state: generation 6268 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-12T15:08:42.536162+00:00",
|
||||
"lastSyncTime": "2026-09-12T15:08:42.332272+00:00",
|
||||
"generatedAt": "2026-09-12T16:02:54.973981+00:00",
|
||||
"lastSyncTime": "2026-09-12T16:02:54.728775+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1638,29 +1638,29 @@
|
||||
"unresolvedFailureCount": 73
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
"decisionFailureRate": 0.7778,
|
||||
"decisionSuccessRate": 0.2222,
|
||||
"decisionTotal": 9,
|
||||
"attributableFailureCount": 8,
|
||||
"decisionFailureRate": 0.8,
|
||||
"decisionSuccessRate": 0.2,
|
||||
"decisionTotal": 10,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 20,
|
||||
"framework_architecture_unsupported": 5,
|
||||
"framework_architecture_unsupported": 6,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 5,
|
||||
"验证失败": 22
|
||||
},
|
||||
"failureCount": 54,
|
||||
"failureRate": 0.9643,
|
||||
"failureCount": 55,
|
||||
"failureRate": 0.9649,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0357,
|
||||
"successRate": 0.0351,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 56,
|
||||
"total": 57,
|
||||
"unresolvedFailureCount": 47
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
|
||||
@@ -2391,14 +2391,14 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 146,
|
||||
"decisionFailureRate": 0.7374,
|
||||
"decisionSuccessRate": 0.2626,
|
||||
"decisionTotal": 198,
|
||||
"attributableFailureCount": 147,
|
||||
"decisionFailureRate": 0.7387,
|
||||
"decisionSuccessRate": 0.2613,
|
||||
"decisionTotal": 199,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 134,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 92,
|
||||
"framework_architecture_unsupported": 93,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 42,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2406,14 +2406,14 @@
|
||||
"参数/模板问题": 59,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1013,
|
||||
"failureCount": 1014,
|
||||
"failureRate": 0.9512,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 52,
|
||||
"successRate": 0.0488,
|
||||
"total": 1065,
|
||||
"total": 1066,
|
||||
"unresolvedFailureCount": 866
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2545,7 +2545,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T15:08:42.531573+00:00",
|
||||
"generatedAt": "2026-09-12T16:02:54.969122+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 28,
|
||||
@@ -2642,26 +2642,26 @@
|
||||
"unresolvedFailureCount": 73
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 17,
|
||||
"decisionFailureRate": 0.8947,
|
||||
"decisionSuccessRate": 0.1053,
|
||||
"decisionTotal": 19,
|
||||
"attributableFailureCount": 18,
|
||||
"decisionFailureRate": 0.9,
|
||||
"decisionSuccessRate": 0.1,
|
||||
"decisionTotal": 20,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 39,
|
||||
"framework_architecture_unsupported": 15,
|
||||
"framework_architecture_unsupported": 16,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 18,
|
||||
"验证失败": 22
|
||||
},
|
||||
"failureCount": 96,
|
||||
"failureRate": 0.9796,
|
||||
"failureCount": 97,
|
||||
"failureRate": 0.9798,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0204,
|
||||
"total": 98,
|
||||
"successRate": 0.0202,
|
||||
"total": 99,
|
||||
"unresolvedFailureCount": 79
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
@@ -4404,20 +4404,21 @@
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 15
|
||||
"ambiguous_runtime": 15,
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureCount": 16,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-12T08:02:48.507658+00:00",
|
||||
"lastTerminalAt": "2026-09-12T16:02:54.728775+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4425,7 +4426,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation",
|
||||
"total": 15,
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 15
|
||||
},
|
||||
"Iluvatar_bi-100|transformers|text-generation": {
|
||||
@@ -4567,9 +4568,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 18
|
||||
"ambiguous_runtime": 17
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureCount": 17,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4581,8 +4582,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 18
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 17
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 5,
|
||||
@@ -4880,9 +4881,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-09-09T11:33:22.442275+00:00",
|
||||
@@ -4895,8 +4896,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -7280,17 +7281,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1725,
|
||||
"totalRecords": 1812,
|
||||
"terminalRecords": 1726,
|
||||
"totalRecords": 1813,
|
||||
"totals": {
|
||||
"attributableFailureCount": 485,
|
||||
"decisionFailureRate": 0.8948,
|
||||
"decisionSuccessRate": 0.1052,
|
||||
"decisionTotal": 542,
|
||||
"attributableFailureCount": 486,
|
||||
"decisionFailureRate": 0.895,
|
||||
"decisionSuccessRate": 0.105,
|
||||
"decisionTotal": 543,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 405,
|
||||
"backend_operator": 42,
|
||||
"framework_architecture_unsupported": 298,
|
||||
"framework_architecture_unsupported": 299,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 72,
|
||||
"platform_infrastructure": 4,
|
||||
@@ -7300,21 +7301,20 @@
|
||||
"参数/模板问题": 101,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1668,
|
||||
"failureCount": 1669,
|
||||
"failureRate": 0.967,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 57,
|
||||
"successRate": 0.033,
|
||||
"total": 1725,
|
||||
"total": 1726,
|
||||
"unresolvedFailureCount": 1179
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 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 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 Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -7323,6 +7323,7 @@
|
||||
"GPU MetaX_c-500 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 Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"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。",
|
||||
"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 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -7344,6 +7345,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1812,
|
||||
"summarizedRecords": 1813,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user