state: generation 9736 (cycle)

This commit is contained in:
2026-09-19 09:49:40 +00:00
parent 0f72a7842f
commit cc63977d5a
10 changed files with 1847 additions and 1825 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T09:37:07.055200+00:00",
"lastSyncTime": "2026-09-19T09:37:06.802052+00:00",
"generatedAt": "2026-09-19T09:47:26.267779+00:00",
"lastSyncTime": "2026-09-19T09:47:25.992989+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2047,25 +2047,25 @@
"unresolvedFailureCount": 79
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 4,
"decisionFailureRate": 0.3636,
"decisionSuccessRate": 0.6364,
"decisionTotal": 11,
"attributableFailureCount": 5,
"decisionFailureRate": 0.4167,
"decisionSuccessRate": 0.5833,
"decisionTotal": 12,
"failureBreakdown": {
"ambiguous_runtime": 8,
"framework_architecture_unsupported": 4
"framework_architecture_unsupported": 5
},
"failureCount": 12,
"failureRate": 0.6316,
"failureCount": 13,
"failureRate": 0.65,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 7,
"successRate": 0.3684,
"successRate": 0.35,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 19,
"total": 20,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
@@ -2249,9 +2249,9 @@
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.6512,
"decisionSuccessRate": 0.3488,
"decisionTotal": 43,
"decisionFailureRate": 0.6364,
"decisionSuccessRate": 0.3636,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 13,
"backend_operator": 4,
@@ -2261,16 +2261,16 @@
"参数/模板问题": 1
},
"failureCount": 42,
"failureRate": 0.7368,
"failureRate": 0.7241,
"framework": "vllm_0_17_0_corex_4_4_0",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.2632,
"successCount": 16,
"successRate": 0.2759,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 57,
"total": 58,
"unresolvedFailureCount": 14
},
"Iluvatar_bi-150|vllm|text-generation": {
@@ -2329,25 +2329,25 @@
},
"Iluvatar_mrv-100|vllm|text-generation": {
"attributableFailureCount": 12,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 18,
"decisionFailureRate": 0.6316,
"decisionSuccessRate": 0.3684,
"decisionTotal": 19,
"failureBreakdown": {
"ambiguous_runtime": 4,
"framework_architecture_unsupported": 11,
"model_load": 1
},
"failureCount": 16,
"failureRate": 0.7273,
"failureRate": 0.6957,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 6,
"successRate": 0.2727,
"successCount": 7,
"successRate": 0.3043,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 22,
"total": 23,
"unresolvedFailureCount": 4
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2863,9 +2863,9 @@
},
"vllm": {
"attributableFailureCount": 424,
"decisionFailureRate": 0.8833,
"decisionSuccessRate": 0.1167,
"decisionTotal": 480,
"decisionFailureRate": 0.8815,
"decisionSuccessRate": 0.1185,
"decisionTotal": 481,
"failureBreakdown": {
"ambiguous_runtime": 246,
"backend_operator": 40,
@@ -2879,34 +2879,34 @@
"参数/模板问题": 40
},
"failureCount": 712,
"failureRate": 0.9271,
"failureRate": 0.9259,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 56,
"successRate": 0.0729,
"total": 768,
"successCount": 57,
"successRate": 0.0741,
"total": 769,
"unresolvedFailureCount": 286
},
"vllm-mlu": {
"attributableFailureCount": 15,
"decisionFailureRate": 0.4839,
"decisionSuccessRate": 0.5161,
"decisionTotal": 31,
"attributableFailureCount": 16,
"decisionFailureRate": 0.5,
"decisionSuccessRate": 0.5,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 38,
"framework_architecture_unsupported": 14,
"framework_architecture_unsupported": 15,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 56,
"failureRate": 0.7778,
"failureCount": 57,
"failureRate": 0.7808,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 16,
"successRate": 0.2222,
"total": 72,
"successRate": 0.2192,
"total": 73,
"unresolvedFailureCount": 41
},
"vllm-patch-tokenizer": {
@@ -2933,9 +2933,9 @@
},
"vllm_0_17_0_corex_4_4_0": {
"attributableFailureCount": 28,
"decisionFailureRate": 0.6512,
"decisionSuccessRate": 0.3488,
"decisionTotal": 43,
"decisionFailureRate": 0.6364,
"decisionSuccessRate": 0.3636,
"decisionTotal": 44,
"failureBreakdown": {
"ambiguous_runtime": 13,
"backend_operator": 4,
@@ -2945,13 +2945,13 @@
"参数/模板问题": 1
},
"failureCount": 42,
"failureRate": 0.7368,
"failureRate": 0.7241,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 15,
"successRate": 0.2632,
"total": 57,
"successCount": 16,
"successRate": 0.2759,
"total": 58,
"unresolvedFailureCount": 14
},
"vllm_fix_tokenizer": {
@@ -2998,7 +2998,7 @@
"unresolvedFailureCount": 18
}
},
"generatedAt": "2026-09-19T09:37:07.049969+00:00",
"generatedAt": "2026-09-19T09:47:26.262417+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 62,
@@ -3075,26 +3075,26 @@
"unresolvedFailureCount": 60
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 34,
"decisionFailureRate": 0.7556,
"decisionSuccessRate": 0.2444,
"decisionTotal": 45,
"attributableFailureCount": 35,
"decisionFailureRate": 0.7609,
"decisionSuccessRate": 0.2391,
"decisionTotal": 46,
"failureBreakdown": {
"ambiguous_runtime": 47,
"framework_architecture_unsupported": 31,
"framework_architecture_unsupported": 32,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 1,
