156, "memory_capacity": 10, "platform_infrastructure": 2, "repository_structure": 27, "tokenizer_compatibility": 11 }, "failureCount": 330, "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": 331, "unresolvedFailureCount": 123 }, "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": 149, "memory_capacity": 1, "参数/模板问题": 1 }, "failureCount": 151, "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": 151, "unresolvedFailureCount": 150 }, "Biren_166m|vllm|text-generation": { "attributableFailureCount": 50, "decisionFailureRate": 0.7692, "decisionSuccessRate": 0.2308, "decisionTotal": 65, "failureBreakdown": { "ambiguous_runtime": 14, "framework_architecture_unsupported": 36, "model_load": 12, "tokenizer_compatibility": 2 }, "failureCount": 64, "failureRate": 0.8101, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 15, "successRate": 0.1899, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 79, "unresolvedFailureCount": 14 }, "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": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 4, "framework_architecture_unsupported": 3 }, "failureCount": 7, "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": 7, "unresolvedFailureCount": 4 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation": { "attributableFailureCount": 32, "decisionFailureRate": 0.7805, "decisionSuccessRate": 0.2195, "decisionTotal": 41, "failureBreakdown": { "ambiguous_runtime": 51, "framework_architecture_unsupported": 28, "model_load": 4, "platform_infrastructure": 1, "参数/模板问题": 2, "验证失败": 3 }, "failureCount": 89, "failureRate": 0.9082, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 9, "successRate": 0.0918, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 98, "unresolvedFailureCount": 56 }, "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": 25, "decisionFailureRate": 0.6579, "decisionSuccessRate": 0.3421, "decisionTotal": 38, "failureBreakdown": { "ambiguous_runtime": 56, "framework_architecture_unsupported": 21, "model_load": 3, "tokenizer_compatibility": 1, "参数/模板问题": 40 }, "failureCount": 121, "failureRate": 0.903, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 13, "successRate": 0.097, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 134, "unresolvedFailureCount": 96 }, "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": 260, "日志缺失": 95, "验证失败": 30 }, "failureCount": 456, "failureRate": 0.7835, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 126, "successRate": 0.2165, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 582, "unresolvedFailureCount": 456 }, "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": 55, "decisionFailureRate": 0.7432, "decisionSuccessRate": 0.2568, "decisionTotal": 74, "failureBreakdown": { "ambiguous_runtime": 34, "backend_operator": 6, "framework_architecture_unsupported": 30, "memory_capacity": 1, "model_load": 8, "runtime_memory": 10, "参数/模板问题": 22 }, "failureCount": 111, "failureRate": 0.8538, "framework": "vllm_0_17_0_corex_4_4_0", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, "successRate": 0.1462, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 130, "unresolvedFailureCount": 56 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 9, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 9, "failureBreakdown": { "ambiguous_runtime": 52, "memory_capacity": 9 }, "failureCount": 61, "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": 61, "unresolvedFailureCount": 52 }, "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": 291, "日志缺失": 5, "验证失败": 47 }, "failureCount": 1479, "failureRate": 0.9018, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 6, "successCount": 161, "successRate": 0.0982, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1640, "unresolvedFailureCount": 530 }, "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": 40, "decisionFailureRate": 0.7143, "decisionSuccessRate": 0.2857, "decisionTotal": 56, "failureBreakdown": { "ambiguous_runtime": 14, "framework_architecture_unsupported": 35, "model_load": 4, "tokenizer_compatibility": 1, "参数/模板问题": 22 }, "failureCount": 76, "failureRate": 0.8261, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 16, "successRate": 0.1739, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 92, "unresolvedFailureCount": 36 }, "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": 188, "参数/模板问题": 4 }, "failureCount": 192, "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": 192, "unresolvedFailureCount": 192 }, "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": 360, "日志缺失": 1, "验证失败": 48 }, "failureCount": 540, "failureRate": 0.8232, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 116, "successRate": 0.1768, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 656, "unresolvedFailureCount": 512 }, "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": 7, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 6, "model_load": 1, "参数/模板问题": 36 }, "failureCount": 44, "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": 44, "unresolvedFailureCount": 37 }, "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": 640, "decisionFailureRate": 0.961, "decisionSuccessRate": 0.039, "decisionTotal": 666, "failureBreakdown": { "ambiguous_runtime": 135, "architecture_compatibility": 20, "backend_operator": 43, "context_length": 46, "framework_architecture_unsupported": 203, "memory_capacity": 84, "model_load": 65, "platform_infrastructure": 3, "repository_structure": 98, "runtime_memory": 2, "tokenizer_compatibility": 79, "参数/模板问题": 10 }, "failureCount": 788, "failureRate": 0.9681, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 26, "successRate": 0.0319, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 814, "unresolvedFailureCount": 145 }, "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": 32, "日志缺失": 6, "验证失败": 25 }, "failureCount": 63, "failureRate": 0.759, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 20, "successRate": 0.241, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 83, "unresolvedFailureCount": 63 }, "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": 86, "decisionFailureRate": 0.7818, "decisionSuccessRate": 0.2182, "decisionTotal": 110, "failureBreakdown": { "ambiguous_runtime": 81, "attention_backend": 2, "backend_operator": 8, "framework_architecture_unsupported": 62, "memory_capacity": 1, "model_load": 3, "platform_infrastructure": 1, "repository_structure": 1, "runtime_memory": 5, "tokenizer_compatibility": 4, "参数/模板问题": 25 }, "failureCount": 193, "failureRate": 0.8894, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 24, "successRate": 0.1106, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 217, "unresolvedFailureCount": 106 }, "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": 132, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 132, "failureBreakdown": { "ambiguous_runtime": 1, "backend_operator": 10, "framework_architecture_unsupported": 26, "platform_infrastructure": 27, "tokenizer_compatibility": 96, "参数/模板问题": 7 }, "failureCount": 167, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 27, "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 167, "unresolvedFailureCount": 8 }, "Sunrise_pt-200-x1|vllm|text-generation": { "attributableFailureCount": 623, "decisionFailureRate": 0.9873, "decisionSuccessRate": 0.0127, "decisionTotal": 631, "failureBreakdown": { "ambiguous_runtime": 109, "architecture_compatibility": 43, "backend_operator": 30, "context_length": 34, "framework_architecture_unsupported": 146, "memory_capacity": 113, "platform_infrastructure": 217, "repository_structure": 75, "runtime_memory": 1, "tokenizer_compatibility": 181, "参数/模板问题": 9 }, "failureCount": 958, "failureRate": 0.9917, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 217, "successCount": 8, "successRate": 0.0083, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 966, "unresolvedFailureCount": 118 }, "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": 28, "framework_architecture_unsupported": 26, "model_load": 13, "参数/模板问题": 4 }, "failureCount": 71, "failureRate": 0.9342, "framework": "vllm_fix_tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 5, "successRate": 