Files
submmit/.modelhub_state/outcome_checkpoint.json

18152 lines
582 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"generatedAt": "2026-09-20T06:27:56.581211+00:00",
"lastSyncTime": "2026-09-20T06:27:54.872487+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"
},
"biren_166m|vllm|text-generation|architectures:sophiaforcausallm": {
"architectureSignature": "architectures:sophiaforcausallm",
"architectures": [
"sophiaforcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-19T17:18:17.894388+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-19T17:18:17.894388+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"Arain119/Sophia"
],
"sourceTaskIds": [
"4960871"
],
"targetGpu": "Biren_166m",
"taskType": "text-generation"
},
"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": 1,
"expiresAt": "2026-10-13T01:11:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-13T01:11:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"XHToken/Spark-X2.5-1.7B"
],
"sourceTaskIds": [
"4557834"
],
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation"
},
"iluvatar_bi-150|vllm|text-generation|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:plamo3forcausallm": {
"architectureSignature": "architectures:plamo3forcausallm",
"architectures": [
"plamo3forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-19T01:47:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-19T01:47:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"pfnet/plamo-3-nict-8b-base"
],
"sourceTaskIds": [
"4460346"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
},
"vastai_va16|vllm|text-generation|architectures:rwkv5forcausallm": {
"architectureSignature": "architectures:rwkv5forcausallm",
"architectures": [
"rwkv5forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-08T18:41:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-08T18:41:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"RWKV/rwkv-5-world-1b5"
],
"sourceTaskIds": [
"4107039"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
},
"vastai_va16|vllm|text-generation|architectures:rwkv7forcausallm": {
"architectureSignature": "architectures:rwkv7forcausallm",
"architectures": [
"rwkv7forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-07T04:19:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-07T04:19:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"fla-hub/rwkv7-7.2B-g0"
],
"sourceTaskIds": [
"4079209"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
},
"vastai_va16|vllm|text-generation|architectures:spark2_5forcausallm": {
"architectureSignature": "architectures:spark2_5forcausallm",
"architectures": [
"spark2_5forcausallm"
],
"evidenceCount": 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": 10,
"expiresAt": "2026-10-19T23:03:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-19T23:03:21+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B",
"r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121",
"ornith-ai/Ornith-1.5-9B-MLX-8bit",
"cyankiwi/Ornith-1.5-9B-AWQ-INT4",
"callmezcc/Qwen3.8-27B-GPTQ-W4A16"
],
"sourceTaskIds": [
"4609086",
"4609094",
"4609081",
"4609101",
"4609083"
],
"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": 86,
"byGpuFramework": {
"Ascend_910-b3|vllm": 11,
"Ascend_910-b3|vllm_tokenizer_patch": 1,
"Ascend_910-b4|vllm": 12,
"Biren_166m|vllm": 1,
"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": 16,
"Vastai_va16|vllm_fix_tokenizer": 2,
"hygon_k100-ai|vllm": 8,
"hygon_k100-ai|vllm-patch-tokenizer": 2
},
"ttlDays": 30
},
"combinationStats": {
"Ascend_910-b3|llamacpp|text-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "llamacpp",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|unknown|feature_emb": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"日志缺失": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "feature_emb",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|unknown|text-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 6,
"failureBreakdown": {
"参数/模板问题": 19,
"日志缺失": 2,
"验证失败": 26
},
"failureCount": 47,
"failureRate": 0.8868,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.1132,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 53,
"unresolvedFailureCount": 47
},
"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": 12,
"decisionFailureRate": 0.9231,
"decisionSuccessRate": 0.0769,
"decisionTotal": 13,
"failureBreakdown": {
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 12
},
"failureCount": 19,
"failureRate": 0.95,
"framework": "vllm_tokenizer_patch",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.05,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 7
},
"Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 59,
"decisionFailureRate": 0.8429,
"decisionSuccessRate": 0.1571,
"decisionTotal": 70,
"failureBreakdown": {
"ambiguous_runtime": 51,
"framework_architecture_unsupported": 56,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 1
},
"failureCount": 110,
"failureRate": 0.9091,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 11,
"successRate": 0.0909,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 121,
"unresolvedFailureCount": 51
},
"Ascend_910-b3|vllm|visual-multi-modal": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "visual-multi-modal",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|llamacpp|text-generation": {
"attributableFailureCount": 92,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 92,
"failureBreakdown": {
"ambiguous_runtime": 19,
"memory_capacity": 9,
"model_load": 83
},
"failureCount": 111,
"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": 111,
"unresolvedFailureCount": 19
},
"Ascend_910-b4|llamacpp|unknown": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "llamacpp",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "unknown",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|llamacpp|visual-multi-modal": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "llamacpp",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "visual-multi-modal",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|unknown|text-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 2,
"参数/模板问题": 246,
"日志缺失": 11,
"验证失败": 175
},
"failureCount": 434,
"failureRate": 0.8785,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 60,
"successRate": 0.1215,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 494,
"unresolvedFailureCount": 434
},
"Ascend_910-b4|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 6,
"参数/模板问题": 8,
"日志缺失": 3
},
"failureCount": 17,
"failureRate": 0.8947,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.1053,
"targetGpu": "Ascend_910-b4",
"taskType": "visual-multi-modal",
"total": 19,
"unresolvedFailureCount": 17
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 10,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 16,
"framework_architecture_unsupported": 10
},
"failureCount": 26,
"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": 26,
"unresolvedFailureCount": 16
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 199,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 199,
"failureBreakdown": {
"ambiguous_runtime": 101,
"context_length": 1,
"framework_architecture_unsupported": 153,
"memory_capacity": 9,
"platform_infrastructure": 1,
"repository_structure": 27,
"tokenizer_compatibility": 9
},
"failureCount": 301,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 301,
"unresolvedFailureCount": 101
},
"Biren_166m|unknown|feature_emb": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "feature_emb",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|unknown|text-generation": {
"attributableFailureCount": 137,
"decisionFailureRate": 0.932,
"decisionSuccessRate": 0.068,
"decisionTotal": 147,
"failureBreakdown": {
"ambiguous_runtime": 130,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 86,
"memory_capacity": 1,
"model_load": 11,
"platform_infrastructure": 2,
"repository_structure": 18,
"runtime_memory": 2,
"tokenizer_compatibility": 5,
"参数/模板问题": 213,
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 571,
"failureRate": 0.9828,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 10,
"successRate": 0.0172,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 581,
"unresolvedFailureCount": 432
},
"Biren_166m|unknown|visual-multi-modal": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "visual-multi-modal",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 31,
"decisionFailureRate": 0.6889,
"decisionSuccessRate": 0.3111,
"decisionTotal": 45,
"failureBreakdown": {
"framework_architecture_unsupported": 24,
"model_load": 6,
"tokenizer_compatibility": 1
},
"failureCount": 31,
"failureRate": 0.6889,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.3111,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 45,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 695,
"decisionFailureRate": 0.9145,
"decisionSuccessRate": 0.0855,
"decisionTotal": 760,
"failureBreakdown": {
"ambiguous_runtime": 414,
"architecture_compatibility": 51,
"context_length": 48,
"framework_architecture_unsupported": 258,
"memory_capacity": 216,
"model_load": 4,
"platform_infrastructure": 15,
"repository_structure": 84,
"tokenizer_compatibility": 34,
"参数/模板问题": 280,
"日志缺失": 13,
"验证失败": 39
},
"failureCount": 1456,
"failureRate": 0.9573,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 15,
"successCount": 65,
"successRate": 0.0427,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1521,
"unresolvedFailureCount": 746
},
"Cambricon_mlu-370-x4|unknown|unknown": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"repository_structure": 1,
"tokenizer_compatibility": 1
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "unknown",
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|visual-multi-modal": {
"attributableFailureCount": 8,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 1,
