state: generation 8224 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-16T14:03:39.987499+00:00",
|
||||
"lastSyncTime": "2026-09-16T14:03:38.007248+00:00",
|
||||
"generatedAt": "2026-09-16T14:13:02.349916+00:00",
|
||||
"lastSyncTime": "2026-09-16T14:13:00.205420+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1948,29 +1948,29 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
"attributableFailureCount": 28,
|
||||
"decisionFailureRate": 0.875,
|
||||
"decisionSuccessRate": 0.125,
|
||||
"decisionTotal": 32,
|
||||
"attributableFailureCount": 29,
|
||||
"decisionFailureRate": 0.8788,
|
||||
"decisionSuccessRate": 0.1212,
|
||||
"decisionTotal": 33,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 38,
|
||||
"framework_architecture_unsupported": 25,
|
||||
"framework_architecture_unsupported": 26,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 2,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 106,
|
||||
"failureRate": 0.9636,
|
||||
"failureCount": 107,
|
||||
"failureRate": 0.964,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 4,
|
||||
"successRate": 0.0364,
|
||||
"successRate": 0.036,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 110,
|
||||
"total": 111,
|
||||
"unresolvedFailureCount": 78
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
|
||||
@@ -2758,14 +2758,14 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 181,
|
||||
"decisionFailureRate": 0.7479,
|
||||
"decisionSuccessRate": 0.2521,
|
||||
"decisionTotal": 242,
|
||||
"attributableFailureCount": 182,
|
||||
"decisionFailureRate": 0.749,
|
||||
"decisionSuccessRate": 0.251,
|
||||
"decisionTotal": 243,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 157,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 121,
|
||||
"framework_architecture_unsupported": 122,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 46,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2773,14 +2773,14 @@
|
||||
"参数/模板问题": 66,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1078,
|
||||
"failureRate": 0.9464,
|
||||
"failureCount": 1079,
|
||||
"failureRate": 0.9465,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 61,
|
||||
"successRate": 0.0536,
|
||||
"total": 1139,
|
||||
"successRate": 0.0535,
|
||||
"total": 1140,
|
||||
"unresolvedFailureCount": 896
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2918,7 +2918,7 @@
|
||||
"unresolvedFailureCount": 5
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-16T14:03:39.980991+00:00",
|
||||
"generatedAt": "2026-09-16T14:13:02.343645+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 49,
|
||||
@@ -2994,26 +2994,26 @@
|
||||
"unresolvedFailureCount": 59
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"attributableFailureCount": 28,
|
||||
"decisionFailureRate": 0.875,
|
||||
"decisionSuccessRate": 0.125,
|
||||
"decisionTotal": 32,
|
||||
"attributableFailureCount": 29,
|
||||
"decisionFailureRate": 0.8788,
|
||||
"decisionSuccessRate": 0.1212,
|
||||
"decisionTotal": 33,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 41,
|
||||
"framework_architecture_unsupported": 25,
|
||||
"framework_architecture_unsupported": 26,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 2,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 109,
|
||||
"failureRate": 0.9646,
|
||||
"failureCount": 110,
|
||||
"failureRate": 0.9649,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 4,
|
||||
"successRate": 0.0354,
|
||||
"total": 113,
|
||||
"successRate": 0.0351,
|
||||
"total": 114,
|
||||
"unresolvedFailureCount": 81
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
@@ -6253,15 +6253,15 @@
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 1,
|
||||
"attributableFailureCount": 9,
|
||||
"consecutiveFailures": 2,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.8,
|
||||
"decisionSuccessRate": 0.2,
|
||||
"decisionTotal": 10,
|
||||
"decisionFailureRate": 0.8182,
|
||||
"decisionSuccessRate": 0.1818,
|
||||
"decisionTotal": 11,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 9,
|
||||
"framework_architecture_unsupported": 7,
|
||||
"ambiguous_runtime": 8,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
@@ -6269,7 +6269,7 @@
|
||||
"failureRate": 0.9,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-16T00:58:27.147335+00:00",
|
||||
"lastTerminalAt": "2026-09-16T14:13:00.205420+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -6278,7 +6278,7 @@
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 10
|
||||
"unresolvedFailureCount": 9
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -10896,17 +10896,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 2018,
|
||||
"totalRecords": 2112,
|
||||
"terminalRecords": 2019,
|
||||
"totalRecords": 2113,
|
||||
"totals": {
|
||||
"attributableFailureCount": 648,
|
||||
"decisionFailureRate": 0.8913,
|
||||
"decisionSuccessRate": 0.1087,
|
||||
"decisionTotal": 727,
|
||||
"attributableFailureCount": 649,
|
||||
"decisionFailureRate": 0.8915,
|
||||
"decisionSuccessRate": 0.1085,
|
||||
"decisionTotal": 728,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 491,
|
||||
"backend_operator": 45,
|
||||
"framework_architecture_unsupported": 424,
|
||||
"framework_architecture_unsupported": 425,
|
||||
"memory_capacity": 12,
|
||||
"model_load": 84,
|
||||
"platform_infrastructure": 10,
|
||||
@@ -10916,14 +10916,14 @@
|
||||
"参数/模板问题": 117,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1939,
|
||||
"failureCount": 1940,
|
||||
"failureRate": 0.9609,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 10,
|
||||
"successCount": 79,
|
||||
"successRate": 0.0391,
|
||||
"total": 2018,
|
||||
"total": 2019,
|
||||
"unresolvedFailureCount": 1281
|
||||
},
|
||||
"warnings": [
|
||||
@@ -10931,14 +10931,14 @@
|
||||
"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 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 Biren_166m 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 hygon_k100-ai 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 Cambricon_mlu-370-x4 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 Cambricon_mlu-370-x8 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。",
|
||||
"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。",
|
||||
"组合 Biren_166m|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_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -10963,6 +10963,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 2112,
|
||||
"summarizedRecords": 2113,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user