{ "generatedAt": "2026-09-23T02:43:28.816899+00:00", "lastSyncTime": "2026-09-23T02:43:25.562726+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { "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: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:glm_ocr": { "architectureSignature": "model_type:glm_ocr", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-04T20:11:22+00:00", "framework": "vllm", "latestFailureAt": "2026-09-04T20:11:22+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "glm_ocr", "sourceModelIds": [ "vastai-ais/GLM-OCR-FP8" ], "sourceTaskIds": [ "4609093" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm|text-generation|model_type:mellum": { "architectureSignature": "model_type:mellum", "architectures": [], "evidenceCount": 3, "expiresAt": "2026-10-04T17:01:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-04T17:01:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mellum", "sourceModelIds": [ "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT", "JetBrains/Mellum2-12B-A2.5B-Instruct", "JetBrains/Mellum2-12B-A2.5B-Thinking" ], "sourceTaskIds": [ "4194474", "4194466", "4194456" ], "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": 2, "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", "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16" ], "sourceTaskIds": [ "4332638", "4582656" ], "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:qwen3_5_mtp": { "architectureSignature": "model_type:qwen3_5_mtp", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-05T10:35:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-05T10:35:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_mtp", "sourceModelIds": [ "mlx-community/Qwen3.8-27B-MTP-nvfp4" ], "sourceTaskIds": [ "4332792" ], "targetGpu": "Ascend_910-b3", "taskType": "text-generation" }, "ascend_910-b3|vllm|text-generation|model_type:qwen3_5_text": { "architectureSignature": "model_type:qwen3_5_text", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-04T20:13:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-04T20:13:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_text", "sourceModelIds": [ "ValueFX/Qwen3.8-27B-CCCP-S" ], "sourceTaskIds": [ "4332634" ], "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|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: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:rwkv5forcausallm": { "architectureSignature": "architectures:rwkv5forcausallm", "architectures": [ "rwkv5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-09T00:51:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-09T00:51:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "RWKV/rwkv-5-world-1b5" ], "sourceTaskIds": [ "4100291" ], "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:mellum": { "architectureSignature": "model_type:mellum", "architectures": [], "evidenceCount": 3, "expiresAt": "2026-10-04T18:31:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-04T18:31:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mellum", "sourceModelIds": [ "JetBrains/Mellum2-12B-A2.5B-Thinking", "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT", "JetBrains/Mellum2-12B-A2.5B-Instruct" ], "sourceTaskIds": [ "4148306", "4149023", "4148528" ], "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_5_mtp": { "architectureSignature": "model_type:qwen3_5_mtp", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-05T17:43:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-05T17:43:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_mtp", "sourceModelIds": [ "mlx-community/Qwen3.8-27B-MTP-nvfp4" ], "sourceTaskIds": [ "4332382" ], "targetGpu": "Ascend_910-b4", "taskType": "text-generation" }, "ascend_910-b4|vllm|text-generation|model_type:qwen3_5_text": { "architectureSignature": "model_type:qwen3_5_text", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-04T23:13:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-04T23:13:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_text", "sourceModelIds": [ "ValueFX/Qwen3.8-27B-CCCP-S" ], "sourceTaskIds": [ "4209387" ], "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" }, "ascend_910-b4|vllm|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-09T01:23:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-09T01:23:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M" ], "sourceTaskIds": [ "4079158" ], "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|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-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|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-08T06:46:11.598902+00:00", "framework": "vllm-mlu", "latestFailureAt": "2026-09-08T06:46:11.598902+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15" ], "sourceTaskIds": [ "4712818" ], "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": 2, "expiresAt": "2026-10-05T03:20:02.336601+00:00", "framework": "vllm-mlu", "latestFailureAt": "2026-09-05T03:20:02.336601+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "ornith-ai/Ornith-1.5-9B-MLX-4bit", "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed" ], "sourceTaskIds": [ "4640028", "4636364" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-05T00:45:53.692926+00:00", "framework": "vllm-mlu", "latestFailureAt": "2026-09-05T00:45:53.692926+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit" ], "sourceTaskIds": [ "4637780" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:qwen3_5_mtp": { "architectureSignature": "model_type:qwen3_5_mtp", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-08T06:46:11.587867+00:00", "framework": "vllm-mlu", "latestFailureAt": "2026-09-08T06:46:11.587867+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_mtp", "sourceModelIds": [ "mlx-community/Qwen3.8-27B-MTP-nvfp4" ], "sourceTaskIds": [ "4712816" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:rwkv7": { "architectureSignature": "model_type:rwkv7", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-08T06:46:11.531728+00:00", "framework": "vllm-mlu", "latestFailureAt": "2026-09-08T06:46:11.531728+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "rwkv7", "sourceModelIds": [ "RWKV/RWKV7-1.5B-20260805" ], "sourceTaskIds": [ "4712811" ], "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": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-08T06:46:11.817069+00:00", "framework": "vllm", "latestFailureAt": "2026-09-08T06:46:11.817069+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "ornith-ai/Ornith-1.5-9B" ], "sourceTaskIds": [ "4712832" ], "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation" }, "cambricon_mlu-370-x8|vllm|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-08T06:46:11.886266+00:00", "framework": "vllm", "latestFailureAt": "2026-09-08T06:46:11.886266+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "EschaLabs/Qwen3.6-35B-A3B-Escha-W2" ], "sourceTaskIds": [ "4712834" ], "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|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:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-05T05:17:16.496259+00:00", "framework": "vllm-patch-tokenizer", "latestFailureAt": "2026-09-05T05:17:16.496259+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B" ], "sourceTaskIds": [ "4641786" ], "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-patch-tokenizer|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-08T14:03:45.031522+00:00", "framework": "vllm-patch-tokenizer", "latestFailureAt": "2026-09-08T14:03:45.031522+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M" ], "sourceTaskIds": [ "4720262" ], "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:mellum": { "architectureSignature": "model_type:mellum", "architectures": [], "evidenceCount": 3, "expiresAt": "2026-10-04T13:51:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-04T13:51:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mellum", "sourceModelIds": [ "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT", "JetBrains/Mellum2-12B-A2.5B-Instruct", "JetBrains/Mellum2-12B-A2.5B-Thinking" ], "sourceTaskIds": [ "4152656", "4148845", "4148308" ], "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_5_mtp": { "architectureSignature": "model_type:qwen3_5_mtp", "architectures": [], "evidenceCount": 4, "expiresAt": "2026-10-05T09:39:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-05T09:39:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_mtp", "sourceModelIds": [ "mlx-community/Qwen3.8-27B-MTP-nvfp4", "mlx-community/Qwen3.8-27B-MTP-mxfp4", "mlx-community/Qwen3.8-27B-MTP-8bit", "mlx-community/Qwen3.8-27B-MTP-bf16" ], "sourceTaskIds": [ "4586225", "4582178", "4587096", "4271618" ], "targetGpu": "hygon_k100-ai", "taskType": "text-generation" }, "hygon_k100-ai|vllm|text-generation|model_type:qwen3_5_text": { "architectureSignature": "model_type:qwen3_5_text", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-04T16:25:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-04T16:25:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_text", "sourceModelIds": [ "ValueFX/Qwen3.8-27B-CCCP-S" ], "sourceTaskIds": [ "4217138" ], "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|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: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": 3, "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", "primitive-ai/Nex-N2.5-mini-NVFP4", "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit" ], "sourceTaskIds": [ "5005325", "5003204", "5000547" ], "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:lille-130m": { "architectureSignature": "model_type:lille-130m", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-01T23:23:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-01T23:23:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "lille-130m", "sourceModelIds": [ "mlx-community/lille-130m-instruct-fp16" ], "sourceTaskIds": [ "4080060" ], "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation" }, "iluvatar_bi-150|vllm|text-generation|model_type:mellum": { "architectureSignature": "model_type:mellum", "architectures": [], "evidenceCount": 3, "expiresAt": "2026-10-04T12:07:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-04T12:07:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mellum", "sourceModelIds": [ "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT", "JetBrains/Mellum2-12B-A2.5B-Instruct", "JetBrains/Mellum2-12B-A2.5B-Thinking" ], "sourceTaskIds": [ "4152671", "4152323", "4152351" ], "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" }, "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: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: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: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": 2, "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", "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU" ], "sourceTaskIds": [ "4988062", "4987485" ], "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" }, "metax_c-500|vllm|text-generation|model_type:mellum": { "architectureSignature": "model_type:mellum", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-04T17:29:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-04T17:29:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mellum", "sourceModelIds": [ "JetBrains/Mellum2-12B-A2.5B-Thinking", "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT" ], "sourceTaskIds": [ "4148305", "4149022" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "metax_c-500|vllm|text-generation|model_type:nemotron_h": { "architectureSignature": "model_type:nemotron_h", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-04T16:33:22+00:00", "framework": "vllm", "latestFailureAt": "2026-09-04T16:33:22+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "nemotron_h", "sourceModelIds": [ "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4" ], "sourceTaskIds": [ "4133678" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "metax_c-500|vllm|text-generation|model_type:qwen3_5": { "architectureSignature": "model_type:qwen3_5", "architectures": [], "evidenceCount": 2, "expiresAt": "2026-10-04T16:10:19.955805+00:00", "framework": "vllm", "latestFailureAt": "2026-09-04T16:10:19.955805+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5", "sourceModelIds": [ "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed" ], "sourceTaskIds": [ "4629852", "4629854" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "metax_c-500|vllm|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-06T03:59:01.992368+00:00", "framework": "vllm", "latestFailureAt": "2026-09-06T03:59:01.992368+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit" ], "sourceTaskIds": [ "4660498" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "metax_c-500|vllm|text-generation|model_type:qwen3_5_mtp": { "architectureSignature": "model_type:qwen3_5_mtp", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-06T08:39:20.512136+00:00", "framework": "vllm", "latestFailureAt": "2026-09-06T08:39:20.512136+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_mtp", "sourceModelIds": [ "mlx-community/Qwen3.8-27B-MTP-mxfp4" ], "sourceTaskIds": [ "4664213" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "metax_c-500|vllm|text-generation|model_type:qwen3_5_text": { "architectureSignature": "model_type:qwen3_5_text", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-05T10:52:05.726238+00:00", "framework": "vllm", "latestFailureAt": "2026-09-05T10:52:05.726238+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_text", "sourceModelIds": [ "ValueFX/Qwen3.8-27B-CCCP-S" ], "sourceTaskIds": [ "4646913" ], "targetGpu": "MetaX_c-500", "taskType": "text-generation" }, "metax_c-500|vllm|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-08T14:49:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-08T14:49:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M" ], "sourceTaskIds": [ "4079917" ], "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:mellum": { "architectureSignature": "model_type:mellum", "architectures": [], "evidenceCount": 3, "expiresAt": "2026-10-05T06:57:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-05T06:57:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mellum", "sourceModelIds": [ "JetBrains/Mellum2-12B-A2.5B-Instruct", "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT", "JetBrains/Mellum2-12B-A2.5B-Thinking" ], "sourceTaskIds": [ "4196912", "4198066", "4196900" ], "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": 2, "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", "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality" ], "sourceTaskIds": [ "4592052", "4332831" ], "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_mtp": { "architectureSignature": "model_type:qwen3_5_mtp", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-06T10:31:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-06T10:31:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_mtp", "sourceModelIds": [ "mlx-community/Qwen3.8-27B-MTP-nvfp4" ], "sourceTaskIds": [ "4590766" ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|model_type:qwen3_5_text": { "architectureSignature": "model_type:qwen3_5_text", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-05T21:33:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-05T21:33:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_text", "sourceModelIds": [ "SupraLabs/reasoning-summarizer-800m-pre" ], "sourceTaskIds": [ "4609104" ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|model_type:qwen3_vl": { "architectureSignature": "model_type:qwen3_vl", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-06T21:23:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-06T21:23:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_vl", "sourceModelIds": [ "metax-tech/Qwen3-VL-8B-Instruct_W8A8" ], "sourceTaskIds": [ "4591579" ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" }, "mthreads_s4000|vllm|text-generation|model_type:rwkv7": { "architectureSignature": "model_type:rwkv7", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-10T04:01:22+00:00", "framework": "vllm", "latestFailureAt": "2026-09-10T04:01:22+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "rwkv7", "sourceModelIds": [ "RWKV/RWKV7-1.5B-20260805" ], "sourceTaskIds": [ "4609102" ], "targetGpu": "Mthreads_s4000", "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" }, "sunrise_pt-200-x1|vllm|text-generation|model_type:qwen3_5_mtp": { "architectureSignature": "model_type:qwen3_5_mtp", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-07T20:41:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-07T20:41:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_mtp", "sourceModelIds": [ "mlx-community/Qwen3.8-27B-MTP-4bit" ], "sourceTaskIds": [ "4585069" ], "targetGpu": "Sunrise_pt-200-x1", "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_fix_tokenizer|text-generation|model_type:qwen3_5_moe": { "architectureSignature": "model_type:qwen3_5_moe", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-05T16:30:08.482261+00:00", "framework": "vllm_fix_tokenizer", "latestFailureAt": "2026-09-05T16:30:08.482261+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_moe", "sourceModelIds": [ "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit" ], "sourceTaskIds": [ "4651930" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm_fix_tokenizer|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-08T15:58:20.200513+00:00", "framework": "vllm_fix_tokenizer", "latestFailureAt": "2026-09-08T15:58:20.200513+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/AppleScript-8B-JANG_4M" ], "sourceTaskIds": [ "4722293" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm|text-generation|architectures:aquiladenseforcausallm": { "architectureSignature": "architectures:aquiladenseforcausallm", "architectures": [ "aquiladenseforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-08T05:39:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-08T05:39:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "BAAI/AquilaDense-7B" ], "sourceTaskIds": [ "4079957" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm|text-generation|architectures:gptneoforcausallm": { "architectureSignature": "architectures:gptneoforcausallm", "architectures": [ "gptneoforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-07T09:45:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-07T09:45:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "KoboldAI/GPT-Neo-2.7B-Janeway" ], "sourceTaskIds": [ "4079146" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm|text-generation|architectures:llavallamaforcausallm": { "architectureSignature": "architectures:llavallamaforcausallm", "architectures": [ "llavallamaforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-07T11:03:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-07T11:03:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "microsoft/llava-med-7b-delta" ], "sourceTaskIds": [ "4079287" ], "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:phi4flashforcausallm": { "architectureSignature": "architectures:phi4flashforcausallm", "architectures": [ "phi4flashforcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-07T10:57:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-07T10:57:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "microsoft/Phi-4-mini-flash-reasoning" ], "sourceTaskIds": [ "4079234" ], "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:rwkv5forcausallm": { "architectureSignature": "architectures:rwkv5forcausallm", "architectures": [ "rwkv5forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-08T18:41:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-08T18:41:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "RWKV/rwkv-5-world-1b5" ], "sourceTaskIds": [ "4107039" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm|text-generation|architectures:rwkv7forcausallm": { "architectureSignature": "architectures:rwkv7forcausallm", "architectures": [ "rwkv7forcausallm" ], "evidenceCount": 1, "expiresAt": "2026-10-07T04:19:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-07T04:19:21+00:00", "latestSuccessfulAt": null, "matchType": "architectures", "modelType": null, "sourceModelIds": [ "fla-hub/rwkv7-7.2B-g0" ], "sourceTaskIds": [ "4079209" ], "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:mellum": { "architectureSignature": "model_type:mellum", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-05T15:03:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-05T15:03:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "mellum", "sourceModelIds": [ "JetBrains/Mellum2-12B-A2.5B-Thinking" ], "sourceTaskIds": [ "4152609" ], "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:qwen3_5_mtp": { "architectureSignature": "model_type:qwen3_5_mtp", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-06T17:03:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-06T17:03:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_mtp", "sourceModelIds": [ "mlx-community/Qwen3.8-27B-MTP-mxfp8" ], "sourceTaskIds": [ "4609075" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" }, "vastai_va16|vllm|text-generation|model_type:qwen3_5_text": { "architectureSignature": "model_type:qwen3_5_text", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-06T04:47:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-06T04:47:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "qwen3_5_text", "sourceModelIds": [ "ValueFX/Qwen3.8-27B-CCCP-S" ], "sourceTaskIds": [ "4576624" ], "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" }, "vastai_va16|vllm|text-generation|model_type:zaya": { "architectureSignature": "model_type:zaya", "architectures": [], "evidenceCount": 1, "expiresAt": "2026-10-08T13:31:21+00:00", "framework": "vllm", "latestFailureAt": "2026-09-08T13:31:21+00:00", "latestSuccessfulAt": null, "matchType": "model_type", "modelType": "zaya", "sourceModelIds": [ "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M" ], "sourceTaskIds": [ "4080030" ], "targetGpu": "Vastai_va16", "taskType": "text-generation" } }, "architectureCompatibilitySummary": { "activeBlockCount": 153, "byGpuFramework": { "Ascend_910-b3|vllm": 13, "Ascend_910-b3|vllm_tokenizer_patch": 5, "Ascend_910-b4|vllm": 13, "Ascend_910-b4|vllm_tokenizer_patch": 6, "Biren_166m|vllm": 3, "Cambricon_mlu-370-x4|vllm": 2, "Cambricon_mlu-370-x8|vllm": 16, "Cambricon_mlu-370-x8|vllm-customized": 6, "Cambricon_mlu-370-x8|vllm-mlu": 5, "Iluvatar_bi-150|transformers": 5, "Iluvatar_bi-150|vllm": 8, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3, "Iluvatar_bi-150|vllm_tokenizer_patch": 2, "Kunlunxin_p-800|vllm": 5, "Kunlunxin_p-800|vllm_tokenizer_patch": 6, "MetaX_c-500|vllm": 7, "Mthreads_s4000|vllm": 9, "Sunrise_pt-200-x1|vllm": 3, "Sunrise_pt-200-x1|vllm_fix_tokenizer": 3, "Vastai_va16|vllm": 16, "Vastai_va16|vllm_fix_tokenizer": 3, "hygon_k100-ai|vllm": 10, "hygon_k100-ai|vllm-patch-tokenizer": 4 }, "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": 31, "日志缺失": 2, "验证失败": 26 }, "failureCount": 60, "failureRate": 0.9091, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 6, "successRate": 0.0909, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 66, "unresolvedFailureCount": 60 }, "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": 32, "decisionFailureRate": 0.9143, "decisionSuccessRate": 0.0857, "decisionTotal": 35, "failureBreakdown": { "ambiguous_runtime": 57, "context_length": 4, "framework_architecture_unsupported": 27, "memory_capacity": 1, "参数/模板问题": 8 }, "failureCount": 97, "failureRate": 0.97, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 3, "successRate": 0.03, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 100, "unresolvedFailureCount": 65 }, "Ascend_910-b3|vllm|text-generation": { "attributableFailureCount": 69, "decisionFailureRate": 0.8625, "decisionSuccessRate": 0.1375, "decisionTotal": 80, "failureBreakdown": { "ambiguous_runtime": 64, "framework_architecture_unsupported": 64, "memory_capacity": 1, "repository_structure": 1, "tokenizer_compatibility": 3 }, "failureCount": 133, "failureRate": 0.9236, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 11, "successRate": 0.0764, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 144, "unresolvedFailureCount": 64 }, "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 }, "failureCount": 111, "failureRate": 0.9911, "framework": "llamacpp", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 1, "successRate": 0.0089, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 112, "unresolvedFailureCount": 19 }, "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": 25, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 25, "failureBreakdown": { "ambiguous_runtime": 81, "framework_architecture_unsupported": 24, "platform_infrastructure": 1, "repository_structure": 1, "参数/模板问题": 6 }, "failureCount": 113, "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": 113, "unresolvedFailureCount": 87 }, "Ascend_910-b4|vllm|text-generation": { "attributableFailureCount": 204, "decisionFailureRate": 0.9951, "decisionSuccessRate": 0.0049, "decisionTotal": 205, "failureBreakdown": { "ambiguous_runtime": 119, "context_length": 1, "framework_architecture_unsupported": 155, "memory_capacity": 10, "platform_infrastructure": 1, "repository_structure": 27, "tokenizer_compatibility": 11 }, "failureCount": 324, "failureRate": 0.9969, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 1, "successRate": 0.0031, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 325, "unresolvedFailureCount": 119 }, "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": 107, "memory_capacity": 1 }, "failureCount": 108, "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": 108, "unresolvedFailureCount": 107 }, "Biren_166m|vllm|text-generation": { "attributableFailureCount": 44, "decisionFailureRate": 0.7458, "decisionSuccessRate": 0.2542, "decisionTotal": 59, "failureBreakdown": { "ambiguous_runtime": 13, "framework_architecture_unsupported": 31, "model_load": 11, "tokenizer_compatibility": 2 }, "failureCount": 57, "failureRate": 0.7917, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 15, "successRate": 0.2083, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 72, "unresolvedFailureCount": 13 }, "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": 281, "日志缺失": 13, "验证失败": 39 }, "failureCount": 1457, "failureRate": 0.9573, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 15, "successCount": 65, "successRate": 0.0427, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1522, "unresolvedFailureCount": 747 }, "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-mlu|text-generation": { "attributableFailureCount": 11, "decisionFailureRate": 0.5789, "decisionSuccessRate": 0.4211, "decisionTotal": 19, "failureBreakdown": { "ambiguous_runtime": 22, "framework_architecture_unsupported": 10, "model_load": 1, "验证失败": 3 }, "failureCount": 36, "failureRate": 0.8182, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 8, "successRate": 0.1818, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 44, "unresolvedFailureCount": 25 }, "Cambricon_mlu-370-x4|vllm|text-generation": { "attributableFailureCount": 7, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "ambiguous_runtime": 5, "framework_architecture_unsupported": 7, "参数/模板问题": 1 }, "failureCount": 13, "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": 13, "unresolvedFailureCount": 6 }, "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": 36, "framework_architecture_unsupported": 8, "model_load": 3, "platform_infrastructure": 2, "tokenizer_compatibility": 1, "参数/模板问题": 5 }, "failureCount": 55, "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": 55, "unresolvedFailureCount": 41 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation": { "attributableFailureCount": 14, "decisionFailureRate": 0.5385, "decisionSuccessRate": 0.4615, "decisionTotal": 26, "failureBreakdown": { "ambiguous_runtime": 45, "framework_architecture_unsupported": 11, "model_load": 2, "tokenizer_compatibility": 1, "参数/模板问题": 3 }, "failureCount": 62, "failureRate": 0.8378, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 12, "successRate": 0.1622, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 74, "unresolvedFailureCount": 48 }, "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": 52 }, "failureCount": 52, "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": 52, "unresolvedFailureCount": 52 }, "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 }, "failureCount": 161, "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": 161, "unresolvedFailureCount": 69 }, "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": 39, "decisionFailureRate": 0.6842, "decisionSuccessRate": 0.3158, "decisionTotal": 57, "failureBreakdown": { "ambiguous_runtime": 23, "backend_operator": 6, "framework_architecture_unsupported": 17, "memory_capacity": 1, "model_load": 6, "runtime_memory": 9, "参数/模板问题": 2 }, "failureCount": 64, "failureRate": 0.7805, "framework": "vllm_0_17_0_corex_4_4_0", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 18, "successRate": 0.2195, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 82, "unresolvedFailureCount": 25 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 9, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 9, "failureBreakdown": { "ambiguous_runtime": 46, "memory_capacity": 9 }, "failureCount": 55, "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": 55, "unresolvedFailureCount": 46 }, "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": 272, "日志缺失": 5, "验证失败": 47 }, "failureCount": 1460, "failureRate": 0.9007, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 6, "successCount": 161, "successRate": 0.0993, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1621, "unresolvedFailureCount": 511 }, "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": 20, "decisionFailureRate": 0.5714, "decisionSuccessRate": 0.4286, "decisionTotal": 35, "failureBreakdown": { "ambiguous_runtime": 8, "framework_architecture_unsupported": 18, "model_load": 2 }, "failureCount": 28, "failureRate": 0.6512, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 15, "successRate": 0.3488, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 43, "unresolvedFailureCount": 8 }, "Kunlunxin_p-800|unknown|text-generation": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 75, "memory_capacity": 1, "参数/模板问题": 13, "日志缺失": 1, "验证失败": 22 }, "failureCount": 112, "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": 112, "unresolvedFailureCount": 111 }, "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": 129, "参数/模板问题": 3 }, "failureCount": 132, "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": 132, "unresolvedFailureCount": 132 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 40, "decisionFailureRate": 0.8889, "decisionSuccessRate": 0.1111, "decisionTotal": 45, "failureBreakdown": { "ambiguous_runtime": 5, "backend_operator": 8, "framework_architecture_unsupported": 15, "memory_capacity": 1, "model_load": 12, "platform_infrastructure": 1, "repository_structure": 2, "runtime_memory": 2, "参数/模板问题": 14 }, "failureCount": 60, "failureRate": 0.9231, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 5, "successRate": 0.0769, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 65, "unresolvedFailureCount": 19 }, "Kunlunxin_p-800|vllm|text-generation": { "attributableFailureCount": 13, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 13, "failureBreakdown": { "backend_operator": 3, "framework_architecture_unsupported": 9, "model_load": 1, "参数/模板问题": 2 }, "failureCount": 15, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 15, "unresolvedFailureCount": 2 }, "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": 351, "日志缺失": 1, "验证失败": 48 }, "failureCount": 531, "failureRate": 0.8207, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 116, "successRate": 0.1793, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 647, "unresolvedFailureCount": 503 }, "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|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": 625, "decisionFailureRate": 0.9615, "decisionSuccessRate": 0.0385, "decisionTotal": 650, "failureBreakdown": { "ambiguous_runtime": 130, "architecture_compatibility": 20, "backend_operator": 43, "context_length": 46, "framework_architecture_unsupported": 193, "memory_capacity": 84, "model_load": 61, "platform_infrastructure": 3, "repository_structure": 98, "runtime_memory": 