0.0658, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 76, "unresolvedFailureCount": 32 }, "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": 24 }, "failureCount": 24, "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": 24, "unresolvedFailureCount": 24 }, "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": 356, "日志缺失": 60, "验证失败": 27 }, "failureCount": 517, "failureRate": 0.9452, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 30, "successRate": 0.0548, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 547, "unresolvedFailureCount": 507 }, "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": 68, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 68, "failureBreakdown": { "ambiguous_runtime": 51, "framework_architecture_unsupported": 29, "model_load": 15, "repository_structure": 5, "runtime_memory": 19, "参数/模板问题": 53 }, "failureCount": 172, "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": 172, "unresolvedFailureCount": 104 }, "hygon_k100-ai|vllm|text-generation": { "attributableFailureCount": 665, "decisionFailureRate": 0.9911, "decisionSuccessRate": 0.0089, "decisionTotal": 671, "failureBreakdown": { "ambiguous_runtime": 163, "architecture_compatibility": 30, "attention_backend": 1, "context_length": 42, "framework_architecture_unsupported": 230, "memory_capacity": 59, "model_load": 60, "platform_infrastructure": 3, "repository_structure": 109, "runtime_memory": 55, "tokenizer_compatibility": 79, "参数/模板问题": 3 }, "failureCount": 834, "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": 840, "unresolvedFailureCount": 166 }, "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": 191, "decisionFailureRate": 0.9845, "decisionSuccessRate": 0.0155, "decisionTotal": 194, "failureBreakdown": { "ambiguous_runtime": 117, "memory_capacity": 20, "model_load": 171, "参数/模板问题": 2 }, "failureCount": 310, "failureRate": 0.9904, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 3, "successRate": 0.0096, "total": 313, "unresolvedFailureCount": 119 }, "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": 3191, "日志缺失": 719, "验证失败": 673 }, "failureCount": 8453, "failureRate": 0.9122, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 42, "successCount": 814, "successRate": 0.0878, "total": 9267, "unresolvedFailureCount": 6551 }, "vllm": { "attributableFailureCount": 3692, "decisionFailureRate": 0.9716, "decisionSuccessRate": 0.0284, "decisionTotal": 3800, "failureBreakdown": { "ambiguous_runtime": 1606, "architecture_compatibility": 112, "attention_backend": 3, "backend_operator": 95, "context_length": 161, "framework_architecture_unsupported": 1410, "memory_capacity": 725, "model_load": 228, "platform_infrastructure": 881, "repository_structure": 470, "runtime_memory": 66, "tokenizer_compatibility": 422, "参数/模板问题": 86 }, "failureCount": 6265, "failureRate": 0.9831, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 881, "successCount": 108, "successRate": 0.0169, "total": 6373, "unresolvedFailureCount": 1692 }, "vllm-customized": { "attributableFailureCount": 15, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 15, "failureBreakdown": { "ambiguous_runtime": 46, "framework_architecture_unsupported": 11, "model_load": 3, "platform_infrastructure": 2, "tokenizer_compatibility": 1, "参数/模板问题": 5 }, "failureCount": 68, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 0, "successRate": 0.0, "total": 68, "unresolvedFailureCount": 51 }, "vllm-mlu": { "attributableFailureCount": 57, "decisionFailureRate": 0.7215, "decisionSuccessRate": 0.2785, "decisionTotal": 79, "failureBreakdown": { "ambiguous_runtime": 107, "framework_architecture_unsupported": 49, "model_load": 7, "platform_infrastructure": 1, "tokenizer_compatibility": 1, "参数/模板问题": 42, "验证失败": 3 }, "failureCount": 210, "failureRate": 0.9052, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, "successRate": 0.0948, "total": 232, "unresolvedFailureCount": 152 }, "vllm-patch-tokenizer": { "attributableFailureCount": 68, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 68, "failureBreakdown": { "ambiguous_runtime": 51, "framework_architecture_unsupported": 29, "model_load": 15, "repository_structure": 5, "runtime_memory": 19, "参数/模板问题": 53 }, "failureCount": 172, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "total": 172, "unresolvedFailureCount": 104 }, "vllm_0_17_0_corex_4_4_0": { "attributableFailureCount": 55, "decisionFailureRate": 0.7432, "decisionSuccessRate": 0.2568, "decisionTotal": 74, "failureBreakdown": { "ambiguous_runtime": 34, "backend_operator": 6, "framework_architecture_unsupported": 30, "memory_capacity": 1, "model_load": 8, "runtime_memory": 10, "参数/模板问题": 22 }, "failureCount": 111, "failureRate": 0.8538, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 19, "successRate": 0.1462, "total": 130, "unresolvedFailureCount": 56 }, "vllm_fix_tokenizer": { "attributableFailureCount": 181, "decisionFailureRate": 0.9731, "decisionSuccessRate": 0.0269, "decisionTotal": 186, "failureBreakdown": { "ambiguous_runtime": 418, "backend_operator": 10, "framework_architecture_unsupported": 52, "memory_capacity": 10, "model_load": 13, "platform_infrastructure": 27, "tokenizer_compatibility": 96, "参数/模板问题": 16 }, "failureCount": 642, "failureRate": 0.9923, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 27, "successCount": 5, "successRate": 0.0077, "total": 647, "unresolvedFailureCount": 434 }, "vllm_tokenizer_patch": { "attributableFailureCount": 170, "decisionFailureRate": 0.9444, "decisionSuccessRate": 0.0556, "decisionTotal": 180, "failureBreakdown": { "ambiguous_runtime": 212, "backend_operator": 15, "context_length": 9, "framework_architecture_unsupported": 112, "memory_capacity": 2, "model_load": 24, "platform_infrastructure": 3, "repository_structure": 3, "runtime_memory": 3, "tokenizer_compatibility": 2, "参数/模板问题": 119 }, "failureCount": 504, "failureRate": 0.9805, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 10, "successRate": 0.0195, "total": 514, "unresolvedFailureCount": 331 } }, "generatedAt": "2026-10-10T18:42:58.208302+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 130, "decisionFailureRate": 0.8553, "decisionSuccessRate": 0.1447, "decisionTotal": 152, "failureBreakdown": { "ambiguous_runtime": 164, "context_length": 9, "framework_architecture_unsupported": 115, "memory_capacity": 2, "platform_infrastructure": 1, "repository_structure": 1, "tokenizer_compatibility": 3, "参数/模板问题": 68, "日志缺失": 3, "验证失败": 27 }, "failureCount": 393, "failureRate": 0.947, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, "successRate": 0.053, "total": 415, "unresolvedFailureCount": 262 }, "Ascend_910-b4": { "attributableFailureCount": 337, "decisionFailureRate": 0.8404, "decisionSuccessRate": 0.1596, "decisionTotal": 401, "failureBreakdown": { "ambiguous_runtime": 252, "context_length": 1, "framework_architecture_unsupported": 193, "memory_capacity": 19, "model_load": 85, "platform_infrastructure": 3, "repository_structure": 28, "tokenizer_compatibility": 11, "参数/模板问题": 295, "日志缺失": 14, "验证失败": 175 }, "failureCount": 1076, "failureRate": 0.9439, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 64, "successRate": 0.0561, "total": 1140, "unresolvedFailureCount": 736 }, "Biren_166m": { "attributableFailureCount": 193, "decisionFailureRate": 0.8853, "decisionSuccessRate": 0.1147, "decisionTotal": 218, "failureBreakdown": { "ambiguous_runtime": 293, "backend_operator": 4, "context_length": 10, "framework_architecture_unsupported": 125, "memory_capacity": 2, "model_load": 24, "platform_infrastructure": 2, "repository_structure": 18, "runtime_memory": 2, "tokenizer_compatibility": 8, "参数/模板问题": 215, "日志缺失": 62, "验证失败": 27 }, "failureCount": 792, "failureRate": 0.9694, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 25, "successRate": 0.0306, "total": 817, "unresolvedFailureCount": 597 }, "Cambricon_mlu-370-x4": { "attributableFailureCount": 765, "decisionFailureRate": 0.9118, "decisionSuccessRate": 0.0882, "decisionTotal": 839, "failureBreakdown": { "ambiguous_runtime": 516, "architecture_compatibility": 53, "context_length": 48, "framework_architecture_unsupported": 317, "memory_capacity": 219, "model_load": 8, "platform_infrastructure": 