state: generation 11478 (cycle)

This commit is contained in:
2026-09-21 13:30:48 +00:00
parent 355ad321e1
commit 510e414c69
9 changed files with 2001 additions and 1930 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-21T13:03:44.822858+00:00",
"lastSyncTime": "2026-09-21T13:03:44.265526+00:00",
"generatedAt": "2026-09-21T13:30:37.394010+00:00",
"lastSyncTime": "2026-09-21T13:30:37.066051+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3371,11 +3371,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 17,
"failureBreakdown": {
"ambiguous_runtime": 13,
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 17,
"参数/模板问题": 11
},
"failureCount": 41,
"failureCount": 42,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -3385,8 +3385,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 41,
"unresolvedFailureCount": 24
"total": 42,
"unresolvedFailureCount": 25
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
@@ -5324,7 +5324,7 @@
"decisionSuccessRate": 0.0241,
"decisionTotal": 3615,
"failureBreakdown": {
"ambiguous_runtime": 1484,
"ambiguous_runtime": 1485,
"architecture_compatibility": 112,
"attention_backend": 1,
"backend_operator": 84,
@@ -5338,15 +5338,15 @@
"tokenizer_compatibility": 411,
"参数/模板问题": 44
},
"failureCount": 5921,
"failureCount": 5922,
"failureRate": 0.9855,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 865,
"successCount": 87,
"successRate": 0.0145,
"total": 6008,
"unresolvedFailureCount": 1528
"total": 6009,
"unresolvedFailureCount": 1529
},
"vllm-customized": {
"attributableFailureCount": 4,
@@ -5492,7 +5492,7 @@
"unresolvedFailureCount": 87
}
},
"generatedAt": "2026-09-21T13:03:44.812305+00:00",
"generatedAt": "2026-09-21T13:30:37.383788+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 94,
@@ -5613,7 +5613,7 @@
"decisionSuccessRate": 0.2333,
"decisionTotal": 60,
"failureBreakdown": {
"ambiguous_runtime": 97,
"ambiguous_runtime": 98,
"framework_architecture_unsupported": 39,
"memory_capacity": 3,
"model_load": 2,
@@ -5621,15 +5621,15 @@
"参数/模板问题": 33,
"验证失败": 22
},
"failureCount": 198,
"failureRate": 0.934,
"failureCount": 199,
"failureRate": 0.9343,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 14,
"successRate": 0.066,
"total": 212,
"unresolvedFailureCount": 152
"successRate": 0.0657,
"total": 213,
"unresolvedFailureCount": 153
},
"Iluvatar_bi-100": {
"attributableFailureCount": 194,
@@ -10047,6 +10047,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|sophia_hybrid|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -16334,15 +16357,15 @@
"unresolvedFailureCount": 6
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 7,
"consecutiveFailures": 7,
"attributableFailureCount": 6,
"consecutiveFailures": 6,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 7,
"decisionTotal": 6,
"failureBreakdown": {
"ambiguous_runtime": 12,
"framework_architecture_unsupported": 7,
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 6,
"参数/模板问题": 1
},
"failureCount": 20,
@@ -16358,7 +16381,7 @@
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 13
"unresolvedFailureCount": 14
},
"Iluvatar_bi-100|transformers|text-generation": {
"attributableFailureCount": 0,
@@ -16606,9 +16629,9 @@
"failureBreakdown": {
"backend_operator": 1,
"framework_architecture_unsupported": 1,
"参数/模板问题": 5
"参数/模板问题": 4
},
"failureCount": 7,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -16620,8 +16643,8 @@
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 5
"total": 6,
"unresolvedFailureCount": 4
},
"MetaX_c-500|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -18012,6 +18035,31 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|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",
"lastTerminalAt": "2026-09-21T13:30:37.066051+00:00",
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|fp8": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -26147,6 +26195,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm|text-generation|sophia_hybrid|none|31": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 31,
"modelType": "sophia_hybrid",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -34809,15 +34881,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16279,
"totalRecords": 16463,
"terminalRecords": 16280,
"totalRecords": 16464,
"totals": {
"attributableFailureCount": 5881,
"decisionFailureRate": 0.8617,
"decisionSuccessRate": 0.1383,
"decisionTotal": 6825,
"failureBreakdown": {
"ambiguous_runtime": 3948,
"ambiguous_runtime": 3949,
"architecture_compatibility": 212,
"attention_backend": 1,
"backend_operator": 103,
@@ -34833,31 +34905,31 @@
"日志缺失": 719,
"验证失败": 674
},
"failureCount": 15335,
"failureCount": 15336,
"failureRate": 0.942,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 925,
"successCount": 944,
"successRate": 0.058,
"total": 16279,
"unresolvedFailureCount": 8529
"total": 16280,
"unresolvedFailureCount": 8530
},
"warnings": [
"GPU Iluvatar_mrv-100 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。",
"GPU Kunlunxin_p-800 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-100 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高(≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 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 Ascend_910-b4 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 Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
"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 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 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。",
@@ -34897,6 +34969,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 16463,
"summarizedRecords": 16464,
"version": 1
}