state: generation 9772 (cycle)

This commit is contained in:
2026-09-19 11:35:48 +00:00
parent 05e316a87d
commit 89ce4d874b
10 changed files with 1830 additions and 1805 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-19T11:25:32.938472+00:00",
"lastSyncTime": "2026-09-19T11:25:32.649970+00:00",
"generatedAt": "2026-09-19T11:34:11.360358+00:00",
"lastSyncTime": "2026-09-19T11:34:11.086869+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1999,25 +1999,25 @@
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 29,
"decisionFailureRate": 0.725,
"decisionSuccessRate": 0.275,
"decisionTotal": 40,
"decisionFailureRate": 0.7073,
"decisionSuccessRate": 0.2927,
"decisionTotal": 41,
"failureBreakdown": {
"framework_architecture_unsupported": 22,
"model_load": 6,
"tokenizer_compatibility": 1
},
"failureCount": 29,
"failureRate": 0.725,
"failureRate": 0.7073,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 11,
"successRate": 0.275,
"successCount": 12,
"successRate": 0.2927,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 40,
"total": 41,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2100,23 +2100,23 @@
"decisionSuccessRate": 0.4286,
"decisionTotal": 21,
"failureBreakdown": {
"ambiguous_runtime": 30,
"ambiguous_runtime": 31,
"framework_architecture_unsupported": 11,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 45,
"failureRate": 0.8333,
"failureCount": 46,
"failureRate": 0.8364,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 9,
"successRate": 0.1667,
"successRate": 0.1636,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 54,
"unresolvedFailureCount": 33
"total": 55,
"unresolvedFailureCount": 34
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3,
@@ -2440,9 +2440,9 @@
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 63,
"decisionFailureRate": 0.7683,
"decisionSuccessRate": 0.2317,
"decisionTotal": 82,
"decisionFailureRate": 0.759,
"decisionSuccessRate": 0.241,
"decisionTotal": 83,
"failureBreakdown": {
"ambiguous_runtime": 11,
"backend_operator": 30,
@@ -2453,16 +2453,16 @@
"参数/模板问题": 9
},
"failureCount": 83,
"failureRate": 0.8137,
"failureRate": 0.8058,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 19,
"successRate": 0.1863,
"successCount": 20,
"successRate": 0.1942,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 102,
"total": 103,
"unresolvedFailureCount": 20
},
"Mthreads_s4000|llamacpp|text-generation": {
@@ -2863,9 +2863,9 @@
},
"vllm": {
"attributableFailureCount": 424,
"decisionFailureRate": 0.8778,
"decisionSuccessRate": 0.1222,
"decisionTotal": 483,
"decisionFailureRate": 0.8742,
"decisionSuccessRate": 0.1258,
"decisionTotal": 485,
"failureBreakdown": {
"ambiguous_runtime": 246,
"backend_operator": 40,
@@ -2879,13 +2879,13 @@
"参数/模板问题": 40
},
"failureCount": 712,
"failureRate": 0.9235,
"failureRate": 0.9211,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 59,
"successRate": 0.0765,
"total": 771,
"successCount": 61,
"successRate": 0.0789,
"total": 773,
"unresolvedFailureCount": 286
},
"vllm-mlu": {
@@ -2894,20 +2894,20 @@
"decisionSuccessRate": 0.4848,
"decisionTotal": 33,
"failureBreakdown": {
"ambiguous_runtime": 38,
"ambiguous_runtime": 39,
"framework_architecture_unsupported": 16,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 58,
"failureRate": 0.7838,
"failureCount": 59,
"failureRate": 0.7867,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 16,
"successRate": 0.2162,
"total": 74,
"unresolvedFailureCount": 41
"successRate": 0.2133,
"total": 75,
"unresolvedFailureCount": 42
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 14,
@@ -2998,7 +2998,7 @@
"unresolvedFailureCount": 18
}
},
"generatedAt": "2026-09-19T11:25:32.932972+00:00",
"generatedAt": "2026-09-19T11:34:11.354088+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 62,
@@ -3050,9 +3050,9 @@
},
"Biren_166m": {
"attributableFailureCount": 69,
"decisionFailureRate": 0.8415,
"decisionSuccessRate": 0.1585,
"decisionTotal": 82,
"decisionFailureRate": 0.8313,
"decisionSuccessRate": 0.1687,
"decisionTotal": 83,
"failureBreakdown": {
"ambiguous_runtime": 32,
"backend_operator": 4,
@@ -3065,13 +3065,13 @@
"验证失败": 27
},
"failureCount": 129,
"failureRate": 0.9085,
"failureRate": 0.9021,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.0915,
"total": 142,
"successCount": 14,
"successRate": 0.0979,
"total": 143,
"unresolvedFailureCount": 60
},
"Cambricon_mlu-370-x4": {
