submmit/.modelhub_state/outcome_checkpoint.json

{
  "generatedAt": "2026-09-18T18:42:04.722129+00:00",
  "lastSyncTime": "2026-09-18T18:42:04.685712+00:00",
  "recentLimit": 300,
  "report": {
    "architectureCompatibilityBlocks": {
      "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:gemma4": {
        "architectureSignature": "model_type:gemma4",
        "architectures": [],
        "evidenceCount": 4,
        "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",
          "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit",
          "mlx-community/gemma-4-e4b-it-OptiQ-4bit",
          "mlx-community/gemma-4-e2b-it-OptiQ-4bit"
        ],
        "sourceTaskIds": [
          "4856934",
          "4856789",
          "4856586",
          "4856587"
        ],
        "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": 2,
        "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",
          "XHToken/Spark-X2.5-4B"
        ],
        "sourceTaskIds": [
          "4558358",
          "4549470"
        ],
        "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: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": 13,
        "expiresAt": "2026-10-17T16:27:21+00:00",
        "framework": "vllm",
        "latestFailureAt": "2026-09-17T16:27:21+00:00",
        "latestSuccessfulAt": null,
        "matchType": "model_type",
        "modelType": "qwen3_5",
        "sourceModelIds": [
          "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo",
          "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
          "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
          "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121",
          "ornith-ai/Ornith-1.5-9B-MLX-8bit"
        ],
        "sourceTaskIds": [
          "4464446",
          "4490182",
          "4458152",
          "4583446",
          "4592742"
        ],
        "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": 2,
        "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",
          "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4"
        ],
        "sourceTaskIds": [
          "4588681",
          "4586733"
        ],
        "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": 3,
        "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",
          "RWKV/RWKV7-13.3B-20260805",
          "RWKV/RWKV7-2.9B-20260805"
        ],
        "sourceTaskIds": [
          "4591876",
          "4582655",
          "4583368"
        ],
        "targetGpu": "Ascend_910-b3",
        "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": 2,
        "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",
          "XHToken/Spark-X2.5-4B"
        ],
        "sourceTaskIds": [
          "4557197",
          "4548919"
        ],
        "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": 8,
        "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",
          "ornith-ai/Ornith-1.5-9B-MLX-8bit",
          "cyankiwi/Ornith-1.5-9B-AWQ-INT4",
          "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B",
          "cyankiwi/Ornith-1.5-9B-AWQ-FP8"
        ],
        "sourceTaskIds": [
          "4610340",
          "4610335",
          "4610341",
          "4610339",
          "4610336"
        ],
        "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": 2,
        "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",
          "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4"
        ],
        "sourceTaskIds": [
          "4576625",
          "4471935"
        ],
        "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:rwkv7": {
        "architectureSignature": "model_type:rwkv7",
        "architectures": [],
        "evidenceCount": 3,
        "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",
          "RWKV/RWKV7-13.3B-20260805",
          "RWKV/RWKV7-2.9B-20260805"
        ],
        "sourceTaskIds": [
          "4588001",
          "4493314",
          "4582844"
        ],
        "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"
      },
      "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|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"
      },
      "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: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|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": 6,
        "expiresAt": "2026-10-17T10:05:21+00:00",
        "framework": "vllm",
        "latestFailureAt": "2026-09-17T10:05:21+00:00",
        "latestSuccessfulAt": null,
        "matchType": "model_type",
        "modelType": "qwen3_5",
        "sourceModelIds": [
          "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
          "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
          "EschaLabs/Qwen3.8-27B-Escha-W2",
          "douyamv/Qwen3.8-27B-FP8",
          "cyankiwi/Ornith-1.5-9B-AWQ-FP8"
        ],
        "sourceTaskIds": [
          "4490374",
          "4460362",
          "4595432",
          "4609095",
          "4592744"
        ],
        "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": 3,
        "expiresAt": "2026-10-16T00:37:21+00:00",
        "framework": "vllm",
        "latestFailureAt": "2026-09-16T00:37:21+00:00",
        "latestSuccessfulAt": null,
        "matchType": "model_type",
        "modelType": "qwen3_5_moe",
        "sourceModelIds": [
          "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit",
          "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4",
          "ornith-ai/Ornith-1.5-35B-A3B-FP8"
        ],
        "sourceTaskIds": [
          "4592020",
          "4493611",
          "4493602"
        ],
        "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": 2,
        "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",
          "RWKV/RWKV7-13.3B-20260805"
        ],
        "sourceTaskIds": [
          "4609108",
          "4592432"
        ],
        "targetGpu": "hygon_k100-ai",
        "taskType": "text-generation"
      },
      "iluvatar_bi-150|vllm|text-generation|architectures:spark2_5forcausallm": {
        "architectureSignature": "architectures:spark2_5forcausallm",
        "architectures": [
          "spark2_5forcausallm"
        ],
        "evidenceCount": 2,
        "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",
          "XHToken/Spark-X2.5-4B"
        ],
        "sourceTaskIds": [
          "4557834",
          "4550765"
        ],
        "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"
      },
      "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": 6,
        "expiresAt": "2026-10-18T15:11:21+00:00",
        "framework": "vllm",
        "latestFailureAt": "2026-09-18T15:11:21+00:00",
        "latestSuccessfulAt": null,
        "matchType": "model_type",
        "modelType": "qwen3_5",
        "sourceModelIds": [
          "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo",
          "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo",
          "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU",
          "EschaLabs/Qwen3.8-27B-Escha-W2",
          "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128"
        ],
        "sourceTaskIds": [
          "4490563",
          "4490562",
          "4460851",
          "4609103",
          "4591690"
        ],
        "targetGpu": "Mthreads_s4000",
        "taskType": "text-generation"
      },
      "mthreads_s4000|vllm|text-generation|model_type:qwen3_5_moe": {
        "architectureSignature": "model_type:qwen3_5_moe",
        "architectures": [],
        "evidenceCount": 2,
        "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",
          "mlx-community/XYZ-Aquila-mini-OptiQ-4bit"
        ],
        "sourceTaskIds": [
          "4868226",
          "4868227"
        ],
        "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": 2,
        "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",
          "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16"
        ],
        "sourceTaskIds": [
          "4337531",
          "4336358"
        ],
        "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": 2,
        "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",
          "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B"
        ],
        "sourceTaskIds": [
          "4490280",
          "4490277"
        ],
        "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_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: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": 2,
        "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",
          "XHToken/Spark-X2.5-4B"
        ],
        "sourceTaskIds": [
          "4557415",
          "4554931"
        ],
        "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": 7,
        "expiresAt": "2026-10-17T23:25:22+00:00",
        "framework": "vllm",
        "latestFailureAt": "2026-09-17T23:25:22+00:00",
        "latestSuccessfulAt": null,
        "matchType": "model_type",
        "modelType": "qwen3_5",
        "sourceModelIds": [
          "cyankiwi/Ornith-1.5-9B-AWQ-INT4",
          "callmezcc/Qwen3.8-27B-GPTQ-W4A16",
          "cyankiwi/Ornith-1.5-9B-AWQ-FP8",
          "EschaLabs/Qwen3.8-27B-Escha-W2",
          "douyamv/Qwen3.8-27B-FP8"
        ],
        "sourceTaskIds": [
          "4609101",
          "4609083",
          "4609077",
          "4593153",
          "4522735"
        ],
        "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": 3,
        "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",
          "RWKV/RWKV7-2.9B-20260805"
        ],
        "sourceTaskIds": [
          "4531335",
          "4609085",
          "4609080"
        ],
        "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": 84,
      "byGpuFramework": {
        "Ascend_910-b3|vllm": 11,
        "Ascend_910-b3|vllm_tokenizer_patch": 1,
        "Ascend_910-b4|vllm": 12,
        "Cambricon_mlu-370-x8|vllm": 2,
        "Cambricon_mlu-370-x8|vllm-mlu": 5,
        "Iluvatar_bi-150|vllm": 4,
        "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": 15,
        "Vastai_va16|vllm_fix_tokenizer": 2,
        "hygon_k100-ai|vllm": 8,
        "hygon_k100-ai|vllm-patch-tokenizer": 2
      },
      "ttlDays": 30
    },
    "combinationStats": {
      "Ascend_910-b3|unknown|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 2,
        "failureBreakdown": {
          "参数/模板问题": 10,
          "验证失败": 26
        },
        "failureCount": 36,
        "failureRate": 0.9474,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 2,
        "successRate": 0.0526,
        "targetGpu": "Ascend_910-b3",
        "taskType": "text-generation",
        "total": 38,
        "unresolvedFailureCount": 36
      },
      "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": 9,
        "decisionFailureRate": 0.9,
        "decisionSuccessRate": 0.1,
        "decisionTotal": 10,
        "failureBreakdown": {
          "ambiguous_runtime": 6,
          "framework_architecture_unsupported": 9
        },
        "failureCount": 15,
        "failureRate": 0.9375,
        "framework": "vllm_tokenizer_patch",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 1,
        "successRate": 0.0625,
        "targetGpu": "Ascend_910-b3",
        "taskType": "text-generation",
        "total": 16,
        "unresolvedFailureCount": 6
      },
      "Ascend_910-b3|vllm|text-generation": {
        "attributableFailureCount": 49,
        "decisionFailureRate": 0.875,
        "decisionSuccessRate": 0.125,
        "decisionTotal": 56,
        "failureBreakdown": {
          "ambiguous_runtime": 33,
          "framework_architecture_unsupported": 47,
          "memory_capacity": 1,
          "tokenizer_compatibility": 1
        },
        "failureCount": 82,
        "failureRate": 0.9213,
        "framework": "vllm",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 7,
        "successRate": 0.0787,
        "targetGpu": "Ascend_910-b3",
        "taskType": "text-generation",
        "total": 89,
        "unresolvedFailureCount": 33
      },
      "Ascend_910-b4|llamacpp|text-generation": {
        "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": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "Ascend_910-b4|unknown|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 2,
        "failureBreakdown": {
          "参数/模板问题": 13,
          "验证失败": 175
        },