2, "tokenizer_compatibility": 78, "参数/模板问题": 9 }, "failureCount": 767, "failureRate": 0.9684, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 25, "successRate": 0.0316, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 792, "unresolvedFailureCount": 139 }, "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": 19, "日志缺失": 6, "验证失败": 25 }, "failureCount": 50, "failureRate": 0.7143, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 20, "successRate": 0.2857, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 70, "unresolvedFailureCount": 50 }, "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": 73, "decisionFailureRate": 0.7604, "decisionSuccessRate": 0.2396, "decisionTotal": 96, "failureBreakdown": { "ambiguous_runtime": 73, "attention_backend": 2, "backend_operator": 8, "framework_architecture_unsupported": 53, "memory_capacity": 1, "model_load": 2, "platform_infrastructure": 1, "repository_structure": 1, "runtime_memory": 5, "tokenizer_compatibility": 1, "参数/模板问题": 12 }, "failureCount": 159, "failureRate": 0.8736, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 23, "successRate": 0.1264, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 182, "unresolvedFailureCount": 85 }, "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": 0.125, "decisionSuccessRate": 0.875, "decisionTotal": 104, "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": 0.7725, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 91, "successRate": 0.2275, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 400, "unresolvedFailureCount": 296 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 103, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 103, "failureBreakdown": { "backend_operator": 9, "framework_architecture_unsupported": 12, "platform_infrastructure": 19, "tokenizer_compatibility": 82, "参数/模板问题": 6 }, "failureCount": 128, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 19, "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 128, "unresolvedFailureCount": 6 }, "Sunrise_pt-200-x1|vllm|text-generation": { "attributableFailureCount": 611, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 611, "failureBreakdown": { "ambiguous_runtime": 109, "architecture_compatibility": 43, "backend_operator": 27, "context_length": 34, "framework_architecture_unsupported": 140, "memory_capacity": 113, "platform_infrastructure": 203, "repository_structure": 75, "runtime_memory": 1, "tokenizer_compatibility": 178, "参数/模板问题": 9 }, "failureCount": 932, "failureRate": 1.0, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 203, "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 932, "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": 237, "日志缺失": 123, "验证失败": 130 }, "failureCount": 704, "failureRate": 0.9312, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 52, "successRate": 0.0688, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 756, "unresolvedFailureCount": 704 }, "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": 22, "decisionFailureRate": 0.8148, "decisionSuccessRate": 0.1852, "decisionTotal": 27, "failureBreakdown": { "ambiguous_runtime": 18, "framework_architecture_unsupported": 17, "model_load": 5, "参数/模板问题": 4 }, "failureCount": 44, "failureRate": 0.898, "framework": "vllm_fix_tokenizer", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 5, "successRate": 0.102, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 49, "unresolvedFailureCount": 22 }, "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": 23 }, "failureCount": 23, "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": 23, "unresolvedFailureCount": 23 }, "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": 355, "日志缺失": 60, "验证失败": 27 }, "failureCount": 516, "failureRate": 0.9451, "framework": "unknown", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 30, "successRate": 0.0549, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 546, "unresolvedFailureCount": 506 }, "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": 42, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 42, "failureBreakdown": { "ambiguous_runtime": 24, "framework_architecture_unsupported": 18, "model_load": 10, "repository_structure": 3, "runtime_memory": 11, "参数/模板问题": 11 }, "failureCount": 77, "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": 77, "unresolvedFailureCount": 35 }, "hygon_k100-ai|vllm|text-generation": { "attributableFailureCount": 663, "decisionFailureRate": 0.9925, "decisionSuccessRate": 0.0075, "decisionTotal": 668, "failureBreakdown": { "ambiguous_runtime": 161, "architecture_compatibility": 30, "attention_backend": 1, "context_length": 42, "framework_architecture_unsupported": 229, "memory_capacity": 58, "model_load": 60, "platform_infrastructure": 3, "repository_structure": 109, "runtime_memory": 55, "tokenizer_compatibility": 79, "参数/模板问题": 3 }, "failureCount": 830, "failureRate": 0.994, "framework": "vllm", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 5, "successRate": 0.006, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 835, "unresolvedFailureCount": 164 }, "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": 116, "memory_capacity": 20, "model_load": 171 }, "failureCount": 307, "failureRate": 0.9903, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 3, "successRate": 0.0097, "total": 310, "unresolvedFailureCount": 116 }, "transformers": { "attributableFailureCount": 27, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 27, "failureBreakdown": { "ambiguous_runtime": 72, "framework_architecture_unsupported": 8, "memory_capacity": 5, "model_load": 2, "tokenizer_compatibility": 12 }, "failureCount": 99, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "total": 99, "unresolvedFailureCount": 72 }, "unknown": { "attributableFailureCount": 1860, "decisionFailureRate": 0.6961, "decisionSuccessRate": 0.3039, "decisionTotal": 2672, "failureBreakdown": { "ambiguous_runtime": 1967, "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": 3103, "日志缺失": 719, "验证失败": 673 }, "failureCount": 8364, "failureRate": 0.9115, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 42, "successCount": 812, "successRate": 0.0885, "total": 9176, "unresolvedFailureCount": 6462 }, "vllm": { "attributableFailureCount": 3575, "decisionFailureRate": 0.9741, "decisionSuccessRate": 0.0259, "decisionTotal": 3670, "failureBreakdown": { "ambiguous_runtime": 1534, "architecture_compatibility": 112, "attention_backend": 3, "backend_operator": 87, "context_length": 161, "framework_architecture_unsupported": 1330, "memory_capacity": 722, "model_load": 211, "platform_infrastructure": 866, "repository_structure": 470, "runtime_memory": 66, "tokenizer_compatibility": 413, "参数/模板问题": 48 }, "failureCount": 6023, "failureRate": 0.9845, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 866, "successCount": 95, "successRate": 0.0155, "total": 6118, "unresolvedFailureCount": 1582 }, "vllm-customized": { "attributableFailureCount": 12, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 12, "failureBreakdown": { "ambiguous_runtime": 36, "framework_architecture_unsupported": 8, "model_load": 3, "platform_infrastructure": 2, "tokenizer_compatibility": 1, "参数/模板问题": 5 }, "failureCount": 55, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 0, "successRate": 0.0, "total": 55, "unresolvedFailureCount": 41 }, "vllm-mlu": { "attributableFailureCount": 25, "decisionFailureRate": 0.5556, "decisionSuccessRate": 0.4444, "decisionTotal": 45, "failureBreakdown": { "ambiguous_runtime": 67, "framework_architecture_unsupported": 21, "model_load": 3, "tokenizer_compatibility": 1, "参数/模板问题": 3, "验证失败": 3 }, "failureCount": 98, "failureRate": 0.8305, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 20, "successRate": 0.1695, "total": 118, "unresolvedFailureCount": 73 }, "vllm-patch-tokenizer": { "attributableFailureCount": 42, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 42, "failureBreakdown": { "ambiguous_runtime": 24, "framework_architecture_unsupported": 18, "model_load": 10, "repository_structure": 3, "runtime_memory": 11, "参数/模板问题": 11 }, "failureCount": 77, "failureRate": 1.0, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "total": 77, "unresolvedFailureCount": 35 }, "vllm_0_17_0_corex_4_4_0": { "attributableFailureCount": 39, "decisionFailureRate": 0.6842, "decisionSuccessRate": 0.3158, "decisionTotal": 57, "failureBreakdown": { "ambiguous_runtime": 23, "backend_operator": 6, "framework_architecture_unsupported": 17, "memory_capacity": 1, "model_load": 6, "runtime_memory": 9, "参数/模板问题": 2 }, "failureCount": 64, "failureRate": 0.7805, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 18, "successRate": 0.2195, "total": 82, "unresolvedFailureCount": 25 }, "vllm_fix_tokenizer": { "attributableFailureCount": 135, "decisionFailureRate": 0.9643, "decisionSuccessRate": 0.0357, "decisionTotal": 140, "failureBreakdown": { "ambiguous_runtime": 300, "backend_operator": 9, "framework_architecture_unsupported": 29, "memory_capacity": 10, "model_load": 5, "platform_infrastructure": 19, "tokenizer_compatibility": 82, "参数/模板问题": 13 }, "failureCount": 467, "failureRate": 0.9894, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 19, "successCount": 5, "successRate": 0.0106, "total": 472, "unresolvedFailureCount": 313 }, "vllm_tokenizer_patch": { "attributableFailureCount": 107, "decisionFailureRate": 0.9304, "decisionSuccessRate": 0.0696, "decisionTotal": 115, "failureBreakdown": { "ambiguous_runtime": 147, "backend_operator": 8, "context_length": 4, "framework_architecture_unsupported": 71, "memory_capacity": 2, "model_load": 15, "platform_infrastructure": 2, "repository_structure": 3, "runtime_memory": 2, "tokenizer_compatibility": 2, "参数/模板问题": 28 }, "failureCount": 284, "failureRate": 0.9726, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 8, "successRate": 0.0274, "total": 292, "unresolvedFailureCount": 175 } }, "generatedAt": "2026-09-23T02:43:28.804947+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 102, "decisionFailureRate": 0.8293, "decisionSuccessRate": 0.1707, "decisionTotal": 123, "failureBreakdown": { "ambiguous_runtime": 123, "context_length": 4, "framework_architecture_unsupported": 92, "memory_capacity": 2, "repository_structure": 1, "tokenizer_compatibility": 3, "参数/模板问题": 39, "日志缺失": 3, "验证失败": 27 }, "failureCount": 294, "failureRate": 0.9333, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 21, "successRate": 0.0667, "total": 315, "unresolvedFailureCount": 192 }, "Ascend_910-b4": { "attributableFailureCount": 323, "decisionFailureRate": 0.8346, "decisionSuccessRate": 0.1654, "decisionTotal": 387, "failureBreakdown": { "ambiguous_runtime": 227, "context_length": 1, "framework_architecture_unsupported": 179, "memory_capacity": 19, "model_load": 85, "platform_infrastructure": 2, "repository_structure": 28, "tokenizer_compatibility": 11, "参数/模板问题": 268, "日志缺失": 14, "验证失败": 175 }, "failureCount": 1009, "failureRate": 0.9404, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 64, "successRate": 0.0596, "total": 1073, "unresolvedFailureCount": 684 }, "Biren_166m": { "attributableFailureCount": 187, "decisionFailureRate": 0.8821, "decisionSuccessRate": 0.1179, "decisionTotal": 212, "failureBreakdown": { "ambiguous_runtime": 250, "backend_operator": 4, "context_length": 10, "framework_architecture_unsupported": 120, "memory_capacity": 2, "model_load": 23, "platform_infrastructure": 2, "repository_structure": 18, "runtime_memory": 2, "tokenizer_compatibility": 8, "参数/模板问题": 214, "日志缺失": 62, "验证失败": 27 }, "failureCount": 742, "failureRate": 0.9674, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 25, "successRate": 0.0326, "total": 767, "unresolvedFailureCount": 553 }, "Cambricon_mlu-370-x4": { "attributableFailureCount": 723, "decisionFailureRate": 0.9083, "decisionSuccessRate": 0.0917, "decisionTotal": 796, "failureBreakdown": { "ambiguous_runtime": 442, "architecture_compatibility": 53, "context_length": 48, "framework_architecture_unsupported": 279, "memory_capacity": 218, "model_load": 5, "platform_infrastructure": 15, "repository_structure": 85, "tokenizer_compatibility": 35, "参数/模板问题": 286, "日志缺失": 13, "验证失败": 42 }, "failureCount": 1521, "failureRate": 0.9542, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 15, "successCount": 73, "successRate": 0.0458, "total": 1594, "unresolvedFailureCount": 783 }, "Cambricon_mlu-370-x8": { "attributableFailureCount": 60, "decisionFailureRate": 0.8108, "decisionSuccessRate": 0.1892, "decisionTotal": 74, "failureBreakdown": { "ambiguous_runtime": 143, "framework_architecture_unsupported": 48, "memory_capacity": 4, "model_load": 5, "platform_infrastructure": 2, "tokenizer_compatibility": 3, "参数/模板问题": 41, "验证失败": 22 }, "failureCount": 268, "failureRate": 0.9504, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 14, "successRate": 0.0496, "total": 282, "unresolvedFailureCount": 206 }, "Iluvatar_bi-100": { "attributableFailureCount": 194, "decisionFailureRate": 0.7608, "decisionSuccessRate": 0.2392, "decisionTotal": 255, "failureBreakdown": { "ambiguous_runtime": 172, "memory_capacity": 194, "platform_infrastructure": 635, "参数/模板问题": 242, "日志缺失": 134, "验证失败": 20 }, "failureCount": 1397, "failureRate": 0.9582, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 635, "successCount": 61, "successRate": 0.0418, "total": 1458, "unresolvedFailureCount": 568 }, "Iluvatar_bi-150": { "attributableFailureCount": 756, "decisionFailureRate": 0.8354, "decisionSuccessRate": 0.1646, "decisionTotal": 905, "failureBreakdown": { "ambiguous_runtime": 650, "architecture_compatibility": 15, "backend_operator": 12, "context_length": 29, "framework_architecture_unsupported": 250, "memory_capacity": 153, "model_load": 126, "platform_infrastructure": 21, "repository_structure": 99, "runtime_memory": 12, "tokenizer_compatibility": 60, "参数/模板问题": 320, "日志缺失": 155, "验证失败": 30 }, "failureCount": 1932, "failureRate": 0.9284, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 21, "successCount": 149, "successRate": 0.0716, "total": 2081, "unresolvedFailureCount": 1155 }, "Iluvatar_mrv-100": { "attributableFailureCount": 970, "decisionFailureRate": 0.8464, "decisionSuccessRate": 0.1536, "decisionTotal": 1146, "failureBreakdown": { "ambiguous_runtime": 348, "architecture_compatibility": 47, "backend_operator": 1, "context_length": 77, "framework_architecture_unsupported": 290, "memory_capacity": 219, "model_load": 86, "platform_infrastructure": 7, "repository_structure": 133, "runtime_memory": 1, "tokenizer_compatibility": 116, "参数/模板问题": 316, "日志缺失": 6, "验证失败": 47 }, "failureCount": 1694, "failureRate": 0.9059, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 7, "successCount": 176, "successRate": 0.0941, "total": 1870, "unresolvedFailureCount": 717 }, "Kunlunxin_p-800": { "attributableFailureCount": 54, "decisionFailureRate": 0.9153, "decisionSuccessRate": 0.0847, "decisionTotal": 59, "failureBreakdown": { "ambiguous_runtime": 210, "backend_operator": 11, "framework_architecture_unsupported": 24, "memory_capacity": 2, "model_load": 13, "platform_infrastructure": 1, "repository_structure": 2, "runtime_memory": 2, "参数/模板问题": 32, "日志缺失": 1, "验证失败": 23 }, "failureCount": 321, "failureRate": 0.9847, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 5, "successRate": 0.0153, "total": 326, "unresolvedFailureCount": 266 }, "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": 660, "decisionFailureRate": 0.8189, "decisionSuccessRate": 0.1811, "decisionTotal": 806, "failureBreakdown": { "ambiguous_runtime": 302, "architecture_compatibility": 21, "backend_operator": 43, "context_length": 59, "framework_architecture_unsupported": 197, "memory_capacity": 85, "model_load": 61, "platform_infrastructure": 5, "repository_structure": 114, "runtime_memory": 2, "tokenizer_compatibility": 78, "参数/模板问题": 398, "日志缺失": 15, "验证失败": 48 }, "failureCount": 1428, "failureRate": 0.9072, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 5, "successCount": 146, "successRate": 0.0928, "total": 1574, "unresolvedFailureCount": 763 }, "Mthreads_s4000": { "attributableFailureCount": 77, "decisionFailureRate": 0.6364, "decisionSuccessRate": 0.3636, "decisionTotal": 121, "failureBreakdown": { "ambiguous_runtime": 119, "attention_backend": 