"architecture_compatibility": 2,
"framework_architecture_unsupported": 4,
"memory_capacity": 2,
"参数/模板问题": 4
},
"failureCount": 13,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "visual-multi-modal",
"total": 13,
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 6,
"decisionFailureRate": 0.4615,
"decisionSuccessRate": 0.5385,
"decisionTotal": 13,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 6
},
"failureCount": 18,
"failureRate": 0.72,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 7,
"successRate": 0.28,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 25,
"unresolvedFailureCount": 12
},
"Cambricon_mlu-370-x8|unknown|feature_emb": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "feature_emb",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 12,
"decisionFailureRate": 0.8571,
"decisionSuccessRate": 0.1429,
"decisionTotal": 14,
"failureBreakdown": {
"ambiguous_runtime": 39,
"framework_architecture_unsupported": 8,
"memory_capacity": 3,
"tokenizer_compatibility": 1,
"参数/模板问题": 11,
"验证失败": 22
},
"failureCount": 84,
"failureRate": 0.9767,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0233,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 86,
"unresolvedFailureCount": 72
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 12,
"decisionFailureRate": 0.5,
"decisionSuccessRate": 0.5,
"decisionTotal": 24,
"failureBreakdown": {
"ambiguous_runtime": 31,
"framework_architecture_unsupported": 11,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 46,
"failureRate": 0.7931,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 12,
"successRate": 0.2069,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 58,
"unresolvedFailureCount": 34
},
"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": 35
},
"failureCount": 35,
"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": 35,
"unresolvedFailureCount": 35
},
"Iluvatar_bi-100|unknown|feature_emb": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"日志缺失": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "feature_emb",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-100|unknown|text-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 61,
"failureBreakdown": {
"ambiguous_runtime": 7,
"platform_infrastructure": 16,
"参数/模板问题": 206,
"日志缺失": 93,
"验证失败": 20
},
"failureCount": 342,
"failureRate": 0.8486,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 61,
"successRate": 0.1514,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 403,
"unresolvedFailureCount": 326
},
"Iluvatar_bi-100|unknown|text-to-image-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 59,
"platform_infrastructure": 1,
"参数/模板问题": 13,
"日志缺失": 13
},
"failureCount": 86,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-to-image-generation",
"total": 86,
"unresolvedFailureCount": 85
},
"Iluvatar_bi-100|unknown|unknown": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3,
"参数/模板问题": 1
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "unknown",
"total": 4,
"unresolvedFailureCount": 4
},
"Iluvatar_bi-100|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 33,
"参数/模板问题": 22,
"日志缺失": 27
},
"failureCount": 82,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "visual-multi-modal",
"total": 82,
"unresolvedFailureCount": 82
},
"Iluvatar_bi-100|vllm|text-generation": {
"attributableFailureCount": 192,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 192,
"failureBreakdown": {
"ambiguous_runtime": 18,
"memory_capacity": 192,
"platform_infrastructure": 611
},
"failureCount": 821,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 611,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "text-generation",
"total": 821,
"unresolvedFailureCount": 18
},
"Iluvatar_bi-100|vllm|unknown": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"platform_infrastructure": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "unknown",
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-100|vllm|visual-multi-modal": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"memory_capacity": 2,
"platform_infrastructure": 5
},
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 5,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-100",
"taskType": "visual-multi-modal",
"total": 7,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|llamacpp|reinforcement_learning": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "llamacpp",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "reinforcement_learning",
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-150|llamacpp|text-generation": {
"attributableFailureCount": 92,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 92,
"failureBreakdown": {
"ambiguous_runtime": 69,
"memory_capacity": 11,
"model_load": 81
},
"failureCount": 161,
"failureRate": 1.0,
"framework": "llamacpp",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 161,
"unresolvedFailureCount": 69
},
"Iluvatar_bi-150|llamacpp|unknown": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "llamacpp",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "unknown",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|llamacpp|visual-multi-modal": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "llamacpp",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "visual-multi-modal",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|unknown|asr": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 36,
"参数/模板问题": 9,
"日志缺失": 12
},
"failureCount": 57,
"failureRate": 0.9828,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0172,
"targetGpu": "Iluvatar_bi-150",
"taskType": "asr",
"total": 58,
"unresolvedFailureCount": 57
},
"Iluvatar_bi-150|unknown|feature_emb": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"日志缺失": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "feature_emb",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|unknown|question_answering": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"日志缺失": 1
},
"failureCount": 2,
"failureRate": 0.6667,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.3333,
"targetGpu": "Iluvatar_bi-150",
"taskType": "question_answering",
"total": 3,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|unknown|reinforcement_learning": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 6,
"参数/模板问题": 6,
"日志缺失": 11
},
"failureCount": 23,
"failureRate": 0.8846,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 3,
"successRate": 0.1154,
"targetGpu": "Iluvatar_bi-150",
"taskType": "reinforcement_learning",
"total": 26,
"unresolvedFailureCount": 23
},
"Iluvatar_bi-150|unknown|text-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 126,
"failureBreakdown": {
"ambiguous_runtime": 71,
"参数/模板问题": 260,
"日志缺失": 95,
"验证失败": 30
},
"failureCount": 456,
"failureRate": 0.7835,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 126,
"successRate": 0.2165,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 582,
"unresolvedFailureCount": 456
},
"Iluvatar_bi-150|unknown|text-to-image-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 59,
"参数/模板问题": 13,
"日志缺失": 10
},
"failureCount": 82,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-to-image-generation",
"total": 82,
"unresolvedFailureCount": 82
},
"Iluvatar_bi-150|unknown|unknown": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3,
"参数/模板问题": 1
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "unknown",
"total": 4,
"unresolvedFailureCount": 4
},
"Iluvatar_bi-150|unknown|vision_classification": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 39,
"参数/模板问题": 6,
"日志缺失": 9
},
"failureCount": 54,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "vision_classification",
"total": 54,
"unresolvedFailureCount": 54
},
"Iluvatar_bi-150|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 43,
"参数/模板问题": 23,
"日志缺失": 16
},
"failureCount": 82,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "visual-multi-modal",
"total": 82,
"unresolvedFailureCount": 82
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.6222,
"decisionSuccessRate": 0.3778,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 15,
"backend_operator": 4,
"framework_architecture_unsupported": 10,
"model_load": 5,
"runtime_memory": 9,
"参数/模板问题": 1
},
"failureCount": 44,
"failureRate": 0.7213,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 17,
"successRate": 0.2787,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 61,
"unresolvedFailureCount": 16
},
"Iluvatar_bi-150|vllm|reinforcement_learning": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 14,
"platform_infrastructure": 6
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "reinforcement_learning",
"total": 20,
"unresolvedFailureCount": 14
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 566,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 566,
"failureBreakdown": {
"ambiguous_runtime": 208,
"architecture_compatibility": 14,
"backend_operator": 6,
"context_length": 29,
"framework_architecture_unsupported": 215,
"memory_capacity": 123,
"model_load": 32,
"platform_infrastructure": 15,
"repository_structure": 98,
"runtime_memory": 3,
"tokenizer_compatibility": 46
},
"failureCount": 789,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 15,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 789,
"unresolvedFailureCount": 208
},
"Iluvatar_bi-150|vllm|unknown": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"repository_structure": 1
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "unknown",
"total": 2,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|visual-multi-modal": {
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1,
"architecture_compatibility": 1,
"framework_architecture_unsupported": 1,
"memory_capacity": 2
},
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "visual-multi-modal",