        "failureCount": 188,
        "failureRate": 0.9895,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 2,
        "successRate": 0.0105,
        "targetGpu": "Ascend_910-b4",
        "taskType": "text-generation",
        "total": 190,
        "unresolvedFailureCount": 188
      },
      "Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
        "attributableFailureCount": 5,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 5,
        "failureBreakdown": {
          "ambiguous_runtime": 12,
          "framework_architecture_unsupported": 5
        },
        "failureCount": 17,
        "failureRate": 1.0,
        "framework": "vllm_tokenizer_patch",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Ascend_910-b4",
        "taskType": "text-generation",
        "total": 17,
        "unresolvedFailureCount": 12
      },
      "Ascend_910-b4|vllm|text-generation": {
        "attributableFailureCount": 58,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 58,
        "failureBreakdown": {
          "ambiguous_runtime": 43,
          "framework_architecture_unsupported": 54,
          "memory_capacity": 1,
          "repository_structure": 1,
          "tokenizer_compatibility": 2
        },
        "failureCount": 101,
        "failureRate": 1.0,
        "framework": "vllm",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Ascend_910-b4",
        "taskType": "text-generation",
        "total": 101,
        "unresolvedFailureCount": 43
      },
      "Biren_166m|unknown|text-generation": {
        "attributableFailureCount": 40,
        "decisionFailureRate": 0.9524,
        "decisionSuccessRate": 0.0476,
        "decisionTotal": 42,
        "failureBreakdown": {
          "ambiguous_runtime": 32,
          "backend_operator": 4,
          "framework_architecture_unsupported": 29,
          "memory_capacity": 1,
          "model_load": 3,
          "runtime_memory": 2,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 1,
          "验证失败": 27
        },
        "failureCount": 100,
        "failureRate": 0.9804,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 2,
        "successRate": 0.0196,
        "targetGpu": "Biren_166m",
        "taskType": "text-generation",
        "total": 102,
        "unresolvedFailureCount": 60
      },
      "Biren_166m|vllm|text-generation": {
        "attributableFailureCount": 25,
        "decisionFailureRate": 0.7143,
        "decisionSuccessRate": 0.2857,
        "decisionTotal": 35,
        "failureBreakdown": {
          "framework_architecture_unsupported": 19,
          "model_load": 5,
          "tokenizer_compatibility": 1
        },
        "failureCount": 25,
        "failureRate": 0.7143,
        "framework": "vllm",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 10,
        "successRate": 0.2857,
        "targetGpu": "Biren_166m",
        "taskType": "text-generation",
        "total": 35,
        "unresolvedFailureCount": 0
      },
      "Cambricon_mlu-370-x4|unknown|text-generation": {
        "attributableFailureCount": 30,
        "decisionFailureRate": 0.8824,
        "decisionSuccessRate": 0.1176,
        "decisionTotal": 34,
        "failureBreakdown": {
          "ambiguous_runtime": 39,
          "framework_architecture_unsupported": 27,
          "memory_capacity": 1,
          "tokenizer_compatibility": 2,
          "参数/模板问题": 1,
          "验证失败": 39
        },
        "failureCount": 109,
        "failureRate": 0.9646,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 4,
        "successRate": 0.0354,
        "targetGpu": "Cambricon_mlu-370-x4",
        "taskType": "text-generation",
        "total": 113,
        "unresolvedFailureCount": 79
      },
      "Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
        "attributableFailureCount": 3,
        "decisionFailureRate": 0.375,
        "decisionSuccessRate": 0.625,
        "decisionTotal": 8,
        "failureBreakdown": {
          "ambiguous_runtime": 8,
          "framework_architecture_unsupported": 3
        },
        "failureCount": 11,
        "failureRate": 0.6875,
        "framework": "vllm-mlu",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 5,
        "successRate": 0.3125,
        "targetGpu": "Cambricon_mlu-370-x4",
        "taskType": "text-generation",
        "total": 16,
        "unresolvedFailureCount": 8
      },
      "Cambricon_mlu-370-x8|unknown|text-generation": {
        "attributableFailureCount": 8,
        "decisionFailureRate": 0.8,
        "decisionSuccessRate": 0.2,
        "decisionTotal": 10,
        "failureBreakdown": {
          "ambiguous_runtime": 20,
          "framework_architecture_unsupported": 6,
          "memory_capacity": 1,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 5,
          "验证失败": 22
        },
        "failureCount": 55,
        "failureRate": 0.9649,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 2,
        "successRate": 0.0351,
        "targetGpu": "Cambricon_mlu-370-x8",
        "taskType": "text-generation",
        "total": 57,
        "unresolvedFailureCount": 47
      },
      "Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
        "attributableFailureCount": 9,
        "decisionFailureRate": 0.5294,
        "decisionSuccessRate": 0.4706,
        "decisionTotal": 17,
        "failureBreakdown": {
          "ambiguous_runtime": 30,
          "framework_architecture_unsupported": 8,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 3
        },
        "failureCount": 42,
        "failureRate": 0.84,
        "framework": "vllm-mlu",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 8,
        "successRate": 0.16,
        "targetGpu": "Cambricon_mlu-370-x8",
        "taskType": "text-generation",
        "total": 50,
        "unresolvedFailureCount": 33
      },
      "Cambricon_mlu-370-x8|vllm|text-generation": {
        "attributableFailureCount": 3,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 3,
        "failureBreakdown": {
          "framework_architecture_unsupported": 3,
          "参数/模板问题": 10
        },
        "failureCount": 13,
        "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": 13,
        "unresolvedFailureCount": 10
      },
      "Iluvatar_bi-100|transformers|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 8
        },
        "failureCount": 8,
        "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": 8,
        "unresolvedFailureCount": 8
      },
      "Iluvatar_bi-100|unknown|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "验证失败": 20
        },
        "failureCount": 20,
        "failureRate": 1.0,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Iluvatar_bi-100",
        "taskType": "text-generation",
        "total": 20,
        "unresolvedFailureCount": 20
      },
      "Iluvatar_bi-100|vllm|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Iluvatar_bi-100",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "Iluvatar_bi-150|llamacpp|text-generation": {
        "attributableFailureCount": 1,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "ambiguous_runtime": 1,
          "model_load": 1
        },
        "failureCount": 2,
        "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": 2,
        "unresolvedFailureCount": 1
      },
      "Iluvatar_bi-150|unknown|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 6,
        "failureBreakdown": {
          "参数/模板问题": 2,
          "验证失败": 30
        },
        "failureCount": 32,
        "failureRate": 0.8421,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 6,
        "successRate": 0.1579,
        "targetGpu": "Iluvatar_bi-150",
        "taskType": "text-generation",
        "total": 38,
        "unresolvedFailureCount": 32
      },
      "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
        "attributableFailureCount": 26,
        "decisionFailureRate": 0.6842,
        "decisionSuccessRate": 0.3158,
        "decisionTotal": 38,
        "failureBreakdown": {
          "ambiguous_runtime": 12,
          "backend_operator": 4,
          "framework_architecture_unsupported": 8,
          "model_load": 5,
          "runtime_memory": 9,
          "参数/模板问题": 1
        },
        "failureCount": 39,
        "failureRate": 0.7647,
        "framework": "vllm_0_17_0_corex_4_4_0",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 12,
        "successRate": 0.2353,
        "targetGpu": "Iluvatar_bi-150",
        "taskType": "text-generation",
        "total": 51,
        "unresolvedFailureCount": 13
      },
      "Iluvatar_bi-150|vllm|text-generation": {
        "attributableFailureCount": 26,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 26,
        "failureBreakdown": {
          "ambiguous_runtime": 7,
          "backend_operator": 3,
          "framework_architecture_unsupported": 14,
          "model_load": 6,
          "repository_structure": 1,
          "runtime_memory": 2
        },
        "failureCount": 33,
        "failureRate": 1.0,
        "framework": "vllm",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Iluvatar_bi-150",
        "taskType": "text-generation",
        "total": 33,
        "unresolvedFailureCount": 7
      },
      "Iluvatar_mrv-100|unknown|text-generation": {
        "attributableFailureCount": 109,
        "decisionFailureRate": 0.8385,
        "decisionSuccessRate": 0.1615,
        "decisionTotal": 130,
        "failureBreakdown": {
          "ambiguous_runtime": 24,
          "framework_architecture_unsupported": 64,
          "memory_capacity": 1,
          "model_load": 43,
          "platform_infrastructure": 1,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 3,
          "验证失败": 47
        },
        "failureCount": 184,
        "failureRate": 0.8976,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 1,
        "successCount": 21,
        "successRate": 0.1024,
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 205,
        "unresolvedFailureCount": 74
      },
      "Iluvatar_mrv-100|vllm|text-generation": {
        "attributableFailureCount": 11,
        "decisionFailureRate": 0.8462,
        "decisionSuccessRate": 0.1538,
        "decisionTotal": 13,
        "failureBreakdown": {
          "ambiguous_runtime": 3,
          "framework_architecture_unsupported": 10,
          "model_load": 1
        },
        "failureCount": 14,
        "failureRate": 0.875,
        "framework": "vllm",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 2,
        "successRate": 0.125,
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 16,
        "unresolvedFailureCount": 3
      },
      "Kunlunxin_p-800|unknown|text-generation": {
        "attributableFailureCount": 1,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "ambiguous_runtime": 49,
          "memory_capacity": 1,
          "验证失败": 22
        },
        "failureCount": 72,
        "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": 72,
        "unresolvedFailureCount": 71
      },
      "Kunlunxin_p-800|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": "Kunlunxin_p-800",
        "taskType": "visual-multi-modal",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 68,
          "参数/模板问题": 2
        },
        "failureCount": 70,
        "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": 70,
        "unresolvedFailureCount": 70
      },
      "MetaX_c-500|unknown|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 9,
        "failureBreakdown": {
          "参数/模板问题": 10,
          "验证失败": 48
        },
        "failureCount": 58,
        "failureRate": 0.8657,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 9,
        "successRate": 0.1343,
        "targetGpu": "MetaX_c-500",
        "taskType": "text-generation",
        "total": 67,
        "unresolvedFailureCount": 58
      },
      "MetaX_c-500|vllm|text-generation": {
        "attributableFailureCount": 63,
        "decisionFailureRate": 0.7778,
        "decisionSuccessRate": 0.2222,
        "decisionTotal": 81,
        "failureBreakdown": {
          "ambiguous_runtime": 11,
          "backend_operator": 30,
          "framework_architecture_unsupported": 23,
          "memory_capacity": 1,
          "model_load": 8,
          "repository_structure": 1,
          "参数/模板问题": 9
        },
        "failureCount": 83,
        "failureRate": 0.8218,
        "framework": "vllm",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 18,
        "successRate": 0.1782,