"验证失败": 39
},
"failureCount": 121,
"failureRate": 0.9167,
"failureCount": 122,
"failureRate": 0.9173,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 11,
"successRate": 0.0833,
"total": 132,
"successRate": 0.0827,
"total": 133,
"unresolvedFailureCount": 87
},
"Cambricon_mlu-370-x8": {
@@ -3141,9 +3141,9 @@
},
"Iluvatar_bi-150": {
"attributableFailureCount": 55,
"decisionFailureRate": 0.7237,
"decisionSuccessRate": 0.2763,
"decisionTotal": 76,
"decisionFailureRate": 0.7143,
"decisionSuccessRate": 0.2857,
"decisionTotal": 77,
"failureBreakdown": {
"ambiguous_runtime": 21,
"backend_operator": 7,
@@ -3155,20 +3155,20 @@
"验证失败": 30
},
"failureCount": 109,
"failureRate": 0.8385,
"failureRate": 0.8321,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 21,
"successRate": 0.1615,
"total": 130,
"successCount": 22,
"successRate": 0.1679,
"total": 131,
"unresolvedFailureCount": 54
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 121,
"decisionFailureRate": 0.8176,
"decisionSuccessRate": 0.1824,
"decisionTotal": 148,
"decisionFailureRate": 0.8121,
"decisionSuccessRate": 0.1879,
"decisionTotal": 149,
"failureBreakdown": {
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 75,
@@ -3180,13 +3180,13 @@
"验证失败": 47
},
"failureCount": 200,
"failureRate": 0.8811,
"failureRate": 0.8772,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 27,
"successRate": 0.1189,
"total": 227,
"successCount": 28,
"successRate": 0.1228,
"total": 228,
"unresolvedFailureCount": 78
},
"Kunlunxin_p-800": {
@@ -4362,14 +4362,14 @@
"unresolvedFailureCount": 2
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_5_text",
@@ -4381,7 +4381,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|exl3": {
@@ -5123,25 +5123,25 @@
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|llama|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 0.25,
"decisionSuccessRate": 0.75,
"decisionTotal": 4,
"decisionFailureRate": 0.2,
"decisionSuccessRate": 0.8,
"decisionTotal": 5,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 0.25,
"failureRate": 0.2,
"framework": "vllm_0_17_0_corex_4_4_0",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 3,
"successRate": 0.75,
"successCount": 4,
"successRate": 0.8,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|muse_glimmer|none": {
@@ -5723,23 +5723,23 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.1667,
"failureRate": 0.1429,
"framework": "vllm",
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 5,
"successRate": 0.8333,
"successCount": 6,
"successRate": 0.8571,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|rwkv7|none": {
@@ -10055,6 +10055,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5_text",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -11205,7 +11229,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -11216,11 +11240,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 3,
"successCount": 4,
"successRate": 1.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation|muse_glimmer|none|34": {
@@ -12134,12 +12158,12 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 0.1667,
"failureRate": 0.1429,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3",
@@ -12147,11 +12171,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 5,
"successRate": 0.8333,
"successCount": 6,
"successRate": 0.8571,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 6,
"total": 7,
"unresolvedFailureCount": 1
},
"Iluvatar_mrv-100|vllm|text-generation|rwkv7|none|32": {
@@ -15476,17 +15500,17 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2317,
"totalRecords": 2420,
"terminalRecords": 2320,
"totalRecords": 2423,
"totals": {
"attributableFailureCount": 760,
"decisionFailureRate": 0.827,
"decisionSuccessRate": 0.173,
"decisionTotal": 919,
"attributableFailureCount": 761,
"decisionFailureRate": 0.8254,
"decisionSuccessRate": 0.1746,
"decisionTotal": 922,
"failureBreakdown": {
"ambiguous_runtime": 581,
"backend_operator": 55,
"framework_architecture_unsupported": 510,
"framework_architecture_unsupported": 511,
"memory_capacity": 12,
"model_load": 89,
"platform_infrastructure": 11,
@@ -15496,18 +15520,18 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2158,
"failureRate": 0.9314,
"failureCount": 2159,
"failureRate": 0.9306,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 159,
"successRate": 0.0686,
"total": 2317,
"successCount": 161,
"successRate": 0.0694,
"total": 2320,
"unresolvedFailureCount": 1387
},
"warnings": [
"GPU Iluvatar_bi-150 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 Ascend_910-b3 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 Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -15518,7 +15542,7 @@
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU MetaX_c-500 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。",
"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 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_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。",
@@ -15543,6 +15567,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2420,
"summarizedRecords": 2423,
"version": 1
}