state: generation 16636 (cycle)

This commit is contained in:
2026-09-26 15:19:31 +00:00
parent f7353d37fd
commit aadf771245
10 changed files with 1525 additions and 1528 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-26T14:43:50.469743+00:00",
"lastSyncTime": "2026-09-26T14:43:50.048411+00:00",
"generatedAt": "2026-09-26T15:18:41.730884+00:00",
"lastSyncTime": "2026-09-26T15:18:41.474100+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3870,12 +3870,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 24,
"failureBreakdown": {
"ambiguous_runtime": 33,
"ambiguous_runtime": 34,
"framework_architecture_unsupported": 23,
"memory_capacity": 1,
"参数/模板问题": 1
},
"failureCount": 58,
"failureCount": 59,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -3885,8 +3885,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 58,
"unresolvedFailureCount": 34
"total": 59,
"unresolvedFailureCount": 35
},
"Cambricon_mlu-370-x8|unknown|feature_emb": {
"attributableFailureCount": 0,
@@ -5961,7 +5961,7 @@
"decisionSuccessRate": 0.0261,
"decisionTotal": 3717,
"failureBreakdown": {
"ambiguous_runtime": 1573,
"ambiguous_runtime": 1574,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 92,
@@ -5975,15 +5975,15 @@
"tokenizer_compatibility": 415,
"参数/模板问题": 50
},
"failureCount": 6112,
"failureCount": 6113,
"failureRate": 0.9844,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 869,
"successCount": 97,
"successRate": 0.0156,
"total": 6209,
"unresolvedFailureCount": 1623
"total": 6210,
"unresolvedFailureCount": 1624
},
"vllm-customized": {
"attributableFailureCount": 13,
@@ -6133,7 +6133,7 @@
"unresolvedFailureCount": 196
}
},
"generatedAt": "2026-09-26T14:43:50.456953+00:00",
"generatedAt": "2026-09-26T15:18:41.718675+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6225,7 +6225,7 @@
"decisionSuccessRate": 0.0894,
"decisionTotal": 817,
"failureBreakdown": {
"ambiguous_runtime": 487,
"ambiguous_runtime": 488,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 297,
@@ -6238,15 +6238,15 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1588,
"failureCount": 1589,
"failureRate": 0.9561,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 16,
"successCount": 73,
"successRate": 0.0439,
"total": 1661,
"unresolvedFailureCount": 828
"total": 1662,
"unresolvedFailureCount": 829
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 60,
@@ -11710,9 +11710,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 7
"ambiguous_runtime": 8
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "starcoder2",
@@ -11724,8 +11724,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 7,
"unresolvedFailureCount": 7
"total": 8,
"unresolvedFailureCount": 8
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|aquila3|none": {
"attributableFailureCount": 1,
@@ -22727,10 +22727,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"framework_architecture_unsupported": 1
},
"failureCount": 11,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
@@ -22742,8 +22742,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 11,
"unresolvedFailureCount": 10
"total": 12,
"unresolvedFailureCount": 11
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -23241,18 +23241,18 @@
"unresolvedFailureCount": 9
},
"hygon_k100-ai|vllm-patch-tokenizer|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": 6,
"repository_structure": 1,
"runtime_memory": 6
"runtime_memory": 5
},
"failureCount": 13,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastPlatformFailureAt": null,
@@ -23264,7 +23264,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 13,
"total": 12,
"unresolvedFailureCount": 6
},
"hygon_k100-ai|vllm|text-generation": {
@@ -23853,9 +23853,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"lastTerminalAt": "2026-09-24T05:11:42.061432+00:00",
@@ -23868,8 +23868,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
@@ -26096,16 +26096,16 @@
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 3,
"consecutiveFailures": 3,
"attributableFailureCount": 2,
"consecutiveFailures": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 2,
"runtime_memory": 3
"runtime_memory": 2
},
"failureCount": 5,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm-patch-tokenizer",
"lastTerminalAt": "2026-09-25T00:33:39.855270+00:00",
@@ -26118,7 +26118,7 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 5,
"total": 4,
"unresolvedFailureCount": 2
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|phi3small|compressed-tensors": {
@@ -34443,9 +34443,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
@@ -34458,8 +34458,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Cambricon_mlu-370-x4|vllm|text-generation|starcoder2|compressed-tensors|33": {
"attributableFailureCount": 0,
@@ -50813,15 +50813,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17037,
"totalRecords": 17258,
"terminalRecords": 17038,
"totalRecords": 17259,
"totals": {
"attributableFailureCount": 6109,
"decisionFailureRate": 0.8636,
"decisionSuccessRate": 0.1364,
"decisionTotal": 7074,
"failureBreakdown": {
"ambiguous_runtime": 4406,
"ambiguous_runtime": 4407,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 127,
@@ -50837,30 +50837,30 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16072,
"failureCount": 16073,
"failureRate": 0.9434,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 935,
"successCount": 965,
"successRate": 0.0566,
"total": 17037,
"unresolvedFailureCount": 9028
"total": 17038,
"unresolvedFailureCount": 9029
},
"warnings": [
"GPU Biren_166m 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 Iluvatar_bi-100 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 Cambricon_mlu-370-x4 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 Kunlunxin_p-800 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 Cambricon_mlu-370-x8 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 Vastai_va16 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 Cambricon_mlu-370-x8 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 Ascend_910-b3 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 Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"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|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -50873,7 +50873,6 @@
"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-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-x4|vllm-mlu|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 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 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 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -50899,10 +50898,11 @@
"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|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 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 MetaX_c-500|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17258,
"summarizedRecords": 17259,
"version": 1
}