        "targetGpu": "MetaX_c-500",
        "taskType": "text-generation",
        "total": 101,
        "unresolvedFailureCount": 20
      },
      "Mthreads_s4000|llamacpp|text-generation": {
        "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": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "Mthreads_s4000|unknown|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 2,
        "failureBreakdown": {
          "参数/模板问题": 8,
          "验证失败": 25
        },
        "failureCount": 33,
        "failureRate": 0.9429,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 2,
        "successRate": 0.0571,
        "targetGpu": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 35,
        "unresolvedFailureCount": 33
      },
      "Mthreads_s4000|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": "Mthreads_s4000",
        "taskType": "visual-multi-modal",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "Mthreads_s4000|vllm|text-generation": {
        "attributableFailureCount": 52,
        "decisionFailureRate": 0.8254,
        "decisionSuccessRate": 0.1746,
        "decisionTotal": 63,
        "failureBreakdown": {
          "ambiguous_runtime": 46,
          "backend_operator": 6,
          "framework_architecture_unsupported": 39,
          "memory_capacity": 1,
          "model_load": 2,
          "repository_structure": 1,
          "runtime_memory": 2,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 12
        },
        "failureCount": 110,
        "failureRate": 0.9091,
        "framework": "vllm",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 11,
        "successRate": 0.0909,
        "targetGpu": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 121,
        "unresolvedFailureCount": 58
      },
      "Sunrise_pt-200-x1|unknown|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 2,
        "failureBreakdown": {
          "参数/模板问题": 3,
          "验证失败": 32
        },
        "failureCount": 35,
        "failureRate": 0.9459,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 2,
        "successRate": 0.0541,
        "targetGpu": "Sunrise_pt-200-x1",
        "taskType": "text-generation",
        "total": 37,
        "unresolvedFailureCount": 35
      },
      "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
        "attributableFailureCount": 62,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 62,
        "failureBreakdown": {
          "backend_operator": 7,
          "framework_architecture_unsupported": 7,
          "platform_infrastructure": 8,
          "tokenizer_compatibility": 48,
          "参数/模板问题": 6
        },
        "failureCount": 76,
        "failureRate": 1.0,
        "framework": "vllm_fix_tokenizer",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 8,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Sunrise_pt-200-x1",
        "taskType": "text-generation",
        "total": 76,
        "unresolvedFailureCount": 6
      },
      "Sunrise_pt-200-x1|vllm|text-generation": {
        "attributableFailureCount": 14,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 14,
        "failureBreakdown": {
          "ambiguous_runtime": 1,
          "backend_operator": 1,
          "framework_architecture_unsupported": 5,
          "memory_capacity": 1,
          "platform_infrastructure": 2,
          "tokenizer_compatibility": 7,
          "参数/模板问题": 9
        },
        "failureCount": 26,
        "failureRate": 1.0,
        "framework": "vllm",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 2,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Sunrise_pt-200-x1",
        "taskType": "text-generation",
        "total": 26,
        "unresolvedFailureCount": 10
      },
      "Vastai_va16|unknown|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 18,
        "failureBreakdown": {
          "参数/模板问题": 15,
          "验证失败": 130
        },
        "failureCount": 145,
        "failureRate": 0.8896,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 18,
        "successRate": 0.1104,
        "targetGpu": "Vastai_va16",
        "taskType": "text-generation",
        "total": 163,
        "unresolvedFailureCount": 145
      },
      "Vastai_va16|vllm_fix_tokenizer|text-generation": {
        "attributableFailureCount": 4,
        "decisionFailureRate": 0.8,
        "decisionSuccessRate": 0.2,
        "decisionTotal": 5,
        "failureBreakdown": {
          "ambiguous_runtime": 6,
          "framework_architecture_unsupported": 3,
          "model_load": 1
        },
        "failureCount": 10,
        "failureRate": 0.9091,
        "framework": "vllm_fix_tokenizer",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 1,
        "successRate": 0.0909,
        "targetGpu": "Vastai_va16",
        "taskType": "text-generation",
        "total": 11,
        "unresolvedFailureCount": 6
      },
      "Vastai_va16|vllm|text-generation": {
        "attributableFailureCount": 58,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 58,
        "failureBreakdown": {
          "ambiguous_runtime": 74,
          "framework_architecture_unsupported": 52,
          "memory_capacity": 1,
          "model_load": 5
        },
        "failureCount": 132,
        "failureRate": 1.0,
        "framework": "vllm",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Vastai_va16",
        "taskType": "text-generation",
        "total": 132,
        "unresolvedFailureCount": 74
      },
      "hygon_k100-ai|llamacpp|text-generation": {
        "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": "hygon_k100-ai",
        "taskType": "text-generation",
        "total": 3,
        "unresolvedFailureCount": 3
      },
      "hygon_k100-ai|unknown|text-generation": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "参数/模板问题": 2,
          "验证失败": 27
        },
        "failureCount": 29,
        "failureRate": 1.0,
        "framework": "unknown",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "hygon_k100-ai",
        "taskType": "text-generation",
        "total": 29,
        "unresolvedFailureCount": 29
      },
      "hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
        "attributableFailureCount": 13,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 13,
        "failureBreakdown": {
          "ambiguous_runtime": 10,
          "framework_architecture_unsupported": 9,
          "model_load": 1,
          "runtime_memory": 3,
          "参数/模板问题": 8
        },
        "failureCount": 31,
        "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": 31,
        "unresolvedFailureCount": 18
      },
      "hygon_k100-ai|vllm|text-generation": {
        "attributableFailureCount": 56,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 56,
        "failureBreakdown": {
          "ambiguous_runtime": 24,
          "framework_architecture_unsupported": 44,
          "memory_capacity": 1,
          "model_load": 5,
          "repository_structure": 4,
          "runtime_memory": 2
        },
        "failureCount": 80,
        "failureRate": 1.0,
        "framework": "vllm",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "hygon_k100-ai",
        "taskType": "text-generation",
        "total": 80,
        "unresolvedFailureCount": 24
      }
    },
    "frameworkSummaries": {
      "llamacpp": {
        "attributableFailureCount": 3,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 3,
        "failureBreakdown": {
          "ambiguous_runtime": 4,
          "model_load": 3
        },
        "failureCount": 7,
        "failureRate": 1.0,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "total": 7,
        "unresolvedFailureCount": 4
      },
      "transformers": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 8
        },
        "failureCount": 8,
        "failureRate": 1.0,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "total": 8,
        "unresolvedFailureCount": 8
      },
      "unknown": {
        "attributableFailureCount": 188,
        "decisionFailureRate": 0.7287,
        "decisionSuccessRate": 0.2713,
        "decisionTotal": 258,
        "failureBreakdown": {
          "ambiguous_runtime": 164,
          "backend_operator": 4,
          "framework_architecture_unsupported": 126,
          "memory_capacity": 5,
          "model_load": 46,
          "platform_infrastructure": 1,
          "runtime_memory": 2,
          "tokenizer_compatibility": 5,
          "参数/模板问题": 73,
          "验证失败": 673
        },
        "failureCount": 1099,
        "failureRate": 0.9401,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 1,
        "successCount": 70,
        "successRate": 0.0599,
        "total": 1169,
        "unresolvedFailureCount": 910
      },
      "vllm": {
        "attributableFailureCount": 415,
        "decisionFailureRate": 0.8963,
        "decisionSuccessRate": 0.1037,
        "decisionTotal": 463,
        "failureBreakdown": {
          "ambiguous_runtime": 243,
          "backend_operator": 40,
          "framework_architecture_unsupported": 310,
          "memory_capacity": 7,
          "model_load": 32,
          "platform_infrastructure": 2,
          "repository_structure": 8,
          "runtime_memory": 6,
          "tokenizer_compatibility": 12,
          "参数/模板问题": 40
        },
        "failureCount": 700,
        "failureRate": 0.9358,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 2,
        "successCount": 48,
        "successRate": 0.0642,
        "total": 748,
        "unresolvedFailureCount": 283
      },
      "vllm-mlu": {
        "attributableFailureCount": 12,
        "decisionFailureRate": 0.48,
        "decisionSuccessRate": 0.52,
        "decisionTotal": 25,
        "failureBreakdown": {
          "ambiguous_runtime": 38,
          "framework_architecture_unsupported": 11,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 3
        },
        "failureCount": 53,
        "failureRate": 0.803,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 13,
        "successRate": 0.197,
        "total": 66,
        "unresolvedFailureCount": 41
      },
      "vllm-patch-tokenizer": {
        "attributableFailureCount": 13,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 13,
        "failureBreakdown": {
          "ambiguous_runtime": 10,
          "framework_architecture_unsupported": 9,
          "model_load": 1,
          "runtime_memory": 3,
          "参数/模板问题": 8
        },
        "failureCount": 31,
        "failureRate": 1.0,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "total": 31,
        "unresolvedFailureCount": 18
      },
      "vllm_0_17_0_corex_4_4_0": {
        "attributableFailureCount": 26,
        "decisionFailureRate": 0.6842,
        "decisionSuccessRate": 0.3158,
        "decisionTotal": 38,
        "failureBreakdown": {
          "ambiguous_runtime": 12,
          "backend_operator": 4,
          "framework_architecture_unsupported": 8,
          "model_load": 5,
          "runtime_memory": 9,
          "参数/模板问题": 1
        },
        "failureCount": 39,
        "failureRate": 0.7647,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 12,
        "successRate": 0.2353,
        "total": 51,
        "unresolvedFailureCount": 13
      },
      "vllm_fix_tokenizer": {
        "attributableFailureCount": 66,
        "decisionFailureRate": 0.9851,
        "decisionSuccessRate": 0.0149,
        "decisionTotal": 67,
        "failureBreakdown": {
          "ambiguous_runtime": 74,
          "backend_operator": 7,
          "framework_architecture_unsupported": 10,
          "model_load": 1,
          "platform_infrastructure": 8,
          "tokenizer_compatibility": 48,
          "参数/模板问题": 8
        },
        "failureCount": 156,
        "failureRate": 0.9936,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 8,
        "successCount": 1,
        "successRate": 0.0064,
        "total": 157,
        "unresolvedFailureCount": 82
      },
      "vllm_tokenizer_patch": {
        "attributableFailureCount": 14,
        "decisionFailureRate": 0.9333,
        "decisionSuccessRate": 0.0667,
        "decisionTotal": 15,
        "failureBreakdown": {
          "ambiguous_runtime": 18,
          "framework_architecture_unsupported": 14
        },
        "failureCount": 32,
        "failureRate": 0.9697,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 1,
        "successRate": 0.0303,
        "total": 33,
        "unresolvedFailureCount": 18
      }
    },
