state: generation 5164 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T12:32:30.185165+00:00",
|
||||
"lastSyncTime": "2026-09-10T12:32:29.847014+00:00",
|
||||
"generatedAt": "2026-09-10T12:40:43.152635+00:00",
|
||||
"lastSyncTime": "2026-09-10T12:40:42.405633+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1793,29 +1793,29 @@
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 71,
|
||||
"decisionFailureRate": 0.8765,
|
||||
"decisionSuccessRate": 0.1235,
|
||||
"decisionTotal": 81,
|
||||
"attributableFailureCount": 72,
|
||||
"decisionFailureRate": 0.878,
|
||||
"decisionSuccessRate": 0.122,
|
||||
"decisionTotal": 82,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 47,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 23,
|
||||
"model_load": 24,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 137,
|
||||
"failureRate": 0.932,
|
||||
"failureCount": 138,
|
||||
"failureRate": 0.9324,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 10,
|
||||
"successRate": 0.068,
|
||||
"successRate": 0.0676,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 147,
|
||||
"total": 148,
|
||||
"unresolvedFailureCount": 66
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
@@ -2293,28 +2293,28 @@
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 124,
|
||||
"decisionFailureRate": 0.7209,
|
||||
"decisionSuccessRate": 0.2791,
|
||||
"decisionTotal": 172,
|
||||
"attributableFailureCount": 125,
|
||||
"decisionFailureRate": 0.7225,
|
||||
"decisionSuccessRate": 0.2775,
|
||||
"decisionTotal": 173,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 115,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 88,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 25,
|
||||
"model_load": 26,
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 968,
|
||||
"failureCount": 969,
|
||||
"failureRate": 0.9528,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0472,
|
||||
"total": 1016,
|
||||
"total": 1017,
|
||||
"unresolvedFailureCount": 844
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2445,7 +2445,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T12:32:30.179883+00:00",
|
||||
"generatedAt": "2026-09-10T12:40:43.148795+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2608,26 +2608,26 @@
|
||||
"unresolvedFailureCount": 43
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 71,
|
||||
"decisionFailureRate": 0.8765,
|
||||
"decisionSuccessRate": 0.1235,
|
||||
"decisionTotal": 81,
|
||||
"attributableFailureCount": 72,
|
||||
"decisionFailureRate": 0.878,
|
||||
"decisionSuccessRate": 0.122,
|
||||
"decisionTotal": 82,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 47,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 23,
|
||||
"model_load": 24,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 137,
|
||||
"failureRate": 0.932,
|
||||
"failureCount": 138,
|
||||
"failureRate": 0.9324,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 10,
|
||||
"successRate": 0.068,
|
||||
"total": 147,
|
||||
"successRate": 0.0676,
|
||||
"total": 148,
|
||||
"unresolvedFailureCount": 66
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
@@ -4125,11 +4125,11 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 15,
|
||||
"ambiguous_runtime": 14,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 17,
|
||||
"failureCount": 16,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4141,8 +4141,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 15
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 14
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
@@ -4251,7 +4251,7 @@
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 16,
|
||||
"consecutiveFailures": 4,
|
||||
"consecutiveFailures": 5,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.8421,
|
||||
"decisionSuccessRate": 0.1579,
|
||||
@@ -4265,7 +4265,7 @@
|
||||
"failureRate": 0.85,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T12:15:14.346623+00:00",
|
||||
"lastTerminalAt": "2026-09-10T12:40:42.405633+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -7031,19 +7031,19 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1584,
|
||||
"totalRecords": 1671,
|
||||
"terminalRecords": 1585,
|
||||
"totalRecords": 1672,
|
||||
"totals": {
|
||||
"attributableFailureCount": 414,
|
||||
"decisionFailureRate": 0.8903,
|
||||
"decisionSuccessRate": 0.1097,
|
||||
"decisionTotal": 465,
|
||||
"attributableFailureCount": 415,
|
||||
"decisionFailureRate": 0.8906,
|
||||
"decisionSuccessRate": 0.1094,
|
||||
"decisionTotal": 466,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 345,
|
||||
"backend_operator": 35,
|
||||
"framework_architecture_unsupported": 272,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 47,
|
||||
"model_load": 48,
|
||||
"platform_infrastructure": 3,
|
||||
"repository_structure": 5,
|
||||
"runtime_memory": 6,
|
||||
@@ -7051,21 +7051,21 @@
|
||||
"参数/模板问题": 98,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1533,
|
||||
"failureCount": 1534,
|
||||
"failureRate": 0.9678,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 51,
|
||||
"successRate": 0.0322,
|
||||
"total": 1584,
|
||||
"total": 1585,
|
||||
"unresolvedFailureCount": 1116
|
||||
},
|
||||
"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 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。",
|
||||
"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。",
|
||||
@@ -7073,7 +7073,7 @@
|
||||
"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 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_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。",
|
||||
@@ -7094,6 +7094,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1671,
|
||||
"summarizedRecords": 1672,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user