"total": 5,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|transformers|text-generation": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "transformers",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|unknown|asr": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 44,
"参数/模板问题": 10
},
"failureCount": 54,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "asr",
"total": 54,
"unresolvedFailureCount": 54
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 943,
"decisionFailureRate": 0.8542,
"decisionSuccessRate": 0.1458,
"decisionTotal": 1104,
"failureBreakdown": {
"ambiguous_runtime": 187,
"architecture_compatibility": 45,
"backend_operator": 1,
"context_length": 77,
"framework_architecture_unsupported": 270,
"memory_capacity": 217,
"model_load": 84,
"platform_infrastructure": 6,
"repository_structure": 132,
"runtime_memory": 1,
"tokenizer_compatibility": 116,
"参数/模板问题": 272,
"日志缺失": 5,
"验证失败": 47
},
"failureCount": 1460,
"failureRate": 0.9007,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 6,
"successCount": 161,
"successRate": 0.0993,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1621,
"unresolvedFailureCount": 511
},
"Iluvatar_mrv-100|unknown|text-to-image-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 69,
"参数/模板问题": 13,
"日志缺失": 1
},
"failureCount": 83,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-to-image-generation",
"total": 83,
"unresolvedFailureCount": 83
},
"Iluvatar_mrv-100|unknown|unknown": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 3,
"platform_infrastructure": 1,
"repository_structure": 1,
"参数/模板问题": 1
},
"failureCount": 6,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "unknown",
"total": 6,
"unresolvedFailureCount": 4
},
"Iluvatar_mrv-100|unknown|visual-multi-modal": {
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 37,
"architecture_compatibility": 2,
"framework_architecture_unsupported": 1,
"memory_capacity": 2,
"参数/模板问题": 20
},
"failureCount": 62,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "visual-multi-modal",
"total": 62,
"unresolvedFailureCount": 57
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 14,
"decisionFailureRate": 0.6364,
"decisionSuccessRate": 0.3636,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 13,
"model_load": 1
},
"failureCount": 18,
"failureRate": 0.6923,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.3077,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 26,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 72,
"memory_capacity": 1,
"日志缺失": 1,
"验证失败": 22
},
"failureCount": 96,
"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": 96,
"unresolvedFailureCount": 95
},
"Kunlunxin_p-800|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1,
"验证失败": 1
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "visual-multi-modal",
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 78,
"参数/模板问题": 2
},
"failureCount": 80,
"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": 80,
"unresolvedFailureCount": 80
},
"Kunlunxin_r-200-8f|unknown|text-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 140,
"日志缺失": 30
},
"failureCount": 170,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_r-200-8f",
"taskType": "text-generation",
"total": 170,
"unresolvedFailureCount": 170
},
"MetaX_c-500|unknown|feature_emb": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 26,
"platform_infrastructure": 1,
"参数/模板问题": 12,
"日志缺失": 12
},
"failureCount": 51,
"failureRate": 0.9107,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 5,
"successRate": 0.0893,
"targetGpu": "MetaX_c-500",
"taskType": "feature_emb",
"total": 56,
"unresolvedFailureCount": 50
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.1958,
"decisionSuccessRate": 0.8042,
"decisionTotal": 143,
"failureBreakdown": {
"ambiguous_runtime": 103,
"context_length": 13,
"memory_capacity": 1,
"repository_structure": 14,
"参数/模板问题": 351,
"日志缺失": 1,
"验证失败": 48
},
"failureCount": 531,
"failureRate": 0.822,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 115,
"successRate": 0.178,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 646,
"unresolvedFailureCount": 503
},
"MetaX_c-500|unknown|unknown": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3,
"参数/模板问题": 1
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "unknown",
"total": 4,
"unresolvedFailureCount": 4
},
"MetaX_c-500|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 39,
"参数/模板问题": 25,
"日志缺失": 2
},
"failureCount": 66,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "visual-multi-modal",
"total": 66,
"unresolvedFailureCount": 66
},
"MetaX_c-500|vllm|feature_emb": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"repository_structure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "feature_emb",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 616,
"decisionFailureRate": 0.9655,
"decisionSuccessRate": 0.0345,
"decisionTotal": 638,
"failureBreakdown": {
"ambiguous_runtime": 124,
"architecture_compatibility": 20,
"backend_operator": 43,
"context_length": 46,
"framework_architecture_unsupported": 191,
"memory_capacity": 84,
"model_load": 58,
"platform_infrastructure": 3,
"repository_structure": 98,
"tokenizer_compatibility": 76,
"参数/模板问题": 9
},
"failureCount": 752,
"failureRate": 0.9716,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 22,
"successRate": 0.0284,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 774,
"unresolvedFailureCount": 133
},
"MetaX_c-500|vllm|unknown": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"platform_infrastructure": 1,
"repository_structure": 1
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "unknown",
"total": 2,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|visual-multi-modal": {
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 1,
"architecture_compatibility": 1,
"framework_architecture_unsupported": 4
},
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "visual-multi-modal",
"total": 6,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|llamacpp|text-generation": {
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 1,
"model_load": 3
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "llamacpp",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|unknown|text-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 20,
"failureBreakdown": {
"参数/模板问题": 19,
"日志缺失": 6,
"验证失败": 25
},
"failureCount": 50,
"failureRate": 0.7143,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 20,
"successRate": 0.2857,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 70,
"unresolvedFailureCount": 50
},
"Mthreads_s4000|unknown|unknown": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2,
"参数/模板问题": 1
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "unknown",
"total": 3,
"unresolvedFailureCount": 3
},
"Mthreads_s4000|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 43,
"参数/模板问题": 24,
"日志缺失": 90,
"验证失败": 1
},
"failureCount": 158,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "visual-multi-modal",
"total": 158,
"unresolvedFailureCount": 158
},
"Mthreads_s4000|vllm|text-generation": {
"attributableFailureCount": 65,
"decisionFailureRate": 0.7927,
"decisionSuccessRate": 0.2073,
"decisionTotal": 82,
"failureBreakdown": {
"ambiguous_runtime": 58,
"backend_operator": 8,
"framework_architecture_unsupported": 48,
"memory_capacity": 1,
"model_load": 2,
"repository_structure": 1,
"runtime_memory": 4,
"tokenizer_compatibility": 1,
"参数/模板问题": 12
},
"failureCount": 135,
"failureRate": 0.8882,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 17,
"successRate": 0.1118,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 152,
"unresolvedFailureCount": 70
},
"Mthreads_s4000|vllm|visual-multi-modal": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "visual-multi-modal",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|unknown|feature_emb": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "feature_emb",
"total": 1,
"unresolvedFailureCount": 1
},
"Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 13,
"decisionFailureRate": 0.1327,
"decisionSuccessRate": 0.8673,
"decisionTotal": 98,
"failureBreakdown": {
"ambiguous_runtime": 52,
"context_length": 5,
"repository_structure": 8,
"参数/模板问题": 212,
"验证失败": 32
},
"failureCount": 309,
"failureRate": 0.7843,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 85,
"successRate": 0.2157,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 394,
"unresolvedFailureCount": 296
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 102,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 102,
"failureBreakdown": {
"backend_operator": 8,
"framework_architecture_unsupported": 12,
"platform_infrastructure": 16,
"tokenizer_compatibility": 82,
"参数/模板问题": 6
},
"failureCount": 124,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 124,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 611,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 611,
"failureBreakdown": {
"ambiguous_runtime": 109,
"architecture_compatibility": 43,
"backend_operator": 27,
"context_length": 34,
"framework_architecture_unsupported": 140,
"memory_capacity": 113,
"platform_infrastructure": 202,
"repository_structure": 75,
"runtime_memory": 1,
"tokenizer_compatibility": 178,
"参数/模板问题": 9
},
"failureCount": 931,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 202,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 931,
"unresolvedFailureCount": 118
},
"Sunrise_pt-200-x1|vllm|unknown": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"tokenizer_compatibility": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "unknown",
"total": 2,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|visual-multi-modal": {
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1,
"architecture_compatibility": 1,
"framework_architecture_unsupported": 2,
"tokenizer_compatibility": 1
},
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "visual-multi-modal",
"total": 5,
"unresolvedFailureCount": 1
},