    "generatedAt": "2026-09-18T18:42:04.716905+00:00",
    "gpuSummaries": {
      "Ascend_910-b3": {
        "attributableFailureCount": 58,
        "decisionFailureRate": 0.8529,
        "decisionSuccessRate": 0.1471,
        "decisionTotal": 68,
        "failureBreakdown": {
          "ambiguous_runtime": 39,
          "framework_architecture_unsupported": 56,
          "memory_capacity": 1,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 10,
          "验证失败": 27
        },
        "failureCount": 134,
        "failureRate": 0.9306,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 10,
        "successRate": 0.0694,
        "total": 144,
        "unresolvedFailureCount": 76
      },
      "Ascend_910-b4": {
        "attributableFailureCount": 64,
        "decisionFailureRate": 0.9697,
        "decisionSuccessRate": 0.0303,
        "decisionTotal": 66,
        "failureBreakdown": {
          "ambiguous_runtime": 55,
          "framework_architecture_unsupported": 59,
          "memory_capacity": 1,
          "model_load": 1,
          "repository_structure": 1,
          "tokenizer_compatibility": 2,
          "参数/模板问题": 13,
          "验证失败": 175
        },
        "failureCount": 307,
        "failureRate": 0.9935,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 2,
        "successRate": 0.0065,
        "total": 309,
        "unresolvedFailureCount": 243
      },
      "Biren_166m": {
        "attributableFailureCount": 65,
        "decisionFailureRate": 0.8442,
        "decisionSuccessRate": 0.1558,
        "decisionTotal": 77,
        "failureBreakdown": {
          "ambiguous_runtime": 32,
          "backend_operator": 4,
          "framework_architecture_unsupported": 48,
          "memory_capacity": 1,
          "model_load": 8,
          "runtime_memory": 2,
          "tokenizer_compatibility": 2,
          "参数/模板问题": 1,
          "验证失败": 27
        },
        "failureCount": 125,
        "failureRate": 0.9124,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 12,
        "successRate": 0.0876,
        "total": 137,
        "unresolvedFailureCount": 60
      },
      "Cambricon_mlu-370-x4": {
        "attributableFailureCount": 33,
        "decisionFailureRate": 0.7857,
        "decisionSuccessRate": 0.2143,
        "decisionTotal": 42,
        "failureBreakdown": {
          "ambiguous_runtime": 47,
          "framework_architecture_unsupported": 30,
          "memory_capacity": 1,
          "tokenizer_compatibility": 2,
          "参数/模板问题": 1,
          "验证失败": 39
        },
        "failureCount": 120,
        "failureRate": 0.9302,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 9,
        "successRate": 0.0698,
        "total": 129,
        "unresolvedFailureCount": 87
      },
      "Cambricon_mlu-370-x8": {
        "attributableFailureCount": 20,
        "decisionFailureRate": 0.6667,
        "decisionSuccessRate": 0.3333,
        "decisionTotal": 30,
        "failureBreakdown": {
          "ambiguous_runtime": 50,
          "framework_architecture_unsupported": 17,
          "memory_capacity": 1,
          "tokenizer_compatibility": 2,
          "参数/模板问题": 18,
          "验证失败": 22
        },
        "failureCount": 110,
        "failureRate": 0.9167,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 10,
        "successRate": 0.0833,
        "total": 120,
        "unresolvedFailureCount": 90
      },
      "Iluvatar_bi-100": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 9,
          "验证失败": 20
        },
        "failureCount": 29,
        "failureRate": 1.0,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "total": 29,
        "unresolvedFailureCount": 29
      },
      "Iluvatar_bi-150": {
        "attributableFailureCount": 53,
        "decisionFailureRate": 0.7465,
        "decisionSuccessRate": 0.2535,
        "decisionTotal": 71,
        "failureBreakdown": {
          "ambiguous_runtime": 20,
          "backend_operator": 7,
          "framework_architecture_unsupported": 22,
          "model_load": 12,
          "repository_structure": 1,
          "runtime_memory": 11,
          "参数/模板问题": 3,
          "验证失败": 30
        },
        "failureCount": 106,
        "failureRate": 0.8548,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 18,
        "successRate": 0.1452,
        "total": 124,
        "unresolvedFailureCount": 53
      },
      "Iluvatar_mrv-100": {
        "attributableFailureCount": 120,
        "decisionFailureRate": 0.8392,
        "decisionSuccessRate": 0.1608,
        "decisionTotal": 143,
        "failureBreakdown": {
          "ambiguous_runtime": 27,
          "framework_architecture_unsupported": 74,
          "memory_capacity": 1,
          "model_load": 44,
          "platform_infrastructure": 1,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 3,
          "验证失败": 47
        },
        "failureCount": 198,
        "failureRate": 0.8959,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 1,
        "successCount": 23,
        "successRate": 0.1041,
        "total": 221,
        "unresolvedFailureCount": 77
      },
      "Kunlunxin_p-800": {
        "attributableFailureCount": 1,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "ambiguous_runtime": 117,
          "memory_capacity": 1,
          "参数/模板问题": 2,
          "验证失败": 23
        },
        "failureCount": 143,
        "failureRate": 1.0,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "total": 143,
        "unresolvedFailureCount": 142
      },
      "MetaX_c-500": {
        "attributableFailureCount": 63,
        "decisionFailureRate": 0.7,
        "decisionSuccessRate": 0.3,
        "decisionTotal": 90,
        "failureBreakdown": {
          "ambiguous_runtime": 11,
          "backend_operator": 30,
          "framework_architecture_unsupported": 23,
          "memory_capacity": 1,
          "model_load": 8,
          "repository_structure": 1,
          "参数/模板问题": 19,
          "验证失败": 48
        },
        "failureCount": 141,
        "failureRate": 0.8393,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 27,
        "successRate": 0.1607,
        "total": 168,
        "unresolvedFailureCount": 78
      },
      "Mthreads_s4000": {
        "attributableFailureCount": 53,
        "decisionFailureRate": 0.803,
        "decisionSuccessRate": 0.197,
        "decisionTotal": 66,
        "failureBreakdown": {
          "ambiguous_runtime": 46,
          "backend_operator": 6,
          "framework_architecture_unsupported": 39,
          "memory_capacity": 1,
          "model_load": 3,
          "repository_structure": 1,
          "runtime_memory": 2,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 20,
          "验证失败": 26
        },
        "failureCount": 145,
        "failureRate": 0.9177,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 13,
        "successRate": 0.0823,
        "total": 158,
        "unresolvedFailureCount": 92
      },
      "Sunrise_pt-200-x1": {
        "attributableFailureCount": 76,
        "decisionFailureRate": 0.9744,
        "decisionSuccessRate": 0.0256,
        "decisionTotal": 78,
        "failureBreakdown": {
          "ambiguous_runtime": 1,
          "backend_operator": 8,
          "framework_architecture_unsupported": 12,
          "memory_capacity": 1,
          "platform_infrastructure": 10,
          "tokenizer_compatibility": 55,
          "参数/模板问题": 18,
          "验证失败": 32
        },
        "failureCount": 137,
        "failureRate": 0.9856,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 10,
        "successCount": 2,
        "successRate": 0.0144,
        "total": 139,
        "unresolvedFailureCount": 51
      },
      "Vastai_va16": {
        "attributableFailureCount": 62,
        "decisionFailureRate": 0.7654,
        "decisionSuccessRate": 0.2346,
        "decisionTotal": 81,
        "failureBreakdown": {
          "ambiguous_runtime": 80,
          "framework_architecture_unsupported": 55,
          "memory_capacity": 1,
          "model_load": 6,
          "参数/模板问题": 15,
          "验证失败": 130
        },
        "failureCount": 287,
        "failureRate": 0.9379,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 19,
        "successRate": 0.0621,
        "total": 306,
        "unresolvedFailureCount": 225
      },
      "hygon_k100-ai": {
        "attributableFailureCount": 69,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 69,
        "failureBreakdown": {
          "ambiguous_runtime": 37,
          "framework_architecture_unsupported": 53,
          "memory_capacity": 1,
          "model_load": 6,
          "repository_structure": 4,
          "runtime_memory": 5,
          "参数/模板问题": 10,
          "验证失败": 27
        },
        "failureCount": 143,
        "failureRate": 1.0,
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "total": 143,
        "unresolvedFailureCount": 74
      }
    },
    "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_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": 103,
    "profileCombinationStats": {
      "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|llama|awq": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 4
        },
        "failureCount": 4,
        "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": 4,
        "unresolvedFailureCount": 4
      },
      "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 0.5,
        "framework": "vllm_tokenizer_patch",
        "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": {
        "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|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": "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": 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": "Ascend_910-b3",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|fp8": {
        "attributableFailureCount": 1,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "framework_architecture_unsupported": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm_tokenizer_patch",
        "modelType": "spark2_5",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "fp8",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Ascend_910-b3",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "Ascend_910-b3|vllm|text-generation|qwen3|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 7,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 0.125,
        "framework": "vllm",
        "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-b4|vllm_tokenizer_patch|text-generation|lfm2|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm_tokenizer_patch",
        "modelType": "lfm2",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Ascend_910-b4",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm_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": 1,
        "unresolvedFailureCount": 1
      },
      "Ascend_910-b4|vllm_tokenizer_patch|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_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": 2,
        "unresolvedFailureCount": 2
      },
      "Ascend_910-b4|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": "Ascend_910-b4",
        "taskType": "text-generation",
        "total": 1,
        "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": 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": "Ascend_910-b4",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "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|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
      },
      "Biren_166m|vllm|text-generation|lfm2|none": {
        "attributableFailureCount": 1,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "model_load": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm",
        "modelType": "lfm2",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Biren_166m",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "Biren_166m|vllm|text-generation|llama|awq": {
        "attributableFailureCount": 4,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 4,
        "failureBreakdown": {
          "model_load": 4
        },
        "failureCount": 4,
        "failureRate": 1.0,
        "framework": "vllm",
        "modelType": "llama",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "awq",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Biren_166m",
        "taskType": "text-generation",
        "total": 4,
        "unresolvedFailureCount": 0
      },
      "Biren_166m|vllm|text-generation|llama|none": {
        "attributableFailureCount": 1,