2, "backend_operator": 8, "framework_architecture_unsupported": 54, "memory_capacity": 1, "model_load": 5, "platform_infrastructure": 1, "repository_structure": 1, "runtime_memory": 5, "tokenizer_compatibility": 1, "参数/模板问题": 56, "日志缺失": 96, "验证失败": 26 }, "failureCount": 375, "failureRate": 0.895, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 44, "successRate": 0.105, "total": 419, "unresolvedFailureCount": 297 }, "Sunrise_pt-200-x1": { "attributableFailureCount": 733, "decisionFailureRate": 0.8896, "decisionSuccessRate": 0.1104, "decisionTotal": 824, "failureBreakdown": { "ambiguous_runtime": 162, "architecture_compatibility": 44, "backend_operator": 36, "context_length": 39, "framework_architecture_unsupported": 154, "memory_capacity": 113, "platform_infrastructure": 222, "repository_structure": 83, "runtime_memory": 1, "tokenizer_compatibility": 263, "参数/模板问题": 228, "验证失败": 32 }, "failureCount": 1377, "failureRate": 0.938, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 222, "successCount": 91, "successRate": 0.062, "total": 1468, "unresolvedFailureCount": 422 }, "Vastai_va16": { "attributableFailureCount": 454, "decisionFailureRate": 0.8885, "decisionSuccessRate": 0.1115, "decisionTotal": 511, "failureBreakdown": { "ambiguous_runtime": 818, "context_length": 9, "framework_architecture_unsupported": 196, "memory_capacity": 133, "model_load": 47, "platform_infrastructure": 14, "repository_structure": 57, "tokenizer_compatibility": 12, "参数/模板问题": 242, "日志缺失": 124, "验证失败": 130 }, "failureCount": 1782, "failureRate": 0.969, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 14, "successCount": 57, "successRate": 0.031, "total": 1839, "unresolvedFailureCount": 1314 }, "hygon_k100-ai": { "attributableFailureCount": 720, "decisionFailureRate": 0.9536, "decisionSuccessRate": 0.0464, "decisionTotal": 755, "failureBreakdown": { "ambiguous_runtime": 320, "architecture_compatibility": 32, "attention_backend": 1, "context_length": 46, "framework_architecture_unsupported": 249, "memory_capacity": 58, "model_load": 70, "platform_infrastructure": 4, "repository_structure": 119, "runtime_memory": 66, "tokenizer_compatibility": 79, "参数/模板问题": 391, "日志缺失": 66, "验证失败": 27 }, "failureCount": 1528, "failureRate": 0.9776, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 4, "successCount": 35, "successRate": 0.0224, "total": 1563, "unresolvedFailureCount": 804 } }, "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": 218, "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": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_tokenizer_patch", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 1.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 8 }, "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": "Ascend_910-b3", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 8 }, "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|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|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|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "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": "Ascend_910-b3", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "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": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 8, "context_length": 2 }, "failureCount": 10, "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": 10, "unresolvedFailureCount": 8 }, "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|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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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|phi3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "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": 4, "unresolvedFailureCount": 4 }, "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|qwen2|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": "qwen2", "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_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": 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": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|sophia_hybrid|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "sophia_hybrid", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|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|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": 9 }, "failureCount": 9, "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": 9, "unresolvedFailureCount": 9 }, "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": 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": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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": 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": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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": 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": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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|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": 6 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 6 }, "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|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": 6 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 6 }, "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": 24 }, "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-b4", "taskType": "text-generation", "total": 24, "unresolvedFailureCount": 24 }, "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|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": 2 }, "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": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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": 6 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 6 }, "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|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|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|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": 8 }, "failureCount": 8, "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": 8, "unresolvedFailureCount": 8 }, "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|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|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 10 }, "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": "Ascend_910-b4", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 10 }, "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|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": 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": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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": 3 }, "failureCount": 3, "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": 3, "unresolvedFailureCount": 3 }, "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|gemma2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 6 }, "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|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": 9 }, "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": "Biren_166m", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 9 }, "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|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": 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": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "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": 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": "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": 5 }, "failureCount": 5, "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": 5, "unresolvedFailureCount": 5 }, "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": 12 }, "failureCount": 12, "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": 12, "unresolvedFailureCount": 12 }, "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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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|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": 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": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 8 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 8 }, "Biren_166m|vllm_fix_tokenizer|text-generation|zaya|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "zaya", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Biren_166m|vllm|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "cohere2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm|text-generation|gemma3|compressed-tensors": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "modelType": "gemma3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm|text-generation|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|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|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": 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": "Biren_166m", "taskType": "text-generation", "total": 1, "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|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|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-mlu|text-generation|cohere2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "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": 1, "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|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": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "验证失败": 1 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|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-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": 2, "unresolvedFailureCount": 2 }, "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|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|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|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|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|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": 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", "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|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 8, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.1111, "framework": "vllm-mlu", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 8, "successRate": 0.8889, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 1 }, "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|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|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|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-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Cambricon_mlu-370-x4|vllm|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", "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": 2, "unresolvedFailureCount": 2 }, "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|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-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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": 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-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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-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": 4, "model_load": 1 }, "failureCount": 5, "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": 5, "unresolvedFailureCount": 4 }, "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": 7 }, "failureCount": 7, "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": 7, "unresolvedFailureCount": 7 }, "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|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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 2 }, "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": 4 }, "failureCount": 4, "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": 4, "unresolvedFailureCount": 4 }, "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|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|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": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen2", "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|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": 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", "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|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": 1, "decisionFailureRate": 0.1111, "decisionSuccessRate": 0.8889, "decisionTotal": 9, "failureBreakdown": { "ambiguous_runtime": 1, "tokenizer_compatibility": 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-x8", "taskType": "text-generation", "total": 10, "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|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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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": 2 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 2 }, "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": 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-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|lfm2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "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": { "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|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|qwen2|none": { "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": "qwen2", "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_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": 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", "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_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": 7, "参数/模板问题": 1 }, "failureCount": 8, "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": 8, "unresolvedFailureCount": 8 }, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 9, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.1, "framework": "vllm_0_17_0_corex_4_4_0", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 9, "successRate": 0.9, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 10, "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|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|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|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|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": { "memory_capacity": 6 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 0 }, "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": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "modelType": "cohere2", "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|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|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|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|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|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": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 3, "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": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "framework_architecture_unsupported": 6 }, "failureCount": 6, "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": 6, "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": 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": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 9, "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|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|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|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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Kunlunxin_p-800|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": "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|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|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": 8 }, "failureCount": 8, "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": 8, "unresolvedFailureCount": 8 }, "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": 16 }, "failureCount": 16, "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": 16, "unresolvedFailureCount": 16 }, "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|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|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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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": 5 }, "failureCount": 5, "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": 5, "unresolvedFailureCount": 5 }, "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": 12, "参数/模板问题": 1 }, "failureCount": 13, "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": 13, "unresolvedFailureCount": 13 }, "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|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": 11 }, "failureCount": 11, "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": 11, "unresolvedFailureCount": 11 }, "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|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|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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 8 }, "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": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "memory_capacity": 1 }, "failureCount": 1, "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": 1, "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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|gemma2|compressed-tensors": { "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", "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|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": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "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": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "backend_operator": 2 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|llama|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": "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": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "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": 1, "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|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_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": 2, "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|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|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|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": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "backend_operator": 6 }, "failureCount": 6, "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": 6, "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|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|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|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": 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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "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": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "backend_operator": 3 }, "failureCount": 3, "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": 3, "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_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|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|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|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|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": "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|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 9, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.1, "framework": "vllm", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 9, "successRate": 0.9, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 10, "unresolvedFailureCount": 1 }, "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|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": 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": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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|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|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|lfm2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 5 }, "failureCount": 5, "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": 5, "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|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|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": 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": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "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|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": "Mthreads_s4000", "taskType": "text-generation", "total": 10, "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|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|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|gemma2|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": "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|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": 6, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 6, "failureBreakdown": { "backend_operator": 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": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": { "attributableFailureCount": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "backend_operator": 2, "tokenizer_compatibility": 2 }, "failureCount": 4, "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": 4, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": { "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_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": 1, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|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_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|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|starcoder2|compressed-tensors": { "attributableFailureCount": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "tokenizer_compatibility": 2 }, "failureCount": 2, "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": 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": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "tokenizer_compatibility": 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": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors": { "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": "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|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", "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 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|cohere2|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_fix_tokenizer", "modelType": "cohere2", "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|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": 4, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "framework_architecture_unsupported": 4 }, "failureCount": 4, "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": 4, "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|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": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 3 }, "failureCount": 4, "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": 4, "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|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|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|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|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|none": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 0.7778, "framework": "vllm_fix_tokenizer", "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": 7 }, "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|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_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": { "runtime_memory": 1 }, "failureCount": 1, "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": 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|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|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-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": 9, "unresolvedFailureCount": 1 }, "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": 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", "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": 3, "unresolvedFailureCount": 2 }, "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|mpt|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": "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": 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|phi3|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": "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|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|qwen2|none": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "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": 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": 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", "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_vl|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_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-patch-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-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": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3|none": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "ambiguous_runtime": 6, "runtime_memory": 3 }, "failureCount": 9, "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": 9, "unresolvedFailureCount": 6 }, "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|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|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": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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|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": 0.2, "decisionSuccessRate": 0.8, "decisionTotal": 5, "failureBreakdown": { "runtime_memory": 1 }, "failureCount": 1, "failureRate": 0.2, "framework": "vllm", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 4, "successRate": 0.8, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 5, "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|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|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": 12 }, "failureCount": 12, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T09:54:21.980346+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 12, "unresolvedFailureCount": 12 }, "Ascend_910-b3|vllm|text-generation": { "attributableFailureCount": 2, "consecutiveFailures": 2, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 4, "framework_architecture_unsupported": 2 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T16:50:30.559274+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 4 }, "Ascend_910-b4|unknown|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "参数/模板问题": 8 }, "failureCount": 8, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T05:59:02.567443+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 8 }, "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": 9 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-23T02:06:44.350356+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 9 }, "Ascend_910-b4|vllm|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", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T21:35:04.154848+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "Biren_166m|unknown|text-generation": { "attributableFailureCount": 4, "consecutiveFailures": 4, "consecutivePlatformFailures": 0, "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": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T16:50:30.559368+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 0 }, "Biren_166m|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 20 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T03:04:40.754950+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 20, "unresolvedFailureCount": 20 }, "Biren_166m|vllm|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T23:59:03.362604+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T09:54:21.980336+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|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": 10 }, "failureCount": 11, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T01:40:44.320371+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 11, "unresolvedFailureCount": 11 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation": { "attributableFailureCount": 2, "consecutiveFailures": 2, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 17, "framework_architecture_unsupported": 2, "参数/模板问题": 1 }, "failureCount": 20, "failureRate": 1.0, "framework": "vllm-customized", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T18:27:54.061728+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": 18 }, "Cambricon_mlu-370-x8|vllm-mlu|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-mlu", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T13:11:01.559226+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-100|transformers|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 12 }, "failureCount": 12, "failureRate": 1.0, "framework": "transformers", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T05:42:03.443548+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-100", "taskType": "text-generation", "total": 12, "unresolvedFailureCount": 12 }, "Iluvatar_bi-150|transformers|text-generation": { "attributableFailureCount": 5, "consecutiveFailures": 5, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "ambiguous_runtime": 11, "framework_architecture_unsupported": 1, "tokenizer_compatibility": 4 }, "failureCount": 16, "failureRate": 1.0, "framework": "transformers", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T04:16:12.463726+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 16, "unresolvedFailureCount": 11 }, "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": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T18:39:29.750819+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 2, "consecutiveFailures": 2, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 15, "memory_capacity": 2 }, "failureCount": 17, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T02:26:33.565797+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 17, "unresolvedFailureCount": 15 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 7, "consecutiveFailures": 7, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "ambiguous_runtime": 4, "framework_architecture_unsupported": 5, "model_load": 1, "tokenizer_compatibility": 1 }, "failureCount": 11, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T02:26:33.565863+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 11, "unresolvedFailureCount": 4 }, "Iluvatar_bi-150|vllm|text-generation": { "attributableFailureCount": 1, "consecutiveFailures": 1, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 2, "framework_architecture_unsupported": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T02:15:13.557183+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 2 }, "Iluvatar_mrv-100|vllm|text-generation": { "attributableFailureCount": 1, "consecutiveFailures": 1, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T23:51:40.058287+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|unknown|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": 13 }, "failureCount": 15, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T10:15:00.768956+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 15, "unresolvedFailureCount": 15 }, "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": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-23T02:02:52.661615+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_tokenizer_patch|text-generation": { "attributableFailureCount": 2, "consecutiveFailures": 2, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 2, "参数/模板问题": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T20:46:09.364327+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 1 }, "Kunlunxin_p-800|vllm|text-generation": { "attributableFailureCount": 7, "consecutiveFailures": 7, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 7, "failureBreakdown": { "backend_operator": 3, "framework_architecture_unsupported": 4, "参数/模板问题": 2 }, "failureCount": 9, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-23T00:07:02.456914+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 2 }, "MetaX_c-500|vllm|text-generation": { "attributableFailureCount": 1, "consecutiveFailures": 1, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 2, "runtime_memory": 1 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T02:58:30.354826+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 2 }, "Mthreads_s4000|vllm|text-generation": { "attributableFailureCount": 4, "consecutiveFailures": 4, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 4, "failureBreakdown": { "ambiguous_runtime": 2, "framework_architecture_unsupported": 3, "runtime_memory": 1 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T18:08:52.159386+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "Mthreads_s4000", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 2 }, "Sunrise_pt-200-x1|unknown|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 6, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T05:51:50.448464+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 6, "successRate": 1.