"Vastai_va16|unknown|feature_emb": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"日志缺失": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "feature_emb",
"total": 1,
"unresolvedFailureCount": 1
},
"Vastai_va16|unknown|text-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 52,
"failureBreakdown": {
"ambiguous_runtime": 214,
"参数/模板问题": 237,
"日志缺失": 123,
"验证失败": 130
},
"failureCount": 704,
"failureRate": 0.9312,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 52,
"successRate": 0.0688,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 756,
"unresolvedFailureCount": 704
},
"Vastai_va16|unknown|unknown": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "unknown",
"total": 1,
"unresolvedFailureCount": 1
},
"Vastai_va16|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2,
"参数/模板问题": 1
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "visual-multi-modal",
"total": 3,
"unresolvedFailureCount": 3
},
"Vastai_va16|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 8,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 10,
"framework_architecture_unsupported": 7,
"model_load": 1
},
"failureCount": 18,
"failureRate": 0.9,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.1,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 10
},
"Vastai_va16|vllm|text-generation": {
"attributableFailureCount": 430,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 430,
"failureBreakdown": {
"ambiguous_runtime": 581,
"context_length": 9,
"framework_architecture_unsupported": 178,
"memory_capacity": 133,
"model_load": 42,
"platform_infrastructure": 14,
"repository_structure": 56,
"tokenizer_compatibility": 12
},
"failureCount": 1025,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 14,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1025,
"unresolvedFailureCount": 581
},
"Vastai_va16|vllm|unknown": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"repository_structure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "unknown",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm|visual-multi-modal": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 1
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "visual-multi-modal",
"total": 3,
"unresolvedFailureCount": 2
},
"hygon_k100-ai|llamacpp|text-generation": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 21
},
"failureCount": 21,
"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": 21,
"unresolvedFailureCount": 21
},
"hygon_k100-ai|unknown|text-generation": {
"attributableFailureCount": 10,
"decisionFailureRate": 0.25,
"decisionSuccessRate": 0.75,
"decisionTotal": 40,
"failureBreakdown": {
"ambiguous_runtime": 64,
"context_length": 4,
"repository_structure": 6,
"参数/模板问题": 346,
"日志缺失": 60,
"验证失败": 27
},
"failureCount": 507,
"failureRate": 0.9441,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 30,
"successRate": 0.0559,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 537,
"unresolvedFailureCount": 497
},
"hygon_k100-ai|unknown|unknown": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2,
"参数/模板问题": 1
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "unknown",
"total": 3,
"unresolvedFailureCount": 3
},
"hygon_k100-ai|unknown|visual-multi-modal": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 45,
"参数/模板问题": 21,
"日志缺失": 6
},
"failureCount": 72,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "visual-multi-modal",
"total": 72,
"unresolvedFailureCount": 72
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 17,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 17,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 11,
"model_load": 1,
"runtime_memory": 5,
"参数/模板问题": 8
},
"failureCount": 37,
"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": 37,
"unresolvedFailureCount": 20
},
"hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 646,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 646,
"failureBreakdown": {
"ambiguous_runtime": 151,
"architecture_compatibility": 30,
"attention_backend": 1,
"context_length": 42,
"framework_architecture_unsupported": 219,
"memory_capacity": 58,
"model_load": 56,
"platform_infrastructure": 3,
"repository_structure": 109,
"runtime_memory": 52,
"tokenizer_compatibility": 79
},
"failureCount": 800,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 800,
"unresolvedFailureCount": 151
},
"hygon_k100-ai|vllm|unknown": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"platform_infrastructure": 1,
"repository_structure": 1
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "unknown",
"total": 2,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm|visual-multi-modal": {
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1,
"architecture_compatibility": 2,
"framework_architecture_unsupported": 2
},
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "visual-multi-modal",
"total": 5,
"unresolvedFailureCount": 1
}
},
"frameworkSummaries": {
"llamacpp": {
"attributableFailureCount": 191,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 191,
"failureBreakdown": {
"ambiguous_runtime": 114,
"memory_capacity": 20,
"model_load": 171
},
"failureCount": 305,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 305,
"unresolvedFailureCount": 114
},
"transformers": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 35,
"framework_architecture_unsupported": 1
},
"failureCount": 36,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 36,
"unresolvedFailureCount": 35
},
"unknown": {
"attributableFailureCount": 1856,
"decisionFailureRate": 0.6975,
"decisionSuccessRate": 0.3025,
"decisionTotal": 2661,
"failureBreakdown": {
"ambiguous_runtime": 1962,
"architecture_compatibility": 100,
"backend_operator": 5,
"context_length": 157,
"framework_architecture_unsupported": 628,
"memory_capacity": 443,
"model_load": 99,
"platform_infrastructure": 42,
"repository_structure": 264,
"runtime_memory": 3,
"tokenizer_compatibility": 157,
"参数/模板问题": 3050,
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 8302,
"failureRate": 0.9116,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 42,
"successCount": 805,
"successRate": 0.0884,
"total": 9107,
"unresolvedFailureCount": 6404
},
"vllm": {
"attributableFailureCount": 3461,
"decisionFailureRate": 0.9796,
"decisionSuccessRate": 0.0204,
"decisionTotal": 3533,
"failureBreakdown": {
"ambiguous_runtime": 1426,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
"context_length": 161,
"framework_architecture_unsupported": 1252,
"memory_capacity": 718,
"model_load": 197,
"platform_infrastructure": 864,
"repository_structure": 470,
"runtime_memory": 60,
"tokenizer_compatibility": 406,
"参数/模板问题": 40
},
"failureCount": 5791,
"failureRate": 0.9877,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 864,
"successCount": 72,
"successRate": 0.0123,
"total": 5863,
"unresolvedFailureCount": 1466
},
"vllm-mlu": {
"attributableFailureCount": 18,
"decisionFailureRate": 0.4865,
"decisionSuccessRate": 0.5135,
"decisionTotal": 37,
"failureBreakdown": {
"ambiguous_runtime": 43,
"framework_architecture_unsupported": 17,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 64,
"failureRate": 0.7711,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.2289,
"total": 83,
"unresolvedFailureCount": 46
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 17,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 17,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 11,
"model_load": 1,
"runtime_memory": 5,
"参数/模板问题": 8
},
"failureCount": 37,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 37,
"unresolvedFailureCount": 20
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.6222,
"decisionSuccessRate": 0.3778,
"decisionTotal": 45,
"failureBreakdown": {
"ambiguous_runtime": 15,
"backend_operator": 4,
"framework_architecture_unsupported": 10,
"model_load": 5,
"runtime_memory": 9,
"参数/模板问题": 1
},
"failureCount": 44,
"failureRate": 0.7213,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 17,
"successRate": 0.2787,
"total": 61,
"unresolvedFailureCount": 16
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 110,
"decisionFailureRate": 0.9821,
"decisionSuccessRate": 0.0179,
"decisionTotal": 112,
"failureBreakdown": {
"ambiguous_runtime": 88,
"backend_operator": 8,
"framework_architecture_unsupported": 19,
"model_load": 1,
"platform_infrastructure": 16,
"tokenizer_compatibility": 82,
"参数/模板问题": 8
},
"failureCount": 222,
"failureRate": 0.9911,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 2,
"successRate": 0.0089,
"total": 224,
"unresolvedFailureCount": 96
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 22,
"decisionFailureRate": 0.9565,
"decisionSuccessRate": 0.0435,
"decisionTotal": 23,
"failureBreakdown": {
"ambiguous_runtime": 23,
"framework_architecture_unsupported": 22
},
"failureCount": 45,
"failureRate": 0.9783,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.0217,
"total": 46,
"unresolvedFailureCount": 23
}
},
"generatedAt": "2026-09-20T06:27:56.574090+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 72,
"decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2,
"decisionTotal": 90,
"failureBreakdown": {
"ambiguous_runtime": 59,
"framework_architecture_unsupported": 69,
"memory_capacity": 1,
"repository_structure": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 19,
"日志缺失": 3,
"验证失败": 27
},
"failureCount": 180,
"failureRate": 0.9091,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 18,
"successRate": 0.0909,
"total": 198,
"unresolvedFailureCount": 108
},
"Ascend_910-b4": {
"attributableFailureCount": 303,
"decisionFailureRate": 0.8301,
"decisionSuccessRate": 0.1699,
"decisionTotal": 365,
"failureBreakdown": {
"ambiguous_runtime": 144,
"context_length": 1,
"framework_architecture_unsupported": 163,
"memory_capacity": 18,
"model_load": 85,
"platform_infrastructure": 1,
"repository_structure": 27,
"tokenizer_compatibility": 9,
"参数/模板问题": 254,
