state: generation 5592 (cycle)

This commit is contained in:
2026-09-11 07:45:05 +00:00
parent 13a3966b99
commit 9165b532d9
9 changed files with 2126 additions and 2100 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-11T07:33:47.456861+00:00",
"lastSyncTime": "2026-09-11T07:33:47.206168+00:00",
"generatedAt": "2026-09-11T07:43:04.447309+00:00",
"lastSyncTime": "2026-09-11T07:43:04.407471+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2185,9 +2185,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1,
"验证失败": 27
},
"failureCount": 27,
"failureCount": 28,
"failureRate": 1.0,
"framework": "unknown",
"pendingCount": 0,
@@ -2197,8 +2198,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 27,
"unresolvedFailureCount": 27
"total": 28,
"unresolvedFailureCount": 28
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 3,
@@ -2300,18 +2301,18 @@
"model_load": 34,
"platform_infrastructure": 1,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"参数/模板问题": 57,
"验证失败": 673
},
"failureCount": 993,
"failureCount": 994,
"failureRate": 0.9539,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 48,
"successRate": 0.0461,
"total": 1041,
"unresolvedFailureCount": 857
"total": 1042,
"unresolvedFailureCount": 858
},
"vllm": {
"attributableFailureCount": 240,
@@ -2441,7 +2442,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T07:33:47.451941+00:00",
"generatedAt": "2026-09-11T07:43:04.442818+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2756,18 +2757,18 @@
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 2,
"参数/模板问题": 8,
"参数/模板问题": 9,
"验证失败": 27
},
"failureCount": 92,
"failureCount": 93,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 92,
"unresolvedFailureCount": 53
"total": 93,
"unresolvedFailureCount": 54
}
},
"observedGpuMemoryGiB": {
@@ -4517,6 +4518,31 @@
"total": 20,
"unresolvedFailureCount": 20
},
"hygon_k100-ai|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"参数/模板问题": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-11T07:43:04.407471+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
@@ -6910,8 +6936,8 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1649,
"totalRecords": 1736,
"terminalRecords": 1650,
"totalRecords": 1737,
"totals": {
"attributableFailureCount": 430,
"decisionFailureRate": 0.8903,
@@ -6927,34 +6953,33 @@
"repository_structure": 5,
"runtime_memory": 6,
"tokenizer_compatibility": 39,
"参数/模板问题": 98,
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1596,
"failureCount": 1597,
"failureRate": 0.9679,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 53,
"successRate": 0.0321,
"total": 1649,
"unresolvedFailureCount": 1162
"total": 1650,
"unresolvedFailureCount": 1163
},
"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。",
@@ -6969,10 +6994,11 @@
"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": 1736,
"summarizedRecords": 1737,
"version": 1
}