state: generation 5184 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T13:23:06.908779+00:00",
|
||||
"lastSyncTime": "2026-09-10T13:23:06.708419+00:00",
|
||||
"generatedAt": "2026-09-10T13:30:05.906084+00:00",
|
||||
"lastSyncTime": "2026-09-10T13:30:05.632388+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1545,24 +1545,24 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 22,
|
||||
"ambiguous_runtime": 23,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 81,
|
||||
"failureRate": 0.9759,
|
||||
"failureCount": 82,
|
||||
"failureRate": 0.9762,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0241,
|
||||
"successRate": 0.0238,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 83,
|
||||
"unresolvedFailureCount": 61
|
||||
"total": 84,
|
||||
"unresolvedFailureCount": 62
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2296,7 +2296,7 @@
|
||||
"decisionSuccessRate": 0.2775,
|
||||
"decisionTotal": 173,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 116,
|
||||
"ambiguous_runtime": 117,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 88,
|
||||
"memory_capacity": 5,
|
||||
@@ -2305,15 +2305,15 @@
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 970,
|
||||
"failureRate": 0.9528,
|
||||
"failureCount": 971,
|
||||
"failureRate": 0.9529,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0472,
|
||||
"total": 1018,
|
||||
"unresolvedFailureCount": 845
|
||||
"successRate": 0.0471,
|
||||
"total": 1019,
|
||||
"unresolvedFailureCount": 846
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 236,
|
||||
@@ -2443,7 +2443,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T13:23:06.904847+00:00",
|
||||
"generatedAt": "2026-09-10T13:30:05.901309+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2523,21 +2523,21 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 22,
|
||||
"ambiguous_runtime": 23,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 81,
|
||||
"failureRate": 0.9759,
|
||||
"failureCount": 82,
|
||||
"failureRate": 0.9762,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0241,
|
||||
"total": 83,
|
||||
"unresolvedFailureCount": 61
|
||||
"successRate": 0.0238,
|
||||
"total": 84,
|
||||
"unresolvedFailureCount": 62
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 17,
|
||||
@@ -4096,15 +4096,15 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 9,
|
||||
"ambiguous_runtime": 10,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 11,
|
||||
"failureCount": 12,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T13:23:06.708419+00:00",
|
||||
"lastTerminalAt": "2026-09-10T13:30:05.632388+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4112,8 +4112,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 9
|
||||
"total": 12,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
@@ -4400,20 +4400,19 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation": {
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 6,
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 6,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 3,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"model_load": 1,
|
||||
"runtime_memory": 1
|
||||
},
|
||||
"failureCount": 13,
|
||||
"failureCount": 12,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4425,7 +4424,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Mthreads_s4000",
|
||||
"taskType": "text-generation",
|
||||
"total": 13,
|
||||
"total": 12,
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Sunrise_pt-200-x1|unknown|text-generation": {
|
||||
@@ -7053,15 +7052,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1590,
|
||||
"totalRecords": 1677,
|
||||
"terminalRecords": 1591,
|
||||
"totalRecords": 1678,
|
||||
"totals": {
|
||||
"attributableFailureCount": 415,
|
||||
"decisionFailureRate": 0.8906,
|
||||
"decisionSuccessRate": 0.1094,
|
||||
"decisionTotal": 466,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 350,
|
||||
"ambiguous_runtime": 351,
|
||||
"backend_operator": 35,
|
||||
"framework_architecture_unsupported": 272,
|
||||
"memory_capacity": 11,
|
||||
@@ -7073,21 +7072,21 @@
|
||||
"参数/模板问题": 98,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1539,
|
||||
"failureCount": 1540,
|
||||
"failureRate": 0.9679,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 51,
|
||||
"successRate": 0.0321,
|
||||
"total": 1590,
|
||||
"unresolvedFailureCount": 1121
|
||||
"total": 1591,
|
||||
"unresolvedFailureCount": 1122
|
||||
},
|
||||
"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。",
|
||||
@@ -7095,7 +7094,7 @@
|
||||
"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。",
|
||||
@@ -7116,6 +7115,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1677,
|
||||
"summarizedRecords": 1678,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user