"日志缺失": 14,
"验证失败": 175
},
"failureCount": 891,
"failureRate": 0.9349,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 62,
"successRate": 0.0651,
"total": 953,
"unresolvedFailureCount": 587
},
"Biren_166m": {
"attributableFailureCount": 169,
"decisionFailureRate": 0.8756,
"decisionSuccessRate": 0.1244,
"decisionTotal": 193,
"failureBreakdown": {
"ambiguous_runtime": 130,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 111,
"memory_capacity": 1,
"model_load": 17,
"platform_infrastructure": 2,
"repository_structure": 18,
"runtime_memory": 2,
"tokenizer_compatibility": 6,
"参数/模板问题": 214,
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 604,
"failureRate": 0.9618,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 24,
"successRate": 0.0382,
"total": 628,
"unresolvedFailureCount": 433
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 711,
"decisionFailureRate": 0.908,
"decisionSuccessRate": 0.092,
"decisionTotal": 783,
"failureBreakdown": {
"ambiguous_runtime": 427,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 268,
"memory_capacity": 218,
"model_load": 4,
"platform_infrastructure": 15,
"repository_structure": 85,
"tokenizer_compatibility": 35,
"参数/模板问题": 284,
"日志缺失": 13,
"验证失败": 39
},
"failureCount": 1489,
"failureRate": 0.9539,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 15,
"successCount": 72,
"successRate": 0.0461,
"total": 1561,
"unresolvedFailureCount": 763
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 27,
"decisionFailureRate": 0.6585,
"decisionSuccessRate": 0.3415,
"decisionTotal": 41,
"failureBreakdown": {
"ambiguous_runtime": 71,
"framework_architecture_unsupported": 22,
"memory_capacity": 3,
"tokenizer_compatibility": 2,
"参数/模板问题": 24,
"验证失败": 22
},
"failureCount": 144,
"failureRate": 0.9114,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.0886,
"total": 158,
"unresolvedFailureCount": 117
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
"decisionFailureRate": 0.7608,
"decisionSuccessRate": 0.2392,
"decisionTotal": 255,
"failureBreakdown": {
"ambiguous_runtime": 155,
"memory_capacity": 194,
"platform_infrastructure": 635,
"参数/模板问题": 242,
"日志缺失": 134,
"验证失败": 20
},
"failureCount": 1380,
"failureRate": 0.9577,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 635,
"successCount": 61,
"successRate": 0.0423,
"total": 1441,
"unresolvedFailureCount": 551
},
"Iluvatar_bi-150": {
"attributableFailureCount": 693,
"decisionFailureRate": 0.824,
"decisionSuccessRate": 0.176,
"decisionTotal": 841,
"failureBreakdown": {
"ambiguous_runtime": 569,
"architecture_compatibility": 15,
"backend_operator": 10,
"context_length": 29,
"framework_architecture_unsupported": 226,
"memory_capacity": 136,
"model_load": 120,
"platform_infrastructure": 21,
"repository_structure": 99,
"runtime_memory": 12,
"tokenizer_compatibility": 46,
"参数/模板问题": 319,
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1787,
"failureRate": 0.9235,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 148,
"successRate": 0.0765,
"total": 1935,
"unresolvedFailureCount": 1073
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 964,
"decisionFailureRate": 0.8508,
"decisionSuccessRate": 0.1492,
"decisionTotal": 1133,
"failureBreakdown": {
"ambiguous_runtime": 344,
"architecture_compatibility": 47,
"backend_operator": 1,
"context_length": 77,
"framework_architecture_unsupported": 285,
"memory_capacity": 219,
"model_load": 85,
"platform_infrastructure": 7,
"repository_structure": 133,
"runtime_memory": 1,
"tokenizer_compatibility": 116,
"参数/模板问题": 316,
"日志缺失": 6,
"验证失败": 47
},
"failureCount": 1684,
"failureRate": 0.9088,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 7,
"successCount": 169,
"successRate": 0.0912,
"total": 1853,
"unresolvedFailureCount": 713
},
"Kunlunxin_p-800": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 151,
"memory_capacity": 1,
"参数/模板问题": 2,
"日志缺失": 1,
"验证失败": 23
},
"failureCount": 178,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 178,
"unresolvedFailureCount": 177
},
"Kunlunxin_r-200-8f": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 140,
"日志缺失": 30
},
"failureCount": 170,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 170,
"unresolvedFailureCount": 170
},
"MetaX_c-500": {
"attributableFailureCount": 651,
"decisionFailureRate": 0.8209,
"decisionSuccessRate": 0.1791,
"decisionTotal": 793,
"failureBreakdown": {
"ambiguous_runtime": 296,
"architecture_compatibility": 21,
"backend_operator": 43,
"context_length": 59,
"framework_architecture_unsupported": 195,
"memory_capacity": 85,
"model_load": 58,
"platform_infrastructure": 5,
"repository_structure": 114,
"tokenizer_compatibility": 76,
"参数/模板问题": 398,
"日志缺失": 15,
"验证失败": 48
},
"failureCount": 1413,
"failureRate": 0.9087,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 5,
"successCount": 142,
"successRate": 0.0913,
"total": 1555,
"unresolvedFailureCount": 757
},
"Mthreads_s4000": {
"attributableFailureCount": 69,
"decisionFailureRate": 0.6509,
"decisionSuccessRate": 0.3491,
"decisionTotal": 106,
"failureBreakdown": {
"ambiguous_runtime": 104,
"backend_operator": 8,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 5,
"repository_structure": 1,
"runtime_memory": 4,
"tokenizer_compatibility": 1,
"参数/模板问题": 56,
"日志缺失": 96,
"验证失败": 26
},
"failureCount": 351,
"failureRate": 0.9046,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 37,
"successRate": 0.0954,
"total": 388,
"unresolvedFailureCount": 282
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 732,
"decisionFailureRate": 0.896,
"decisionSuccessRate": 0.104,
"decisionTotal": 817,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
"backend_operator": 35,
"context_length": 39,
"framework_architecture_unsupported": 154,
"memory_capacity": 113,
"platform_infrastructure": 218,
"repository_structure": 83,
"runtime_memory": 1,
"tokenizer_compatibility": 263,
"参数/模板问题": 228,
"验证失败": 32
},
"failureCount": 1372,
"failureRate": 0.9417,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 218,
"successCount": 85,
"successRate": 0.0583,
"total": 1457,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
"attributableFailureCount": 440,
"decisionFailureRate": 0.8907,
"decisionSuccessRate": 0.1093,
"decisionTotal": 494,
"failureBreakdown": {
"ambiguous_runtime": 810,
"context_length": 9,
"framework_architecture_unsupported": 186,
"memory_capacity": 133,
"model_load": 43,
"platform_infrastructure": 14,
"repository_structure": 57,
"tokenizer_compatibility": 12,
"参数/模板问题": 238,
"日志缺失": 124,
"验证失败": 130
},
"failureCount": 1756,
"failureRate": 0.9702,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 14,
"successCount": 54,
"successRate": 0.0298,
"total": 1810,
"unresolvedFailureCount": 1302
},
"hygon_k100-ai": {
"attributableFailureCount": 678,
"decisionFailureRate": 0.9576,
"decisionSuccessRate": 0.0424,
"decisionTotal": 708,
"failureBreakdown": {
"ambiguous_runtime": 296,
"architecture_compatibility": 32,
"attention_backend": 1,
"context_length": 46,
"framework_architecture_unsupported": 232,
"memory_capacity": 58,
"model_load": 57,
"platform_infrastructure": 4,
"repository_structure": 116,
"runtime_memory": 57,
"tokenizer_compatibility": 79,
"参数/模板问题": 376,
"日志缺失": 66,
"验证失败": 27
},
"failureCount": 1447,
"failureRate": 0.9797,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 30,
"successRate": 0.0203,
"total": 1477,
"unresolvedFailureCount": 765
}
},
"observedGpuMemoryGiB": {
"Ascend_910-b3": 64.0,
"Ascend_910-b4": 32.0,
"Biren_166m": 64.0,
"Cambricon_mlu-370-x4": 24.0,
"Cambricon_mlu-370-x8": 24.0,
"Iluvatar_bi-100": 32.0,
"Iluvatar_bi-150": 32.0,
"Iluvatar_mrv-100": 32.0,
"Kunlunxin_p-800": 100.0,
"MetaX_c-500": 64.0,
"Mthreads_s4000": 48.0,
"Sunrise_pt-200-x1": 64.0,
"Vastai_va16": 32.0,
"hygon_k100-ai": 64.0
},
"pendingRecords": 0,
"policyCancelledRecords": 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_text|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|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": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen3_5",
"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|sophia_hybrid|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|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": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm|text-generation|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 3,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 3,
"successRate": 1.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 8,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.1111,
"framework": "vllm",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 8,
"successRate": 0.8889,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 9,
"unresolvedFailureCount": 1
},
"Ascend_910-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": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
},
"failureCount": 5,
"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": 5,
"unresolvedFailureCount": 5
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "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": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|modelopt": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3|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": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"model_load": 5
},
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 0.2,
"decisionSuccessRate": 0.8,
"decisionTotal": 5,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 0.2,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 4,
"successRate": 0.8,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"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": 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": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 4