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 0 }, "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": { "attributableFailureCount": 0, "consecutiveFailures": 0, "consecutivePlatformFailures": 2, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "platform_infrastructure": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": "2026-09-23T02:14:08+00:00", "lastTerminalAt": "2026-09-23T02:15:13.670721+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 0, "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "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": 9 }, "failureCount": 9, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T02:55:04.446730+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 9, "unresolvedFailureCount": 9 }, "hygon_k100-ai|vllm-patch-tokenizer|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": "vllm-patch-tokenizer", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-22T22:37:24.242959+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|text-generation": { "attributableFailureCount": 5, "consecutiveFailures": 5, "consecutivePlatformFailures": 0, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "ambiguous_runtime": 2, "framework_architecture_unsupported": 3, "model_load": 2 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, "lastTerminalAt": "2026-09-21T15:02:24.876304+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 2 } }, "recentProfileCombinationStats": { "Ascend_910-b3|vllm|text-generation|gemma3|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", "lastTerminalAt": "2026-09-22T06:07:03.049892+00:00", "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": 1, "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm|text-generation|llama|awq": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-22T07:42:35.356592+00:00", "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": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-22T08:01:56.366395+00:00", "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-b4|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 8 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-23T02:06:44.350356+00:00", "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|mistral|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-22T15:21:29.958141+00:00", "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|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", "lastTerminalAt": "2026-09-22T13:42:23.869741+00:00", "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|text-generation|llama|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", "lastTerminalAt": "2026-09-22T21:35:04.154848+00:00", "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|starcoder2|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", "lastTerminalAt": "2026-09-22T21:35:04.154885+00:00", "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": { "attributableFailureCount": 1, "consecutiveFailures": 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", "lastTerminalAt": "2026-09-22T18:42:22.556692+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T18:49:48.654842+00:00", "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|gemma2|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T18:35:30.172051+00:00", "modelType": "gemma2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 6, "unresolvedFailureCount": 6 }, "Biren_166m|vllm_fix_tokenizer|text-generation|gemma3|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": "2026-09-22T10:22:21.952623+00:00", "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|hrm_text|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": "2026-09-22T21:12:13.094704+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T19:05:56.949007+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 8 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T03:04:40.754950+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": 8, "unresolvedFailureCount": 8 }, "Biren_166m|vllm_fix_tokenizer|text-generation|llama|awq": { "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": "2026-09-22T03:07:15.068804+00:00", "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": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 10 }, "failureCount": 10, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-23T00:02:55.259360+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T19:05:56.949036+00:00", "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|mpt|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": "2026-09-22T00:56:39.677708+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:20:26.367867+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T01:05:23.461259+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T10:25:50.060508+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T13:30:17.459493+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T13:24:17.269096+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T04:31:25.156759+00:00", "modelType": "phi3", "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|plamo3|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T04:28:46.463574+00:00", "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|qwen3_5_moe|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559167+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T04:26:14.287510+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T10:18:38.460469+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T10:22:21.952661+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": 2, "unresolvedFailureCount": 2 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_text|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": "2026-09-22T23:59:09.461238+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T21:27:15.261138+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T13:30:17.459483+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T04:36:32.459162+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559222+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 7, "unresolvedFailureCount": 7 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3|compressed-tensors": { "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": "2026-09-22T13:30:17.459467+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T07:42:35.356501+00:00", "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": { "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": "2026-09-22T04:22:26.358545+00:00", "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|spark2_5|fp8": { "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": "2026-09-23T02:31:28.170137+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T13:20:33.361556+00:00", "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|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 8 }, "failureCount": 8, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T10:18:38.460439+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T13:34:05.154428+00:00", "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|llama|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", "lastTerminalAt": "2026-09-21T15:54:37.859021+00:00", "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|text-generation|starcoder2|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", "lastTerminalAt": "2026-09-21T23:59:03.362604+00:00", "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 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|aquila3|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T23:47:28.194182+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T08:17:47.558862+00:00", "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, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T06:14:29.458474+00:00", "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|lfm2_moe|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T08:21:38.461094+00:00", "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": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+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-customized|text-generation|llama|awq": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T21:50:30.559334+00:00", "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": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T18:27:54.061728+00:00", "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": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T23:49:30.866184+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|minicpm|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T08:13:39.456382+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:45:40.057911+00:00", "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, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T13:37:53.563484+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-23T02:39:29.759268+00:00", "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|qwen2|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T13:11:01.559205+00:00", "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": 2, "unresolvedFailureCount": 2 }, "Cambricon_mlu-370-x8|vllm-customized|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-23T02:43:25.562726+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T21:46:47.362893+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T08:29:00.965161+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T01:48:12.547533+00:00", "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|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-22T18:31:46.771079+00:00", "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-mlu|text-generation|qwen2|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": "2026-09-22T13:11:01.559226+00:00", "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|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-mlu", "lastTerminalAt": "2026-09-22T08:13:39.456338+00:00", "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 }, "Iluvatar_bi-100|transformers|text-generation|gemma4_unified|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-21T05:42:03.443516+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-21T05:42:03.443548+00:00", "modelType": "gemma4", "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|lfm2|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-21T05:42:03.443562+00:00", "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": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-21T05:42:03.443484+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-21T05:17:51.457662+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-21T05:42:03.443575+00:00", "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|sophia_hybrid|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-21T05:14:26.178403+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-22T04:32:43.855496+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-22T01:45:02.870739+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-21T23:54:30.855927+00:00", "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, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-21T20:22:53.859247+00:00", "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": 3, "consecutiveFailures": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "tokenizer_compatibility": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-21T20:22:53.859269+00:00", "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|lfm2|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-22T00:17:02.854932+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|transformers|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-22T04:13:17.855566+00:00", "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|mistral|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-22T03:52:25.458296+00:00", "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|spark2_5|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-22T02:22:55.559793+00:00", "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": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-22T04:16:12.463726+00:00", "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, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "transformers", "lastTerminalAt": "2026-09-21T22:33:35.352083+00:00", "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|starcoder2|compressed-tensors": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "backend_operator": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-09-21T18:39:29.750819+00:00", "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_fix_tokenizer|text-generation|gemma2|compressed-tensors": { "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": "2026-09-22T00:17:02.854946+00:00", "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_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": "2026-09-21T20:22:53.859210+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_fix_tokenizer|text-generation|llama|compressed-tensors": { "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": "2026-09-22T00:17:02.854957+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T01:15:43.966491+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3small|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": "2026-09-22T02:26:33.565823+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T02:04:59.667018+00:00", "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|none": { "attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "memory_capacity": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T02:26:33.565797+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 4 }, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T02:26:33.565759+00:00", "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": 4, "unresolvedFailureCount": 4 }, "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|zaya|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": "2026-09-22T01:15:43.966483+00:00", "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, "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": "2026-09-21T20:22:53.859263+00:00", "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|lfm2|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-22T02:26:33.565863+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": 3, "unresolvedFailureCount": 3 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|mistral3|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": "2026-09-21T20:22:53.859282+00:00", "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": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T22:36:33.961892+00:00", "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": 0 }, "Iluvatar_bi-150|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": "2026-09-22T00:05:13.753874+00:00", "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, "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": "2026-09-22T02:26:33.565788+00:00", "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, "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": "2026-09-21T20:22:53.859255+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": { "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": "2026-09-22T02:09:12.061129+00:00", "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, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-22T02:15:13.557183+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Iluvatar_bi-150|vllm|text-generation|mpt|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": "2026-09-21T17:41:26.757140+00:00", "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|zaya|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": "2026-09-21T19:05:56.949027+00:00", "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|starcoder2|compressed-tensors": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "model_load": 1 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-22T23:51:40.058287+00:00", "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 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": { "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": "2026-09-23T02:02:52.661615+00:00", "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": 2 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation|hrm_text|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": "2026-09-23T01:54:25.558841+00:00", "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": 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": "2026-09-22T20:46:09.364327+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": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm|text-generation|nemotron_h|modelopt": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-22T20:46:09.364297+00:00", "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|qwen3_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", "lastTerminalAt": "2026-09-23T01:33:13.863433+00:00", "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|text-generation|qwen3_5|escha": { "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": "2026-09-23T01:58:55.445357+00:00", "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|spark2_5|none": { "attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-22T16:03:02.581809+00:00", "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": 3, "consecutiveFailures": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "backend_operator": 3 }, "failureCount": 3, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-23T02:35:34.755698+00:00", "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": 0 }, "Mthreads_s4000|vllm|text-generation|llama|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 2 }, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-22T18:00:11.252309+00:00", "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 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|starcoder2|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-patch-tokenizer", "lastTerminalAt": "2026-09-22T22:37:24.242959+00:00", "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 } }, "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|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|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_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": 1, "unresolvedFailureCount": 1 }, "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": 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-b3", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "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": 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": "Ascend_910-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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|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|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|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": 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": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|30": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "ambiguous_runtime": 1, "context_length": 1 }, "failureCount": 2, "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": 2, "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": 2 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 2 }, "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": 4 }, "failureCount": 4, "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": 4, "unresolvedFailureCount": 4 }, "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|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": 1 }, "failureCount": 1, "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": 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|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_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": 1, "unresolvedFailureCount": 1 }, "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": 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": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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": 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-b3", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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|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|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|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|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|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|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": 3 }, "failureCount": 3, "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": 3, "unresolvedFailureCount": 3 }, "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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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": 3 }, "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": "Ascend_910-b3", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "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": 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": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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|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|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|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": 4 }, "failureCount": 4, "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": 4, "unresolvedFailureCount": 4 }, "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|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|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": 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": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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": 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-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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": 5 }, "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-b4", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5 }, "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": 2 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 2 }, "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": 13 }, "failureCount": 13, "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": 13, "unresolvedFailureCount": 13 }, "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|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": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 1 }, "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": 2 }, "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": "Ascend_910-b4", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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|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|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|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": 8 }, "failureCount": 8, "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": 8, "unresolvedFailureCount": 8 }, "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|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|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_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": 3, "unresolvedFailureCount": 3 }, "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": 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": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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|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|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": 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": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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|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|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": 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": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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": 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": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|plamo3|none|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "Biren_166m|vllm_fix_tokenizer|text-generation|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|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": 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": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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": 2 }, "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": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "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|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": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|34": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 7 }, "failureCount": 7, "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": 7, "unresolvedFailureCount": 7 }, "Biren_166m|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": "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|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|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": 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": "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|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|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|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|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|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|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-mlu|text-generation|cohere2|none|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "model_load": 1 }, "failureCount": 1, "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": 1, "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|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": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "framework_architecture_unsupported": 1, "验证失败": 1 }, "failureCount": 2, "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": 2, "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|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|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|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|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|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|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|33": { "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": 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": 3, "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": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 7, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.125, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 7, "successRate": 0.875, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 8, "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|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|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|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-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": 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": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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": "Cambricon_mlu-370-x4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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|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|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-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": 2 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 2 }, "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": 2 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 2 }, "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|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|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|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|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": 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-x8", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "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|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|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": 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": "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|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": 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-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "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": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 7, "failureBreakdown": { "ambiguous_runtime": 1 }, "failureCount": 1, "failureRate": 0.125, "framework": "vllm-mlu", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 7, "successRate": 0.875, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 8, "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|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": 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-x8", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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": 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-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|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|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|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|qwen2|none|31": { "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": 31, "modelType": "qwen2", "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_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|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": "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_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|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", "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|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|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": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 8, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "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": 1.