        "decisionFailureRate": 0.5,
        "decisionSuccessRate": 0.5,
        "decisionTotal": 2,
        "failureBreakdown": {
          "tokenizer_compatibility": 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": "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|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|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": 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": "compressed-tensors",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Biren_166m",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "Biren_166m|vllm|text-generation|qwen3_5_moe|none": {
        "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": 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": "Biren_166m",
        "taskType": "text-generation",
        "total": 1,
        "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": 3,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 3,
        "failureBreakdown": {
          "framework_architecture_unsupported": 3
        },
        "failureCount": 3,
        "failureRate": 1.0,
        "framework": "vllm",
        "modelType": "qwen3_5",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Biren_166m",
        "taskType": "text-generation",
        "total": 3,
        "unresolvedFailureCount": 0
      },
      "Biren_166m|vllm|text-generation|qwen3|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 8,
        "failureBreakdown": {},
        "failureCount": 0,
        "failureRate": 0.0,
        "framework": "vllm",
        "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|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|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
      },
      "Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|awq": {
        "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": "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|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 2
        },
        "failureCount": 2,
        "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": 2,
        "unresolvedFailureCount": 2
      },
      "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": 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": "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|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 5,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 0.1667,
        "framework": "vllm-mlu",
        "modelType": "qwen3",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 5,
        "successRate": 0.8333,
        "targetGpu": "Cambricon_mlu-370-x4",
        "taskType": "text-generation",
        "total": 6,
        "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-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|llama|awq": {
        "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": "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|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": "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": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 0.5,
        "framework": "vllm-mlu",
        "modelType": "llama",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 1,
        "successRate": 0.5,
        "targetGpu": "Cambricon_mlu-370-x8",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 1
      },
      "Cambricon_mlu-370-x8|vllm-mlu|text-generation|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": 3
        },
        "failureCount": 3,
        "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": 3,
        "unresolvedFailureCount": 3
      },
      "Cambricon_mlu-370-x8|vllm-mlu|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-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": 1,
        "unresolvedFailureCount": 1
      },
      "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|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|none": {
        "attributableFailureCount": 1,
        "decisionFailureRate": 0.125,
        "decisionSuccessRate": 0.875,
        "decisionTotal": 8,
        "failureBreakdown": {
          "ambiguous_runtime": 1,
          "tokenizer_compatibility": 1
        },
        "failureCount": 2,
        "failureRate": 0.2222,
        "framework": "vllm-mlu",
        "modelType": "qwen3",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 7,
        "successRate": 0.7778,
        "targetGpu": "Cambricon_mlu-370-x8",
        "taskType": "text-generation",
        "total": 9,
        "unresolvedFailureCount": 1
      },
      "Cambricon_mlu-370-x8|vllm-mlu|text-generation|rwkv7|none": {
        "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|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": 6
        },
        "failureCount": 6,
        "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": 6,
        "unresolvedFailureCount": 6
      },
      "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|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
      },
      "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|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|llama|awq": {
        "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",
        "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": {
        "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": 0.5,
        "decisionSuccessRate": 0.5,
        "decisionTotal": 2,
        "failureBreakdown": {
          "model_load": 1
        },
        "failureCount": 1,
        "failureRate": 0.5,
        "framework": "vllm_0_17_0_corex_4_4_0",
        "modelType": "llama",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 1,
        "successRate": 0.5,
        "targetGpu": "Iluvatar_bi-150",
        "taskType": "text-generation",
        "total": 2,
        "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|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": 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": "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|qwen3_5_moe|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm_0_17_0_corex_4_4_0",
        "modelType": "qwen3_5_moe",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Iluvatar_bi-150",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_text|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": "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": {
        "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": 3,
          "参数/模板问题": 1
        },
        "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": "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|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 8,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 0.1111,
        "framework": "vllm_0_17_0_corex_4_4_0",
        "modelType": "qwen3",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 8,
        "successRate": 0.8889,
        "targetGpu": "Iluvatar_bi-150",
        "taskType": "text-generation",
        "total": 9,
        "unresolvedFailureCount": 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|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": 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": "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_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": 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": "awq",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "Iluvatar_mrv-100|vllm|text-generation|llama|none": {
        "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": "none",
        "successCount": 1,
        "successRate": 0.5,
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 1
      },
      "Iluvatar_mrv-100|vllm|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",
        "modelType": "qwen3_5_moe",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "compressed-tensors",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 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": 3,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 3,
        "failureBreakdown": {
          "framework_architecture_unsupported": 3
        },
        "failureCount": 3,
        "failureRate": 1.0,
        "framework": "vllm",
        "modelType": "qwen3_5",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 3,
        "unresolvedFailureCount": 0
      },
      "Iluvatar_mrv-100|vllm|text-generation|qwen3|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 0.5,
        "framework": "vllm",
        "modelType": "qwen3",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 1,
        "successRate": 0.5,
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 1
      },
      "Iluvatar_mrv-100|vllm|text-generation|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|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|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|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|llama|awq": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 4
        },
        "failureCount": 4,
        "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": 4,
        "unresolvedFailureCount": 4
      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 9
        },
        "failureCount": 9,
        "failureRate": 1.0,
        "framework": "vllm_fix_tokenizer",
        "modelType": "llama",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "compressed-tensors",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 9,
        "unresolvedFailureCount": 9
      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|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": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 2
      },
      "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": 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": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 3,
        "unresolvedFailureCount": 3
      },
      "Kunlunxin_p-800|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": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|compressed-tensors": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 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": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 2
      },
      "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|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": 7,
          "参数/模板问题": 1
        },
        "failureCount": 8,
        "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": 8,
        "unresolvedFailureCount": 8
      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 10
        },
        "failureCount": 10,
        "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": 10,
        "unresolvedFailureCount": 10
      },
      "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|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": 7
        },
        "failureCount": 7,
        "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": 7,
        "unresolvedFailureCount": 7
      },
      "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": {
          "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": "MetaX_c-500",
        "taskType": "text-generation",
        "total": 1,
        "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|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": 5,
        "failureBreakdown": {},
        "failureCount": 0,
        "failureRate": 0.0,
        "framework": "vllm",
        "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": {
        "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": 0.5,
        "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": "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|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": "MetaX_c-500",
        "taskType": "text-generation",
        "total": 9,
        "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|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|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|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": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "Mthreads_s4000|vllm|text-generation|llama|awq": {
        "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": "awq",
        "successCount": 4,
        "successRate": 0.6667,
        "targetGpu": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 6,
        "unresolvedFailureCount": 2
      },
      "Mthreads_s4000|vllm|text-generation|llama|none": {