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|escha": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "escha",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|gptq": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "gptq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|modelopt": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none": {
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 4
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 9,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 9,
"successRate": 1.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 9,
"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|sophia_hybrid|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|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-x4",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
},
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|modelopt": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none": {
"attributableFailureCount": 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": 7,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.125,
"framework": "vllm-mlu",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 7,
"successRate": 0.875,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8": {
"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": 6
},
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
},
"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": 4,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.2,
"framework": "vllm-mlu",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 4,
"successRate": 0.8,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nanbeige|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "nanbeige",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "nemotron_h",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "phi3small",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 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_text|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 0.1111,
"decisionSuccessRate": 0.8889,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 1,
"tokenizer_compatibility": 1
},
"failureCount": 2,
"failureRate": 0.2,
"framework": "vllm-mlu",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 8,
"successRate": 0.8,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|rwkv7|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|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": 0.8333,
"decisionSuccessRate": 0.1667,
"decisionTotal": 6,
"failureBreakdown": {
"runtime_memory": 5
},
"failureCount": 5,
"failureRate": 0.8333,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 1,
"successRate": 0.1667,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 3,
"decisionFailureRate": 0.75,
"decisionSuccessRate": 0.25,
"decisionTotal": 4,
"failureBreakdown": {
"backend_operator": 3
},
"failureCount": 3,
"failureRate": 0.75,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 0.25,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 0.2,
"decisionSuccessRate": 0.8,
"decisionTotal": 5,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 0.2,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 4,
"successRate": 0.8,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|nanbeige|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "nanbeige",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|phi3|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen2|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 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": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"runtime_memory": 2
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|escha": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "escha",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|gptq": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "gptq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|modelopt": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5,
"参数/模板问题": 1
},
"failureCount": 6,
"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": 6,
"unresolvedFailureCount": 6
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.1,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 9,
"successRate": 0.9,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 10,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none": {
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 4
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|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|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|compressed-tensors": {
"attributableFailureCount": 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_text|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|modelopt": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none": {
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 4
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|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": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 8,
"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|spark2_5|fp8": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|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": 5
},
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 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": 5
},
"failureCount": 5,
"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": 5,
"unresolvedFailureCount": 5
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|muse_glimmer|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": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|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_text|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|gptq": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "gptq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 8,
"参数/模板问题": 1
},
"failureCount": 9,
"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": 9,
"unresolvedFailureCount": 9
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 11
},
"failureCount": 11,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 11,
"unresolvedFailureCount": 11
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|fp8": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 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": 6,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 6,
"successRate": 1.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 15,
"decisionFailureRate": 0.9375,
"decisionSuccessRate": 0.0625,
"decisionTotal": 16,
"failureBreakdown": {
"backend_operator": 15
},
"failureCount": 15,
"failureRate": 0.9375,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 0.0625,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 0.2,
"decisionSuccessRate": 0.8,
"decisionTotal": 5,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 0.2,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 4,
"successRate": 0.8,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"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": 5,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 0.2857,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 5,
"successRate": 0.7143,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 2
},
"Mthreads_s4000|vllm|text-generation|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.3333,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successRate": 0.6667,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 3,
"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|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|nanbeige|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "nanbeige",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen2|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": 9,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 9,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 9,
"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|llama|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|minicpm|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "minicpm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|exl3": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 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": "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": 2,
"failureBreakdown": {
"ambiguous_runtime": 3
},
"failureCount": 3,
"failureRate": 0.6,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successRate": 0.4,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 3
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|zaya|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "zaya",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|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": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 3,
"runtime_memory": 2
},
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 3
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 3,
"model_load": 1,
"runtime_memory": 1
},
"failureCount": 5,
"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": 5,
"unresolvedFailureCount": 3
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|muse_glimmer|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|nanbeige|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "nanbeige",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|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": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3|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": 2,
"framework_architecture_unsupported": 4
},
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T01:06:12.681494+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 2
},
"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": 13,
"consecutiveFailures": 9,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9286,
"decisionSuccessRate": 0.0714,
"decisionTotal": 14,
"failureBreakdown": {
"ambiguous_runtime": 5,