16, "repository_structure": 85, "tokenizer_compatibility": 35, "参数/模板问题": 305, "日志缺失": 13, "验证失败": 42 }, "failureCount": 1657, "failureRate": 0.9573, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 16, "successCount": 74, "successRate": 0.0427, "total": 1731, "unresolvedFailureCount": 876 }, "Cambricon_mlu-370-x8": { "attributableFailureCount": 71, "decisionFailureRate": 0.8256, "decisionSuccessRate": 0.1744, "decisionTotal": 86, "failureBreakdown": { "ambiguous_runtime": 160, "framework_architecture_unsupported": 58, "memory_capacity": 4, "model_load": 6, "platform_infrastructure": 2, "tokenizer_compatibility": 3, "参数/模板问题": 78, "验证失败": 22 }, "failureCount": 333, "failureRate": 0.9569, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 15, "successRate": 0.0431, "total": 348, "unresolvedFailureCount": 260 }, "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": 772, "decisionFailureRate": 0.8373, "decisionSuccessRate": 0.1627, "decisionTotal": 922, "failureBreakdown": { "ambiguous_runtime": 667, "architecture_compatibility": 15, "backend_operator": 12, "context_length": 29, "framework_architecture_unsupported": 263, "memory_capacity": 153, "model_load": 128, "platform_infrastructure": 21, "repository_structure": 99, "runtime_memory": 13, "tokenizer_compatibility": 60, "参数/模板问题": 341, "日志缺失": 155, "验证失败": 30 }, "failureCount": 1986, "failureRate": 0.9298, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 21, "successCount": 150, "successRate": 0.0702, "total": 2136, "unresolvedFailureCount": 1193 }, "Iluvatar_mrv-100": { "attributableFailureCount": 990, "decisionFailureRate": 0.8483, "decisionSuccessRate": 0.1517, "decisionTotal": 1167, "failureBreakdown": { "ambiguous_runtime": 354, "architecture_compatibility": 47, "backend_operator": 1, "context_length": 77, "framework_architecture_unsupported": 307, "memory_capacity": 219, "model_load": 88, "platform_infrastructure": 7, "repository_structure": 133, "runtime_memory": 1, "tokenizer_compatibility": 117, "参数/模板问题": 357, "日志缺失": 6, "验证失败": 47 }, "failureCount": 1761, "failureRate": 0.9087, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 7, "successCount": 177, "successRate": 0.0913, "total": 1938, "unresolvedFailureCount": 764 }, "Kunlunxin_p-800": { "attributableFailureCount": 99, "decisionFailureRate": 0.934, "decisionSuccessRate": 0.066, "decisionTotal": 106, "failureBreakdown": { "ambiguous_runtime": 277, "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": 48, "日志缺失": 1, "验证失败": 23 }, "failureCount": 449, "failureRate": 0.9846, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 7, "successRate": 0.0154, "total": 456, "unresolvedFailureCount": 349 }, "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": 682, "decisionFailureRate": 0.8227, "decisionSuccessRate": 0.1773, "decisionTotal": 829, "failureBreakdown": { "ambiguous_runtime": 308, "architecture_compatibility": 21, "backend_operator": 43, "context_length": 59, "framework_architecture_unsupported": 213, "memory_capacity": 85, "model_load": 66, "platform_infrastructure": 5, "repository_structure": 114, "runtime_memory": 2, "tokenizer_compatibility": 79, "参数/模板问题": 444, "日志缺失": 15, "验证失败": 48 }, "failureCount": 1502, "failureRate": 0.9109, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 5, "successCount": 147, "successRate": 0.0891, "total": 1649, "unresolvedFailureCount": 815 }, "Mthreads_s4000": { "attributableFailureCount": 90, "decisionFailureRate": 0.6667, "decisionSuccessRate": 0.3333, "decisionTotal": 135, "failureBreakdown": { "ambiguous_runtime": 127, "attention_backend": 2, "backend_operator": 8, "framework_architecture_unsupported": 63, "memory_capacity": 1, "model_load": 6, "platform_infrastructure": 1, "repository_structure": 1, "runtime_memory": 5, "tokenizer_compatibility": 4, "参数/模板问题": 82, "日志缺失": 96, "验证失败": 26 }, "failureCount": 422, "failureRate": 0.9036, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 45, "successRate": 0.0964, "total": 467, "unresolvedFailureCount": 331 }, "Sunrise_pt-200-x1": { "attributableFailureCount": 774, "decisionFailureRate": 0.8846, "decisionSuccessRate": 0.1154, "decisionTotal": 875, "failureBreakdown": { "ambiguous_runtime": 163, "architecture_compatibility": 44, "backend_operator": 40, "context_length": 39, "framework_architecture_unsupported": 174, "memory_capacity": 113, "platform_infrastructure": 244, "repository_structure": 83, "runtime_memory": 1, "tokenizer_compatibility": 280, "参数/模板问题": 229, "验证失败": 32 }, "failureCount": 1442, "failureRate": 0.9345, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 244, "successCount": 101, "successRate": 0.0655, "total": 1543, "unresolvedFailureCount": 424 }, "Vastai_va16": { "attributableFailureCount": 471, "decisionFailureRate": 0.892, "decisionSuccessRate": 0.108, "decisionTotal": 528, "failureBreakdown": { "ambiguous_runtime": 828, "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": 258, "日志缺失": 124, "验证失败": 130 }, "failureCount": 1825, "failureRate": 0.9697, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 14, "successCount": 57, "successRate": 0.0303, "total": 1882, "unresolvedFailureCount": 1340 }, "hygon_k100-ai": { "attributableFailureCount": 748, "decisionFailureRate": 0.9541, "decisionSuccessRate": 0.0459, "decisionTotal": 784, "failureBreakdown": { "ambiguous_runtime": 350, "architecture_compatibility": 32, "attention_backend": 1, "context_length": 46, "framework_architecture_unsupported": 261, "memory_capacity": 59, "model_load": 75, "platform_infrastructure": 4, "repository_structure": 121, "runtime_memory": 74, "tokenizer_compatibility": 79, "参数/模板问题": 434, "日志缺失": 66, "验证失败": 27 }, "failureCount": 1629, "failureRate": 0.9784, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 4, "successCount": 36, "successRate": 0.0216, "total": 1665, "unresolvedFailureCount": 877 } }, "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": 518, "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|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|k2_horizon|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": "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": 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 }, "failureCount": 2, "failureRate": 0.6667, "framework": "vllm_tokenizer_patch", "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": { "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|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": 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": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "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|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|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-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "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 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 0 }, "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": 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-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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|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|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|k2_horizon|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": "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": 1, "unresolvedFailureCount": 1 }, "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": 8 }, "failureCount": 8, "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": 8, "unresolvedFailureCount": 8 }, "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 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 6 }, "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|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": 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": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "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|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 }, "failureCount": 4, "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": 4, "unresolvedFailureCount": 0 }, "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": 