        "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": "none",
        "successCount": 1,
        "successRate": 0.5,
        "targetGpu": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 2,
        "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|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|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": 5,
        "failureBreakdown": {},
        "failureCount": 0,
        "failureRate": 0.0,
        "framework": "vllm",
        "modelType": "qwen3",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 5,
        "successRate": 1.0,
        "targetGpu": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 5,
        "unresolvedFailureCount": 0
      },
      "Mthreads_s4000|vllm|text-generation|spark2_5|fp8": {
        "attributableFailureCount": 1,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "framework_architecture_unsupported": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm",
        "modelType": "spark2_5",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "fp8",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "Mthreads_s4000|vllm|text-generation|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": 5,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 5,
        "failureBreakdown": {
          "backend_operator": 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": "Sunrise_pt-200-x1",
        "taskType": "text-generation",
        "total": 5,
        "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|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|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|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|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": "Vastai_va16",
        "taskType": "text-generation",
        "total": 5,
        "unresolvedFailureCount": 5
      },
      "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|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|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|none": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 1,
        "failureBreakdown": {},
        "failureCount": 0,
        "failureRate": 0.0,
        "framework": "vllm_fix_tokenizer",
        "modelType": "qwen3",
        "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|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|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|llama|awq": {
        "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",
        "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|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-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": 2,
        "unresolvedFailureCount": 1
      },
      "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|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-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": 1,
        "unresolvedFailureCount": 0
      },
      "hygon_k100-ai|vllm-patch-tokenizer|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-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": 1,
        "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|none": {
        "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",
        "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": {
        "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|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
      }
    },
    "recentCombinationStats": {
      "Ascend_910-b3|unknown|text-generation": {
        "attributableFailureCount": 0,
        "consecutiveFailures": 0,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "参数/模板问题": 2
        },
        "failureCount": 2,
        "failureRate": 0.6667,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-16T16:08:21.748752+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 1,
        "successRate": 0.3333,
        "targetGpu": "Ascend_910-b3",
        "taskType": "text-generation",
        "total": 3,
        "unresolvedFailureCount": 2
      },
      "Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
        "attributableFailureCount": 4,
        "consecutiveFailures": 4,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 4,
        "failureBreakdown": {
          "ambiguous_runtime": 1,
          "framework_architecture_unsupported": 4
        },
        "failureCount": 5,
        "failureRate": 1.0,
        "framework": "vllm_tokenizer_patch",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-15T12:23:08.015674+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Ascend_910-b3",
        "taskType": "text-generation",
        "total": 5,
        "unresolvedFailureCount": 1
      },
      "Ascend_910-b3|vllm|text-generation": {
        "attributableFailureCount": 17,
        "consecutiveFailures": 17,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 17,
        "failureBreakdown": {
          "ambiguous_runtime": 3,
          "framework_architecture_unsupported": 17
        },
        "failureCount": 20,
        "failureRate": 1.0,
        "framework": "vllm",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-17T16:28:20.827018+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Ascend_910-b3",
        "taskType": "text-generation",
        "total": 20,
        "unresolvedFailureCount": 3
      },
      "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": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-16T16:08:21.748785+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Ascend_910-b4",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "Ascend_910-b4|vllm|text-generation": {
        "attributableFailureCount": 12,
        "consecutiveFailures": 12,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 12,
        "failureBreakdown": {
          "ambiguous_runtime": 8,
          "framework_architecture_unsupported": 12
        },
        "failureCount": 20,
        "failureRate": 1.0,
        "framework": "vllm",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-17T03:22:03.500197+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Ascend_910-b4",
        "taskType": "text-generation",
        "total": 20,
        "unresolvedFailureCount": 8
      },
      "Biren_166m|unknown|text-generation": {
        "attributableFailureCount": 12,
        "consecutiveFailures": 8,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 0.9231,
        "decisionSuccessRate": 0.0769,
        "decisionTotal": 13,
        "failureBreakdown": {
          "ambiguous_runtime": 6,
          "framework_architecture_unsupported": 9,
          "model_load": 1,
          "runtime_memory": 2,
          "参数/模板问题": 1
        },
        "failureCount": 19,
        "failureRate": 0.95,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-17T11:44:39.929678+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 1,
        "successRate": 0.05,
        "targetGpu": "Biren_166m",
        "taskType": "text-generation",
        "total": 20,
        "unresolvedFailureCount": 7
      },
      "Cambricon_mlu-370-x4|unknown|text-generation": {
        "attributableFailureCount": 10,
        "consecutiveFailures": 3,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 0.8333,
        "decisionSuccessRate": 0.1667,
        "decisionTotal": 12,
        "failureBreakdown": {
          "ambiguous_runtime": 5,
          "framework_architecture_unsupported": 9,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 1
        },
        "failureCount": 16,
        "failureRate": 0.8889,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-17T10:44:59.509445+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 2,
        "successRate": 0.1111,
        "targetGpu": "Cambricon_mlu-370-x4",
        "taskType": "text-generation",
        "total": 18,
        "unresolvedFailureCount": 6
      },
      "Cambricon_mlu-370-x8|unknown|text-generation": {
        "attributableFailureCount": 1,
        "consecutiveFailures": 1,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "ambiguous_runtime": 1,
          "framework_architecture_unsupported": 1
        },
        "failureCount": 2,
        "failureRate": 1.0,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-12T16:02:54.728775+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Cambricon_mlu-370-x8",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 1
      },
      "Iluvatar_bi-100|transformers|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": "transformers",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-12T15:08:42.332272+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Iluvatar_bi-100",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 2
      },
      "Iluvatar_bi-150|vllm|text-generation": {
        "attributableFailureCount": 9,
        "consecutiveFailures": 9,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 9,
        "failureBreakdown": {
          "backend_operator": 1,
          "framework_architecture_unsupported": 5,
          "model_load": 2,
          "repository_structure": 1
        },
        "failureCount": 9,
        "failureRate": 1.0,
        "framework": "vllm",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-13T01:11:40.231412+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Iluvatar_bi-150",
        "taskType": "text-generation",
        "total": 9,
        "unresolvedFailureCount": 0
      },
      "Iluvatar_mrv-100|unknown|text-generation": {
        "attributableFailureCount": 12,
        "consecutiveFailures": 1,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 0.6667,
        "decisionSuccessRate": 0.3333,
        "decisionTotal": 18,
        "failureBreakdown": {
          "ambiguous_runtime": 1,
          "framework_architecture_unsupported": 11,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 1
        },
        "failureCount": 14,
        "failureRate": 0.7,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 6,
        "successRate": 0.3,
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 20,
        "unresolvedFailureCount": 2
      },
      "Kunlunxin_p-800|unknown|text-generation": {
        "attributableFailureCount": 0,
        "consecutiveFailures": 0,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 17
        },
        "failureCount": 17,
        "failureRate": 1.0,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-17T14:07:00.815583+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 17,
        "unresolvedFailureCount": 17
      },
      "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": "2026-09-15T22:59:41.110897+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
      },
      "MetaX_c-500|unknown|text-generation": {
        "attributableFailureCount": 0,
        "consecutiveFailures": 0,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "参数/模板问题": 2
        },
        "failureCount": 2,
        "failureRate": 1.0,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-16T16:08:21.748761+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "MetaX_c-500",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 2
      },
      "MetaX_c-500|vllm|text-generation": {
        "attributableFailureCount": 7,
        "consecutiveFailures": 7,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 7,
        "failureBreakdown": {
          "ambiguous_runtime": 2,
          "backend_operator": 1,
          "framework_architecture_unsupported": 2,
          "model_load": 3,
          "repository_structure": 1
        },
        "failureCount": 9,
        "failureRate": 1.0,
        "framework": "vllm",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-17T01:10:41.230667+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "MetaX_c-500",
        "taskType": "text-generation",
        "total": 9,
        "unresolvedFailureCount": 2
      },
      "Mthreads_s4000|unknown|text-generation": {
        "attributableFailureCount": 0,
        "consecutiveFailures": 0,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "参数/模板问题": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-16T16:08:21.748777+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "Mthreads_s4000|vllm|text-generation": {
        "attributableFailureCount": 13,
        "consecutiveFailures": 13,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 13,
        "failureBreakdown": {
          "ambiguous_runtime": 3,
          "backend_operator": 2,
          "framework_architecture_unsupported": 10,
          "tokenizer_compatibility": 1,