"framework_architecture_unsupported": 10,
"model_load": 1,
"runtime_memory": 2,
"参数/模板问题": 1
},
"failureCount": 19,
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T06:27:54.872472+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 1,
"successRate": 0.05,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 6
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T06:27:54.872414+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"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": 1
},
"failureCount": 1,
"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": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm|text-generation": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"backend_operator": 1,
"framework_architecture_unsupported": 2
},
"failureCount": 3,
"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": 3,
"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": 3
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T03:35:24.469804+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"failureBreakdown": {
"参数/模板问题": 2
},
"failureCount": 2,
"failureRate": 0.5,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T05:59:18.862303+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.5,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 2
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 5,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"ambiguous_runtime": 1,
"backend_operator": 1,
"framework_architecture_unsupported": 1,
"model_load": 2,
"repository_structure": 1
},
"failureCount": 6,
"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": 6,
"unresolvedFailureCount": 1
},
"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": 10,
"consecutiveFailures": 10,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"framework_architecture_unsupported": 3,
"platform_infrastructure": 4,
"tokenizer_compatibility": 7
},
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-16T02:03:21+00:00",
"lastTerminalAt": "2026-09-19T23:13:47.695526+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"backend_operator": 1,
"framework_architecture_unsupported": 3,
"memory_capacity": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 1
},
"failureCount": 8,
"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": 8,
"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": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 6
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-20T03:09:22.973374+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 14
},
"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
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-20T01:06:12.681494+00:00",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-20T06:27:54.872414+00:00",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"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
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-20T03:35:24.469804+00:00",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"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_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|modelopt|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "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|sophia_hybrid|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 31,
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|llama|awq|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b3|vllm|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 3,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 3,
"successRate": 1.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|qwen3|none|13": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 13,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.125,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 7,
"successRate": 0.875,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 1
},
"Ascend_910-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|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|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": 4
},
"failureCount": 4,
"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": 4,
"unresolvedFailureCount": 4
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|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_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": 2,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|modelopt|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "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|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 4,
"failureBreakdown": {
"model_load": 4
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|none|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 4,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 4,
"successRate": 1.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|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": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5_text|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors|33": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|compressed-tensors|34": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|escha|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "escha",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|gptq|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "gptq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|modelopt|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|modelopt|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 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": 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": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3|none|13": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 13,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 8,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 8,
"successRate": 1.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|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|sophia_hybrid|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 31,
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|awq|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|none|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|modelopt|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.125,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 7,
"successRate": 0.875,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-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|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
},
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|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": 4,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 4,
"successRate": 1.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nanbeige|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "nanbeige",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|nemotron_h|modelopt|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 34,
"modelType": "nemotron_h",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3small|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 33,
"modelType": "phi3small",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 31,
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|phi3|compressed-tensors|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_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5_text|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none|13": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 13,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none|24": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 24,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.125,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 7,
"successRate": 0.875,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|rwkv7|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 31,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|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|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|awq|32": {
"attributableFailureCount": 5,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"failureBreakdown": {
"runtime_memory": 5
},
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors|28": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 28,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|compressed-tensors|33": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"backend_operator": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 33,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 4,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 4,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|nanbeige|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 32,
"modelType": "nanbeige",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|phi3|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 33,
"modelType": "phi3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen2|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 31,
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 3
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 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_text|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|compressed-tensors|33": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"backend_operator": 1,
"runtime_memory": 1
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1,
"runtime_memory": 1
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|escha|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "escha",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|gptq|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "gptq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|modelopt|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|modelopt|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"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": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2,
