state: generation 4806 (cycle)

This commit is contained in:
2026-09-09 22:08:17 +00:00
parent dbf40b8e74
commit c9830d896c
9 changed files with 2312 additions and 2314 deletions

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-09T21:47:28.483336+00:00",
"lastSyncTime": "2026-09-09T21:47:28.214740+00:00",
"generatedAt": "2026-09-09T22:06:26.542677+00:00",
"lastSyncTime": "2026-09-09T22:06:26.296264+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -2230,14 +2230,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 35,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 27,
"memory_capacity": 1,
"model_load": 3,
"repository_structure": 3,
"runtime_memory": 1
},
"failureCount": 41,
"failureCount": 42,
"failureRate": 1.0,
"framework": "vllm",
"pendingCount": 0,
@@ -2247,8 +2247,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 41,
"unresolvedFailureCount": 6
"total": 42,
"unresolvedFailureCount": 7
}
},
"frameworkSummaries": {
@@ -2320,7 +2320,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 223,
"failureBreakdown": {
"ambiguous_runtime": 115,
"ambiguous_runtime": 116,
"backend_operator": 18,
"framework_architecture_unsupported": 168,
"memory_capacity": 6,
@@ -2331,15 +2331,15 @@
"tokenizer_compatibility": 3,
"参数/模板问题": 21
},
"failureCount": 360,
"failureCount": 361,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 0,
"successRate": 0.0,
"total": 360,
"unresolvedFailureCount": 136
"total": 361,
"unresolvedFailureCount": 137
},
"vllm-mlu": {
"attributableFailureCount": 7,
@@ -2442,7 +2442,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-09T21:47:28.479448+00:00",
"generatedAt": "2026-09-09T22:06:26.538602+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2749,7 +2749,7 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 38,
"failureBreakdown": {
"ambiguous_runtime": 8,
"ambiguous_runtime": 9,
"framework_architecture_unsupported": 30,
"memory_capacity": 1,
"model_load": 3,
@@ -2758,15 +2758,15 @@
"参数/模板问题": 8,
"验证失败": 27
},
"failureCount": 81,
"failureCount": 82,
"failureRate": 1.0,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"total": 81,
"unresolvedFailureCount": 43
"total": 82,
"unresolvedFailureCount": 44
}
},
"observedGpuMemoryGiB": {
@@ -4433,18 +4433,18 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 14,
"consecutiveFailures": 14,
"attributableFailureCount": 13,
"consecutiveFailures": 13,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 14,
"decisionTotal": 13,
"failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1,
"tokenizer_compatibility": 13
"tokenizer_compatibility": 12
},
"failureCount": 15,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": "2026-09-08T18:27:21+00:00",
@@ -4456,7 +4456,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 15,
"total": 14,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -4620,16 +4620,16 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 10,
"failureBreakdown": {
"ambiguous_runtime": 6,
"ambiguous_runtime": 7,
"framework_architecture_unsupported": 8,
"model_load": 1,
"repository_structure": 1
},
"failureCount": 16,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-09T19:08:24.911910+00:00",
"lastTerminalAt": "2026-09-09T22:06:26.296264+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -4637,8 +4637,8 @@
"successRate": 0.0,
"targetGpu": "hygon_k100-ai",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 6
"total": 17,
"unresolvedFailureCount": 7
}
},
"recentProfileCombinationStats": {
@@ -6633,15 +6633,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1450,
"totalRecords": 1534,
"terminalRecords": 1451,
"totalRecords": 1535,
"totals": {
"attributableFailureCount": 386,
"decisionFailureRate": 0.8915,
"decisionSuccessRate": 0.1085,
"decisionTotal": 433,
"failureBreakdown": {
"ambiguous_runtime": 248,
"ambiguous_runtime": 249,
"backend_operator": 21,
"framework_architecture_unsupported": 266,
"memory_capacity": 11,
@@ -6653,21 +6653,21 @@
"参数/模板问题": 94,
"验证失败": 673
},
"failureCount": 1403,
"failureCount": 1404,
"failureRate": 0.9676,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 47,
"successRate": 0.0324,
"total": 1450,
"unresolvedFailureCount": 1015
"total": 1451,
"unresolvedFailureCount": 1016
},
"warnings": [
"GPU Cambricon_mlu-370-x8 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_mrv-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 Sunrise_pt-200-x1 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 MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
@@ -6675,7 +6675,7 @@
"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。",
"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 Iluvatar_bi-150 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-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 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -6695,6 +6695,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1534,
"summarizedRecords": 1535,
"version": 1
}