          "参数/模板问题": 4
        },
        "failureCount": 20,
        "failureRate": 1.0,
        "framework": "vllm",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-18T15:57:57.287164+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 20,
        "unresolvedFailureCount": 7
      },
      "Sunrise_pt-200-x1|unknown|text-generation": {
        "attributableFailureCount": 0,
        "consecutiveFailures": 0,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "参数/模板问题": 2
        },
        "failureCount": 2,
        "failureRate": 0.6667,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-18T12:02:30.805315+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 1,
        "successRate": 0.3333,
        "targetGpu": "Sunrise_pt-200-x1",
        "taskType": "text-generation",
        "total": 3,
        "unresolvedFailureCount": 2
      },
      "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
        "attributableFailureCount": 9,
        "consecutiveFailures": 9,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 9,
        "failureBreakdown": {
          "framework_architecture_unsupported": 4,
          "platform_infrastructure": 4,
          "tokenizer_compatibility": 5
        },
        "failureCount": 13,
        "failureRate": 1.0,
        "framework": "vllm_fix_tokenizer",
        "lastPlatformFailureAt": "2026-09-16T02:03:21+00:00",
        "lastTerminalAt": "2026-09-18T05:37:23.595667+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 4,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Sunrise_pt-200-x1",
        "taskType": "text-generation",
        "total": 13,
        "unresolvedFailureCount": 0
      },
      "Sunrise_pt-200-x1|vllm|text-generation": {
        "attributableFailureCount": 7,
        "consecutiveFailures": 7,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 7,
        "failureBreakdown": {
          "backend_operator": 1,
          "framework_architecture_unsupported": 3,
          "memory_capacity": 1,
          "platform_infrastructure": 1,
          "tokenizer_compatibility": 2,
          "参数/模板问题": 1
        },
        "failureCount": 9,
        "failureRate": 1.0,
        "framework": "vllm",
        "lastPlatformFailureAt": "2026-09-15T06:15:21+00:00",
        "lastTerminalAt": "2026-09-16T01:44:44.924001+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 1,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Sunrise_pt-200-x1",
        "taskType": "text-generation",
        "total": 9,
        "unresolvedFailureCount": 1
      },
      "Vastai_va16|unknown|text-generation": {
        "attributableFailureCount": 0,
        "consecutiveFailures": 0,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 5,
        "failureBreakdown": {
          "参数/模板问题": 2
        },
        "failureCount": 2,
        "failureRate": 0.2857,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-17T14:07:00.815606+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 5,
        "successRate": 0.7143,
        "targetGpu": "Vastai_va16",
        "taskType": "text-generation",
        "total": 7,
        "unresolvedFailureCount": 2
      },
      "Vastai_va16|vllm|text-generation": {
        "attributableFailureCount": 9,
        "consecutiveFailures": 9,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 9,
        "failureBreakdown": {
          "ambiguous_runtime": 11,
          "framework_architecture_unsupported": 9
        },
        "failureCount": 20,
        "failureRate": 1.0,
        "framework": "vllm",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-18T04:07:34.207962+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Vastai_va16",
        "taskType": "text-generation",
        "total": 20,
        "unresolvedFailureCount": 11
      },
      "hygon_k100-ai|llamacpp|text-generation": {
        "attributableFailureCount": 0,
        "consecutiveFailures": 0,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "llamacpp",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-17T16:51:47.754691+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "hygon_k100-ai",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "hygon_k100-ai|unknown|text-generation": {
        "attributableFailureCount": 0,
        "consecutiveFailures": 0,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "参数/模板问题": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "unknown",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-16T16:08:21.748716+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": 14,
        "consecutiveFailures": 14,
        "consecutivePlatformFailures": 0,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 14,
        "failureBreakdown": {
          "ambiguous_runtime": 6,
          "framework_architecture_unsupported": 13,
          "model_load": 1
        },
        "failureCount": 20,
        "failureRate": 1.0,
        "framework": "vllm",
        "lastPlatformFailureAt": null,
        "lastTerminalAt": "2026-09-17T10:10:02.608119+00:00",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "hygon_k100-ai",
        "taskType": "text-generation",
        "total": 20,
        "unresolvedFailureCount": 6
      }
    },
    "recentProfileCombinationStats": {
      "Ascend_910-b3|vllm_tokenizer_patch|text-generation|gemma4|none": {
        "attributableFailureCount": 4,
        "consecutiveFailures": 4,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 4,
        "failureBreakdown": {
          "framework_architecture_unsupported": 4
        },
        "failureCount": 4,
        "failureRate": 1.0,
        "framework": "vllm_tokenizer_patch",
        "lastTerminalAt": "2026-09-15T12:23:08.015674+00:00",
        "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|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": "2026-09-15T11:29:34.655390+00:00",
        "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
      },
      "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
        "attributableFailureCount": 0,
        "consecutiveFailures": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 2
        },
        "failureCount": 2,
        "failureRate": 1.0,
        "framework": "vllm_fix_tokenizer",
        "lastTerminalAt": "2026-09-15T22:59:41.110897+00:00",
        "modelType": "qwen3_5_moe",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 2
      },
      "Mthreads_s4000|vllm|text-generation|gemma4|none": {
        "attributableFailureCount": 3,
        "consecutiveFailures": 3,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 3,
        "failureBreakdown": {
          "framework_architecture_unsupported": 3
        },
        "failureCount": 3,
        "failureRate": 1.0,
        "framework": "vllm",
        "lastTerminalAt": "2026-09-17T01:28:07.114653+00:00",
        "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|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",
        "lastTerminalAt": "2026-09-17T01:10:41.230625+00:00",
        "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|qwen3_5_moe|none": {
        "attributableFailureCount": 2,
        "consecutiveFailures": 2,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 2,
        "failureBreakdown": {
          "framework_architecture_unsupported": 2
        },
        "failureCount": 2,
        "failureRate": 1.0,
        "framework": "vllm",
        "lastTerminalAt": "2026-09-17T01:19:27.449250+00:00",
        "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
      }
    },
    "sizedProfileCombinationStats": {
      "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|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|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": {},
        "failureCount": 0,
        "failureRate": 0.0,
        "framework": "vllm_tokenizer_patch",
        "loadSizeLog2Bucket": 32,
        "modelType": "llama",
        "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|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|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": "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|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|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-b4|vllm_tokenizer_patch|text-generation|lfm2|none|29": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm_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": 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|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": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm_tokenizer_patch",
        "loadSizeLog2Bucket": 32,
        "modelType": "llama",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "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": 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": "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|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|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
      },
      "Biren_166m|vllm|text-generation|lfm2|none|29": {
        "attributableFailureCount": 1,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 1,
        "failureBreakdown": {
          "model_load": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm",
        "loadSizeLog2Bucket": 29,
        "modelType": "lfm2",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "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|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": 1,
        "failureBreakdown": {},
        "failureCount": 0,
        "failureRate": 0.0,
        "framework": "vllm",
        "loadSizeLog2Bucket": 32,
        "modelType": "llama",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 1,
        "successRate": 1.0,
        "targetGpu": "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|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|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": 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": "compressed-tensors",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Biren_166m",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "Biren_166m|vllm|text-generation|qwen3_5_moe|none|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|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": 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": "Biren_166m",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "Biren_166m|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": "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|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|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
      },
      "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|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": 1
        },
        "failureCount": 1,
        "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": 1,
        "unresolvedFailureCount": 1
      },
      "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|none|32": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 5,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 0.1667,
        "framework": "vllm-mlu",
        "loadSizeLog2Bucket": 32,
        "modelType": "qwen3",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 5,
        "successRate": 0.8333,
        "targetGpu": "Cambricon_mlu-370-x4",
        "taskType": "text-generation",
        "total": 6,
        "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-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|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|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": 2
        },
        "failureCount": 2,
        "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": 2,
        "unresolvedFailureCount": 2
      },
      "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": 1,
        "failureBreakdown": {},
        "failureCount": 0,
        "failureRate": 0.0,
        "framework": "vllm-mlu",
        "loadSizeLog2Bucket": 32,
        "modelType": "llama",
        "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|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|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": "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-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|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|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|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|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|34": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 2