"参数/模板问题": 1
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none|13": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 13,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none|24": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 24,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 8,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 8,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 31,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 32,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 33,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|rwkv7|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"loadSizeLog2Bucket": 34,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|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|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5_moe|compressed-tensors|34": {
"attributableFailureCount": 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_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|compressed-tensors|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|modelopt|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|modelopt|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 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": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 7,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.125,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 7,
"successRate": 0.875,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|rwkv7|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_mrv-100|vllm|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|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|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 4
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|28": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 28,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 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": 4
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|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_text|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_text|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|gptq|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "gptq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 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": 4,
"参数/模板问题": 1
},
"failureCount": 5,
"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": 5,
"unresolvedFailureCount": 5
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|13": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 13,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|24": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 24,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 8
},
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 8
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3|none|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 31,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|rwkv7|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|sophia_hybrid|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 31,
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 31,
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
},
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 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|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 5,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 5,
"successRate": 1.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|28": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 28,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|30": {
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"backend_operator": 3
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 31,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|32": {
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"failureBreakdown": {
"backend_operator": 3
},
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 3,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|33": {
"attributableFailureCount": 7,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"failureBreakdown": {
"backend_operator": 7
},
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|none|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|llama|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 4,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 4,
"successRate": 1.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|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|30": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 4,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.2,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 4,
"successRate": 0.8,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|llama|awq|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Mthreads_s4000|vllm|text-generation|llama|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": 2,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|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|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|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": 8,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 8,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 8,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|qwen3|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Mthreads_s4000",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|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|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": "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|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|exl3|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "exl3",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|modelopt|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|qwen3|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 3
},
"failureCount": 3,
"failureRate": 0.6,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successRate": 0.4,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 3
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Vastai_va16|vllm_fix_tokenizer|text-generation|zaya|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "zaya",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Vastai_va16",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|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|30": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"runtime_memory": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 30,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|awq|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 3,
"runtime_memory": 1
},
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 3
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|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": 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": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 4,
"unresolvedFailureCount": 3
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|muse_glimmer|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "muse_glimmer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|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_text|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|qwen3|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": 15762,
"totalRecords": 15865,
"totals": {
"attributableFailureCount": 5704,
"decisionFailureRate": 0.8616,
"decisionSuccessRate": 0.1384,
"decisionTotal": 6620,
"failureBreakdown": {
"ambiguous_runtime": 3718,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 101,
"context_length": 318,
"framework_architecture_unsupported": 1960,
"memory_capacity": 1181,
"model_load": 474,
"platform_infrastructure": 922,
"repository_structure": 734,
"runtime_memory": 77,
"tokenizer_compatibility": 646,
"参数/模板问题": 3110,
"日志缺失": 719,
"验证失败": 673
},
"failureCount": 14846,
"failureRate": 0.9419,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 922,
"successCount": 916,
"successRate": 0.0581,
"total": 15762,
"unresolvedFailureCount": 8220
},
"warnings": [
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU MetaX_c-500 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 Ascend_910-b3 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 Iluvatar_mrv-100 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 Vastai_va16 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 Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"组合 Mthreads_s4000|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-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 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 Vastai_va16|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 MetaX_c-500|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 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 hygon_k100-ai|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 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 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 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 MetaX_c-500|vllm|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 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|llamacpp|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-100|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-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 Cambricon_mlu-370-x4|unknown|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 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 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 Ascend_910-b3|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 15865,
"version": 1
}