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": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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|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|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|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|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 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 2 }, "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|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": 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": "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": 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": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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 }, "failureCount": 11, "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": 11, "unresolvedFailureCount": 11 }, "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 }, "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": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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": 18 }, "failureCount": 18, "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": 18, "unresolvedFailureCount": 18 }, "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 }, "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": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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": 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": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3 }, "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": "Biren_166m", "taskType": "text-generation", "total": 3, "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 }, "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": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "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|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|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|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|k2_horizon|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": "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": 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": 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-x4", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "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 }, "failureCount": 5, "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": 5, "unresolvedFailureCount": 5 }, "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|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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 0 }, "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": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "framework_architecture_unsupported": 6, "验证失败": 1 }, "failureCount": 7, "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": 7, "unresolvedFailureCount": 1 }, "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": 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-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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|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|k2_horizon|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": "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": 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 }, "failureCount": 1, "failureRate": 0.2, "framework": "vllm-mlu", "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": { "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|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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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|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 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 0 }, "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|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|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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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|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|k2_horizon|compressed-tensors": { "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": "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": 1, "unresolvedFailureCount": 1 }, "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 }, "failureCount": 1, "failureRate": 0.2, "framework": "vllm_0_17_0_corex_4_4_0", "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": 0 }, "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|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|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|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 }, "failureCount": 8, "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": 8, "unresolvedFailureCount": 7 }, "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": 9, "参数/模板问题": 1 }, "failureCount": 10, "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": 10, "unresolvedFailureCount": 10 }, "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|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|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|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|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": 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": "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 }, "failureCount": 2, "failureRate": 0.3333, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 0.6667, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 2 }, "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|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 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 0 }, "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 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|vllm|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", "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": { "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": 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": "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, "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": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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|k2_horizon|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": "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": 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 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 6 }, "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|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|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|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": 4 }, "failureCount": 4, "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": 4, "unresolvedFailureCount": 4 }, "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 }, "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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 12, "unresolvedFailureCount": 12 }, "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 }, "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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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": 18, "参数/模板问题": 1 }, "failureCount": 19, "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": 19, "unresolvedFailureCount": 19 }, "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": 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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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|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|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|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|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|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|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|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": "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 }, "failureCount": 2, "failureRate": 