@@ -3103,22 +3103,22 @@
"decisionSuccessRate": 0.3235,
"decisionTotal": 34,
"failureBreakdown": {
"ambiguous_runtime": 50,
"ambiguous_runtime": 51,
"framework_architecture_unsupported": 20,
"memory_capacity": 1,
"tokenizer_compatibility": 2,
"参数/模板问题": 18,
"验证失败": 22
},
"failureCount": 113,
"failureRate": 0.9113,
"failureCount": 114,
"failureRate": 0.912,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 11,
"successRate": 0.0887,
"total": 124,
"unresolvedFailureCount": 90
"successRate": 0.088,
"total": 125,
"unresolvedFailureCount": 91
},
"Iluvatar_bi-100": {
"attributableFailureCount": 0,
@@ -3212,9 +3212,9 @@
},
"MetaX_c-500": {
"attributableFailureCount": 63,
"decisionFailureRate": 0.6923,
"decisionSuccessRate": 0.3077,
"decisionTotal": 91,
"decisionFailureRate": 0.6848,
"decisionSuccessRate": 0.3152,
"decisionTotal": 92,
"failureBreakdown": {
"ambiguous_runtime": 11,
"backend_operator": 30,
@@ -3226,13 +3226,13 @@
"验证失败": 48
},
"failureCount": 141,
"failureRate": 0.8343,
"failureRate": 0.8294,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 28,
"successRate": 0.1657,
"total": 169,
"successCount": 29,
"successRate": 0.1706,
"total": 170,
"unresolvedFailureCount": 78
},
"Mthreads_s4000": {
@@ -3951,25 +3951,25 @@
},
"Biren_166m|vllm|text-generation|llama|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 0.3333,
"decisionSuccessRate": 0.6667,
"decisionTotal": 3,
"decisionFailureRate": 0.25,
"decisionSuccessRate": 0.75,
"decisionTotal": 4,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 0.3333,
"failureRate": 0.25,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successRate": 0.6667,
"successCount": 3,
"successRate": 0.75,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|muse_glimmer|none": {
@@ -4572,9 +4572,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 5
"ambiguous_runtime": 6
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "llama",
@@ -4586,8 +4586,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 5,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0,
@@ -6546,25 +6546,25 @@
},
"MetaX_c-500|vllm|text-generation|llama|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 0.3333,
"decisionSuccessRate": 0.6667,
"decisionTotal": 3,
"decisionFailureRate": 0.25,
"decisionSuccessRate": 0.75,
"decisionTotal": 4,
"failureBreakdown": {
"model_load": 1
},
"failureCount": 1,
"failureRate": 0.3333,
"failureRate": 0.25,
"framework": "vllm",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successRate": 0.6667,
"successCount": 3,
"successRate": 0.75,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors": {
@@ -9531,7 +9531,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -9542,11 +9542,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successCount": 3,
"successRate": 1.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Biren_166m|vllm|text-generation|muse_glimmer|none|34": {
@@ -10385,6 +10385,30 @@
"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,
@@ -13709,7 +13733,7 @@
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
@@ -13720,11 +13744,11 @@
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 2,
"successCount": 3,
"successRate": 1.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors|32": {
@@ -15614,15 +15638,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 2326,
"totalRecords": 2429,
"terminalRecords": 2329,
"totalRecords": 2432,
"totals": {
"attributableFailureCount": 762,
"decisionFailureRate": 0.8238,
"decisionSuccessRate": 0.1762,
"decisionTotal": 925,
"decisionFailureRate": 0.822,
"decisionSuccessRate": 0.178,
"decisionTotal": 927,
"failureBreakdown": {
"ambiguous_runtime": 584,
"ambiguous_runtime": 585,
"backend_operator": 55,
"framework_architecture_unsupported": 512,
"memory_capacity": 12,
@@ -15634,18 +15658,18 @@
"参数/模板问题": 133,
"验证失败": 673
},
"failureCount": 2163,
"failureRate": 0.9299,
"failureCount": 2164,
"failureRate": 0.9292,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 11,
"successCount": 163,
"successRate": 0.0701,
"total": 2326,
"unresolvedFailureCount": 1390
"successCount": 165,
"successRate": 0.0708,
"total": 2329,
"unresolvedFailureCount": 1391
},
"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。",
@@ -15656,7 +15680,7 @@
"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。",
@@ -15681,6 +15705,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 2429,
"summarizedRecords": 2432,
"version": 1
}