state: generation 5696 (cycle)

This commit is contained in:
2026-09-11 13:02:05 +00:00
parent 5eed681ab6
commit 3f8b103f94
9 changed files with 2632 additions and 2637 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-11T12:50:33.981130+00:00",
"lastSyncTime": "2026-09-11T12:50:33.752023+00:00",
"generatedAt": "2026-09-11T12:59:52.891244+00:00",
"lastSyncTime": "2026-09-11T12:59:52.253401+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1541,24 +1541,24 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 33,
"ambiguous_runtime": 34,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 92,
"failureRate": 0.9787,
"failureCount": 93,
"failureRate": 0.9789,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0213,
"successRate": 0.0211,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 94,
"unresolvedFailureCount": 72
"total": 95,
"unresolvedFailureCount": 73
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 7,
@@ -2295,7 +2295,7 @@
"decisionSuccessRate": 0.2609,
"decisionTotal": 184,
"failureBreakdown": {
"ambiguous_runtime": 128,
"ambiguous_runtime": 129,
"backend_operator": 4,
"framework_architecture_unsupported": 89,
"memory_capacity": 5,
@@ -2305,15 +2305,15 @@
"参数/模板问题": 57,
"验证失败": 673
},
"failureCount": 995,
"failureCount": 996,
"failureRate": 0.954,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.046,
"total": 1043,
"unresolvedFailureCount": 858
"total": 1044,
"unresolvedFailureCount": 859
},
"vllm": {
"attributableFailureCount": 241,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T12:50:33.976285+00:00",
"generatedAt": "2026-09-11T12:59:52.887160+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2523,21 +2523,21 @@
"decisionSuccessRate": 0.0909,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 33,
"ambiguous_runtime": 34,
"framework_architecture_unsupported": 18,
"memory_capacity": 1,
"tokenizer_compatibility": 1,
"验证失败": 39
},
"failureCount": 92,
"failureRate": 0.9787,
"failureCount": 93,
"failureRate": 0.9789,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 2,
"successRate": 0.0213,
"total": 94,
"unresolvedFailureCount": 72
"successRate": 0.0211,
"total": 95,
"unresolvedFailureCount": 73
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 17,
@@ -4133,21 +4133,20 @@
"unresolvedFailureCount": 10
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 19,
"tokenizer_compatibility": 1
"ambiguous_runtime": 20
},
"failureCount": 20,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-11T03:33:48.898214+00:00",
"lastTerminalAt": "2026-09-11T12:59:52.253401+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4156,7 +4155,7 @@
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 19
"unresolvedFailureCount": 20
},
"Cambricon_mlu-370-x8|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -6938,15 +6937,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1654,
"totalRecords": 1741,
"terminalRecords": 1655,
"totalRecords": 1742,
"totals": {
"attributableFailureCount": 434,
"decisionFailureRate": 0.8912,
"decisionSuccessRate": 0.1088,
"decisionTotal": 487,
"failureBreakdown": {
"ambiguous_runtime": 391,
"ambiguous_runtime": 392,
"backend_operator": 40,
"framework_architecture_unsupported": 273,
"memory_capacity": 11,
@@ -6958,31 +6957,30 @@
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1601,
"failureCount": 1602,
"failureRate": 0.968,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.032,
"total": 1654,
"unresolvedFailureCount": 1163
"total": 1655,
"unresolvedFailureCount": 1164
},
"warnings": [
"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 Iluvatar_mrv-100 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 Mthreads_s4000 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 MetaX_c-500 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 Iluvatar_bi-150 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 Cambricon_mlu-370-x8 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-b4 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 Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"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 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 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-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 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。",
@@ -6997,10 +6995,11 @@
"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 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 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 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 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。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1741,
"summarizedRecords": 1742,
"version": 1
}