0.2857, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 5, "successRate": 0.7143, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 1 }, "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|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|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|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": 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": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "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": 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": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Mthreads_s4000|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": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|gemma4|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": "gemma4", "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|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|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|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|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|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": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "framework_architecture_unsupported": 6, "platform_infrastructure": 1 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "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": 7, "unresolvedFailureCount": 0 }, "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|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_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|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|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|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|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|llama|awq": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "backend_operator": 2 }, "failureCount": 2, "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": 2, "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": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "tokenizer_compatibility": 4 }, "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": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 4, "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|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|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": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "platform_infrastructure": 6 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 6, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 6, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 6, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 6, "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": 2 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "modelType": "rwkv7", "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|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|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": 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": "zaya", "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 }, "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|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|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 }, "failureCount": 4, "failureRate": 0.6667, "framework": "vllm_fix_tokenizer", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 0.3333, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 3 }, "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|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|k2_horizon|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": "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": 1, "unresolvedFailureCount": 1 }, "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 }, "failureCount": 8, "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": 8, "unresolvedFailureCount": 6 }, "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|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": { "repository_structure": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 0 }, "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|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|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_5_text", "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_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|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|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|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": "2026-10-03T21:52:42.757636+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 2, "consecutiveFailures": 2, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 3, "framework_architecture_unsupported": 2, "参数/模板问题": 15 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-10T13:04:00.870447+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 20, "unresolvedFailureCount": 18 }, "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": 12 }, "failureCount": 13, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-10T18:42:58.165451+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 13, "unresolvedFailureCount": 13 }, "Biren_166m|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-06T19:00:42.266417+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "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-mlu|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 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", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-10T13:57:15.079577+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": 1, "consecutiveFailures": 1, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 2, "framework_architecture_unsupported": 1, "参数/模板问题": 17 }, "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": 19 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": { "attributableFailureCount": 1, "consecutiveFailures": 1, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 1, "参数/模板问题": 14 }, "failureCount": 16, "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": 16, "unresolvedFailureCount": 15 }, "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": 19 }, "failureCount": 19, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-08T12:14:09.655780+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 19, "unresolvedFailureCount": 19 }, "Iluvatar_mrv-100|vllm|text-generation": { "attributableFailureCount": 2, "consecutiveFailures": 2, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2, "参数/模板问题": 18 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-10T09:26:43.784435+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 20, "unresolvedFailureCount": 18 }, "Kunlunxin_p-800|unknown|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": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-05T02:01:26.868359+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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": 5 }, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-10T18:12:14.470925+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "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": 9 }, "failureCount": 9, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-08T11:26:46.346579+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 9 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 5, "consecutiveFailures": 5, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "framework_architecture_unsupported": 4, "model_load": 1, "参数/模板问题": 15 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-10T15:45:17.258678+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 20, "unresolvedFailureCount": 15 }, "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": 13 }, "failureCount": 13, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-08T15:17:12.844319+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 13, "unresolvedFailureCount": 13 }, "Mthreads_s4000|vllm|text-generation": { "attributableFailureCount": 3, "consecutiveFailures": 3, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 2, "framework_architecture_unsupported": 2, "tokenizer_compatibility": 1, "参数/模板问题": 13 }, "failureCount": 18, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-08T15:17:12.844470+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 18, "unresolvedFailureCount": 15 }, "Sunrise_pt-200-x1|unknown|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-26T17:14:27.552028+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 1, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 2, "consecutiveFailures": 2, "consecutivePlatformFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "platform_infrastructure": 2, "tokenizer_compatibility": 2 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": "2026-10-02T02:42:08+00:00", "lastTerminalAt": "2026-10-02T02:51:37.460202+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation": { "attributableFailureCount": 1, "consecutiveFailures": 1, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-29T08:08:02.743424+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "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": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "llamacpp", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-10T03:15:33.370676+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|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": "2026-10-03T21:52:42.757662+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": 2, "consecutiveFailures": 2, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 1, "framework_architecture_unsupported": 1, "model_load": 1, "参数/模板问题": 17 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-10-10T11:17:52.552072+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 20, "unresolvedFailureCount": 18 } }, "recentProfileCombinationStats": { "Ascend_910-b3|vllm_tokenizer_patch|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_tokenizer_patch", "lastTerminalAt": "2026-10-04T01:37:22.760175+00:00", "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|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_tokenizer_patch", "lastTerminalAt": "2026-10-10T09:26:43.784451+00:00", "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|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_tokenizer_patch", "lastTerminalAt": "2026-10-10T05:03:43.549182+00:00", "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|sse_swa_moba|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_tokenizer_patch", "lastTerminalAt": "2026-10-08T14:18:33.043414+00:00", "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|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|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_tokenizer_patch", "lastTerminalAt": "2026-09-27T04:31:48.760568+00:00", "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 }, "Biren_166m|vllm_fix_tokenizer|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_fix_tokenizer", "lastTerminalAt": "2026-10-06T19:00:42.266417+00:00", "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|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_fix_tokenizer", "lastTerminalAt": "2026-10-09T17:44:29.077619+00:00", "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|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": "2026-10-10T00:08:25.360789+00:00", "modelType": "mini_k3", "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|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": "2026-10-08T11:54:51.560590+00:00", "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|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": "2026-10-10T02:38:53.253382+00:00", "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 }, "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|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": "2026-10-08T05:42:37.051754+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-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|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|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|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|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 }, "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|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_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|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|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", "lastTerminalAt": "2026-10-08T05:42:37.051716+00:00", "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": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_fix_tokenizer|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_fix_tokenizer", "lastTerminalAt": "2026-09-26T22:23:08.761596+00:00", "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|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|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|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 }, "MetaX_c-500|vllm_tokenizer_patch|text-generation|gpt_oss|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-07T06:27:34.062566+00:00", "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|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_tokenizer_patch", "lastTerminalAt": "2026-10-09T20:13:21.379246+00:00", "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|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_tokenizer_patch", "lastTerminalAt": "2026-10-10T04:16:40.361082+00:00", "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|qwen3_5_moe|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_tokenizer_patch", "lastTerminalAt": "2026-10-07T11:42:31.164571+00:00", "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, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-07T06:05:03.160740+00:00", "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|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_tokenizer_patch", "lastTerminalAt": "2026-10-07T06:27:34.062607+00:00", "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|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_tokenizer_patch", "lastTerminalAt": "2026-10-10T07:37:42.662674+00:00", "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 }, "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|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|qwen3_5_text|none": { "attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-10-07T00:15:56.875101+00:00", "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|sse_swa_moba|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": "2026-10-09T13:05:40.965751+00:00", "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 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|gpt_oss|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "lastTerminalAt": "2026-10-07T13:20:53.257507+00:00", "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|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-patch-tokenizer", "lastTerminalAt": "2026-10-09T23:01:31.562549+00:00", "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|qwen3_5|none": { "attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "lastTerminalAt": "2026-10-07T03:40:15.756923+00:00", "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": 2, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|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-patch-tokenizer", "lastTerminalAt": "2026-10-10T03:15:33.370698+00:00", "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 } }, "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|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|k2_horizon|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": "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": 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 }, "failureCount": 1, "failureRate": 0.5, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.5, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "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|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|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|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|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|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 }, "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": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "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|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|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|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|k2_horizon|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": "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": 1, "unresolvedFailureCount": 1 }, "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": 2 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 2 }, "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 }, "failureCount": 5, "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": 5, "unresolvedFailureCount": 5 }, "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|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|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|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 }, "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": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "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|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|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|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|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|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|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|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 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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|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|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|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|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 }, "failureCount": 5, "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": 5, "unresolvedFailureCount": 5 }, "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|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|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|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", "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|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", "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|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 10 }, "failureCount": 10, "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": 10, "unresolvedFailureCount": 10 }, "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 }, "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": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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_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|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|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|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|k2_horizon|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": "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": 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": 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-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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 }, "failureCount": 4, "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": 4, "unresolvedFailureCount": 4 }, "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|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|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 }, "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-x4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "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|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-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|33": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3, "验证失败": 1 }, "failureCount": 4, "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": 4, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|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-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": 1, "unresolvedFailureCount": 0 }, "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|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|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|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|k2_horizon|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": "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": 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": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 4, "successRate": 1.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "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|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|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|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 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 0 }, "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|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|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|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|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|k2_horizon|compressed-tensors|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": "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": 1, "unresolvedFailureCount": 1 }, "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": {}, "failureCount": 0, "failureRate": 0.0, "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": 1.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|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|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|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|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 }, "failureCount": 4, "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": 4, "unresolvedFailureCount": 3 }, "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 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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": 5 }, "failureCount": 5, "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": 5, "unresolvedFailureCount": 5 }, "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|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|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|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|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|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": "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": {}, "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": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "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|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 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 0 }, "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 }, "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": "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": 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": "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|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": "spark2_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|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|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|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|k2_horizon|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": "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": 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 }, "failureCount": 4, "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": 4, "unresolvedFailureCount": 4 }, "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|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|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|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|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 }, "failureCount": 5, "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": 5, "unresolvedFailureCount": 5 }, "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 }, "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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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", "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|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "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": 8, "参数/模板问题": 1 }, "failureCount": 9, "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": 9, "unresolvedFailureCount": 9 }, "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|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|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|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|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|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|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|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|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|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|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": "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 }, "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": "Mthreads_s4000", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 0 }, "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|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|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|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|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": 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": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Mthreads_s4000|vllm|text-generation|spark2_5|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": "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|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|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|gemma4|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": "gemma4", "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|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|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|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|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|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": 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_moe", "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|qwen3_5_moe|none|34": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "framework_architecture_unsupported": 3, "platform_infrastructure": 1 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, "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": 4, "unresolvedFailureCount": 0 }, "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|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|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|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|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|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|llama|awq|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": "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|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|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": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "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": 2, "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|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|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|33": { "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", "loadSizeLog2Bucket": 33, "modelType": "qwen3_5", "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|text-generation|qwen3_5|none|34": { "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", "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": 4, "unresolvedFailureCount": 0 }, "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": 5, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 5, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 5, "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|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|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": 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": 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": 2, "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|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|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 }, "failureCount": 3, "failureRate": 0.75, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 1, "successRate": 0.25, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 3 }, "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|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|k2_horizon|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": "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": 1, "unresolvedFailureCount": 1 }, "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 }, "failureCount": 5, "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": 5, "unresolvedFailureCount": 4 }, "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|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|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|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|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|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|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|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": 17818, "totalRecords": 18336, "totals": { "attributableFailureCount": 6316, "decisionFailureRate": 0.8656, "decisionSuccessRate": 0.1344, "decisionTotal": 7297, "failureBreakdown": { "ambiguous_runtime": 4634, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 131, "context_length": 327, "framework_architecture_unsupported": 2331, "memory_capacity": 1206, "model_load": 571, "platform_infrastructure": 956, "repository_structure": 742, "runtime_memory": 101, "tokenizer_compatibility": 692, "参数/模板问题": 3536, "日志缺失": 719, "验证失败": 676 }, "failureCount": 16837, "failureRate": 0.9449, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 956, "successCount": 981, "successRate": 0.0551, "total": 17818, "unresolvedFailureCount": 9565 }, "warnings": [ "GPU MetaX_c-500 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 Iluvatar_bi-150 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 Ascend_910-b3 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 Cambricon_mlu-370-x8 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。", "GPU Sunrise_pt-200-x1 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 Cambricon_mlu-370-x4 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 hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "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 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 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 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 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|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 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 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 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 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。", "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 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 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 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 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 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 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 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 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 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 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 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 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_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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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 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。" ] }, "storageMode": "decision_state_only", "summarizedRecords": 18336, "version": 1 }