        },
        "failureCount": 2,
        "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": 2,
        "unresolvedFailureCount": 2
      },
      "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|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
      },
      "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|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|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": 1,
        "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": 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|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|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": 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": "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|qwen3_5_moe|none|34": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm_0_17_0_corex_4_4_0",
        "loadSizeLog2Bucket": 34,
        "modelType": "qwen3_5_moe",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Iluvatar_bi-150",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_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|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": 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": "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|34": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 1,
          "参数/模板问题": 1
        },
        "failureCount": 2,
        "failureRate": 1.0,
        "framework": "vllm_0_17_0_corex_4_4_0",
        "loadSizeLog2Bucket": 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": 2
      },
      "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|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|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": "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_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|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|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": 1,
        "failureBreakdown": {},
        "failureCount": 0,
        "failureRate": 0.0,
        "framework": "vllm",
        "loadSizeLog2Bucket": 32,
        "modelType": "llama",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 1,
        "successRate": 1.0,
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "Iluvatar_mrv-100|vllm|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",
        "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": 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": 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": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 0
      },
      "Iluvatar_mrv-100|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": "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": 1,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 0.5,
        "framework": "vllm",
        "loadSizeLog2Bucket": 32,
        "modelType": "qwen3",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 1,
        "successRate": 0.5,
        "targetGpu": "Iluvatar_mrv-100",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 1
      },
      "Iluvatar_mrv-100|vllm|text-generation|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|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|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|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|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": 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": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "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": 2
        },
        "failureCount": 2,
        "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": 2,
        "unresolvedFailureCount": 2
      },
      "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": 5
        },
        "failureCount": 5,
        "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": 5,
        "unresolvedFailureCount": 5
      },
      "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": 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": "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|33": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 2
        },
        "failureCount": 2,
        "failureRate": 1.0,
        "framework": "vllm_fix_tokenizer",
        "loadSizeLog2Bucket": 33,
        "modelType": "phi3",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "compressed-tensors",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 2
      },
      "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|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": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 2,
        "unresolvedFailureCount": 2
      },
      "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|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": 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": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 3,
        "unresolvedFailureCount": 3
      },
      "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": 3,
          "参数/模板问题": 1
        },
        "failureCount": 4,
        "failureRate": 1.0,
        "framework": "vllm_fix_tokenizer",
        "loadSizeLog2Bucket": 34,
        "modelType": "qwen3_5",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 4,
        "unresolvedFailureCount": 4
      },
      "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|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": 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": "Kunlunxin_p-800",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "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
      },
      "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|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|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|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": 1,
        "failureBreakdown": {},
        "failureCount": 0,
        "failureRate": 0.0,
        "framework": "vllm",
        "loadSizeLog2Bucket": 32,
        "modelType": "llama",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 1,
        "successRate": 1.0,
        "targetGpu": "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|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|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|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|lfm2|none|29": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 0,
        "failureBreakdown": {
          "ambiguous_runtime": 1
        },
        "failureCount": 1,
        "failureRate": 1.0,
        "framework": "vllm",
        "loadSizeLog2Bucket": 29,
        "modelType": "lfm2",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 0,
        "successRate": 0.0,
        "targetGpu": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 1,
        "unresolvedFailureCount": 1
      },
      "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|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": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 1,
        "failureBreakdown": {},
        "failureCount": 0,
        "failureRate": 0.0,
        "framework": "vllm",
        "loadSizeLog2Bucket": 32,
        "modelType": "llama",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 1,
        "successRate": 1.0,
        "targetGpu": "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|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|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|32": {
        "attributableFailureCount": 0,
        "decisionFailureRate": 0.0,
        "decisionSuccessRate": 1.0,
        "decisionTotal": 4,
        "failureBreakdown": {},
        "failureCount": 0,
        "failureRate": 0.0,
        "framework": "vllm",
        "loadSizeLog2Bucket": 32,
        "modelType": "qwen3",
        "pendingCount": 0,
        "pendingRate": 0.0,
        "platformFailureCount": 0,
        "quantizationMethod": "none",
        "successCount": 4,
        "successRate": 1.0,
        "targetGpu": "Mthreads_s4000",
        "taskType": "text-generation",
        "total": 4,
        "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|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": 4,
        "decisionFailureRate": 1.0,
        "decisionSuccessRate": 0.0,
        "decisionTotal": 4,
        "failureBreakdown": {
          "backend_operator": 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": "Sunrise_pt-200-x1",
        "taskType": "text-generation",
        "total": 4,
        "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|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|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|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|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|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|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|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|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": "qwen3",
        "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|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|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|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|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|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": "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|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|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-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": 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|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|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|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
      }
    },
    "terminalRecords": 2270,
    "totalRecords": 2373,
    "totals": {
      "attributableFailureCount": 737,
      "decisionFailureRate": 0.8356,
      "decisionSuccessRate": 0.1644,
      "decisionTotal": 882,
      "failureBreakdown": {
        "ambiguous_runtime": 571,
        "backend_operator": 55,
        "framework_architecture_unsupported": 488,
        "memory_capacity": 12,
        "model_load": 88,
        "platform_infrastructure": 11,
        "repository_structure": 8,
        "runtime_memory": 20,
        "tokenizer_compatibility": 66,
        "参数/模板问题": 133,
        "验证失败": 673
      },
      "failureCount": 2125,
      "failureRate": 0.9361,
      "pendingCount": 0,
      "pendingRate": 0.0,
      "platformFailureCount": 11,
      "successCount": 145,
      "successRate": 0.0639,
      "total": 2270,
      "unresolvedFailureCount": 1377
    },
    "warnings": [
      "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
      "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
      "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 Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
      "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
      "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
      "GPU Mthreads_s4000 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 Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
      "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 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 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
      "组合 Iluvatar_bi-150|vllm|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 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 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 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 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 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
      "组合 Cambricon_mlu-370-x8|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_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
      "组合 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 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 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 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 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 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
      "组合 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 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
      "组合 MetaX_c-500|vllm|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": 2373,
  "version": 1
}