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 8, "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|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|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|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|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": { "memory_capacity": 3 }, "failureCount": 3, "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": 3, "unresolvedFailureCount": 0 }, "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": {}, "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": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "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|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|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|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|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": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 3, "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|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": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0 }, "Iluvatar_mrv-100|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": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 2, "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": 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": "Iluvatar_mrv-100", "taskType": "text-generation", "total": 8, "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|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|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|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_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": 1, "unresolvedFailureCount": 1 }, "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|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": "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|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|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|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": 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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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": "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": 2 }, "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": 10 }, "failureCount": 10, "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": 10, "unresolvedFailureCount": 10 }, "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|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|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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1 }, "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|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|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": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|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": 2 }, "failureCount": 2, "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": 2, "unresolvedFailureCount": 2 }, "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|33": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 6 }, "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": 5, "参数/模板问题": 1 }, "failureCount": 6, "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": 6, "unresolvedFailureCount": 6 }, "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|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": 8 }, "failureCount": 8, "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": 8, "unresolvedFailureCount": 8 }, "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|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|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": 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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3 }, "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|cohere2|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": "cohere2", "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|gemma2|compressed-tensors|32": { "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { "model_load": 2, "runtime_memory": 1 }, "failureCount": 3, "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": 3, "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|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": 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": "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|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|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_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": 1, "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|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": 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": "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_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|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|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|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": { "backend_operator": 1 }, "failureCount": 1, "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": 1, "unresolvedFailureCount": 0 }, "Kunlunxin_p-800|vllm_tokenizer_patch|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_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": 2, "unresolvedFailureCount": 0 }, "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": { "backend_operator": 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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "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|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|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|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": 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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "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": 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": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "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 }, "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_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|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|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|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|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": "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|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": {}, "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": "MetaX_c-500", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 0 }, "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|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": 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": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "MetaX_c-500|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": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "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": 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": "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|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|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|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|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|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|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": 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": "Mthreads_s4000", "taskType": "text-generation", "total": 1, "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|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": 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": "Mthreads_s4000", "taskType": "text-generation", "total": 8, "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|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|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|gemma2|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": "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|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|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|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": "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|qwen3_5_moe|compressed-tensors|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_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": 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|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|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|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": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "tokenizer_compatibility": 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": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "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|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": "Sunrise_pt-200-x1", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|text-generation|cohere2|none|32": { "attributableFailureCount": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 1, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "cohere2", "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|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": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "framework_architecture_unsupported": 2 }, "failureCount": 2, "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": 2, "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|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": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": { "model_load": 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": "Vastai_va16", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0 }, "Vastai_va16|vllm_fix_tokenizer|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_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": 1, "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|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|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|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|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|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": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 1.0, "decisionTotal": 2, "failureBreakdown": { "ambiguous_runtime": 6 }, "failureCount": 6, "failureRate": 0.75, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 32, "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 2, "successRate": 0.25, "targetGpu": "Vastai_va16", "taskType": "text-generation", "total": 8, "unresolvedFailureCount": 6 }, "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|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_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": { "runtime_memory": 1 }, "failureCount": 1, "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": 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|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|lfm2|none|29": { "attributableFailureCount": 5, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 5, "failureBreakdown": { "model_load": 5 }, "failureCount": 5, "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": 5, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|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-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": 1, "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|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": "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|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-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": 1, "unresolvedFailureCount": 1 }, "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|mpt|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": "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": 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|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-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": 1, "unresolvedFailureCount": 1 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|plamo3|none|33": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { "repository_structure": 1 }, "failureCount": 1, "failureRate": 1.0, "framework": "vllm-patch-tokenizer", "loadSizeLog2Bucket": 33, "modelType": "plamo3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|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|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": 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": "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_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": 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_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-patch-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-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": 1, "unresolvedFailureCount": 1 }, "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": 6, "runtime_memory": 2 }, "failureCount": 8, "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": 8, "unresolvedFailureCount": 6 }, "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|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|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": 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": "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|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|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": 4, "failureBreakdown": {}, "failureCount": 0, "failureRate": 0.0, "framework": "vllm", "loadSizeLog2Bucket": 32, "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "awq", "successCount": 4, "successRate": 1.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", "total": 4, "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|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|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": 16799, "totalRecords": 17017, "totals": { "attributableFailureCount": 6013, "decisionFailureRate": 0.8622, "decisionSuccessRate": 0.1378, "decisionTotal": 6974, "failureBreakdown": { "ambiguous_runtime": 4286, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 115, "context_length": 322, "framework_architecture_unsupported": 2132, "memory_capacity": 1203, "model_load": 526, "platform_infrastructure": 931, "repository_structure": 740, "runtime_memory": 91, "tokenizer_compatibility": 669, "参数/模板问题": 3213, "日志缺失": 719, "验证失败": 676 }, "failureCount": 15838, "failureRate": 0.9428, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 931, "successCount": 961, "successRate": 0.0572, "total": 16799, "unresolvedFailureCount": 8894 }, "warnings": [ "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 MetaX_c-500 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 Cambricon_mlu-370-x4 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 Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-150 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 Ascend_910-b4 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 Biren_166m 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。", "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 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_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 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 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 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 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 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-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 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|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_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 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 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 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 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 Cambricon_mlu-370-x4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_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 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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b4|vllm_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 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 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-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 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 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 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 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 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|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 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 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 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|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。" ] }, "storageMode": "decision_state_only", "summarizedRecords": 17017, "version": 1 }