state: generation 6395 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-12T21:39:57.345906+00:00",
|
||||
"lastSyncTime": "2026-09-12T21:39:57.012261+00:00",
|
||||
"generatedAt": "2026-09-12T22:34:15.755489+00:00",
|
||||
"lastSyncTime": "2026-09-12T22:34:15.509071+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1659,28 +1659,28 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
"attributableFailureCount": 20,
|
||||
"decisionFailureRate": 0.9091,
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"attributableFailureCount": 21,
|
||||
"decisionFailureRate": 0.913,
|
||||
"decisionSuccessRate": 0.087,
|
||||
"decisionTotal": 23,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 35,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"framework_architecture_unsupported": 19,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 94,
|
||||
"failureRate": 0.9792,
|
||||
"failureCount": 95,
|
||||
"failureRate": 0.9794,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0208,
|
||||
"successRate": 0.0206,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 96,
|
||||
"total": 97,
|
||||
"unresolvedFailureCount": 74
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
@@ -2437,14 +2437,14 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 148,
|
||||
"decisionFailureRate": 0.7363,
|
||||
"decisionSuccessRate": 0.2637,
|
||||
"decisionTotal": 201,
|
||||
"attributableFailureCount": 149,
|
||||
"decisionFailureRate": 0.7376,
|
||||
"decisionSuccessRate": 0.2624,
|
||||
"decisionTotal": 202,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 136,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 93,
|
||||
"framework_architecture_unsupported": 94,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 43,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2452,14 +2452,14 @@
|
||||
"参数/模板问题": 59,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1017,
|
||||
"failureCount": 1018,
|
||||
"failureRate": 0.9505,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 53,
|
||||
"successRate": 0.0495,
|
||||
"total": 1070,
|
||||
"total": 1071,
|
||||
"unresolvedFailureCount": 868
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2591,7 +2591,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T21:39:57.341679+00:00",
|
||||
"generatedAt": "2026-09-12T22:34:15.749897+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 30,
|
||||
@@ -2666,25 +2666,25 @@
|
||||
"unresolvedFailureCount": 54
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"attributableFailureCount": 20,
|
||||
"decisionFailureRate": 0.9091,
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"attributableFailureCount": 21,
|
||||
"decisionFailureRate": 0.913,
|
||||
"decisionSuccessRate": 0.087,
|
||||
"decisionTotal": 23,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 35,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"framework_architecture_unsupported": 19,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 94,
|
||||
"failureRate": 0.9792,
|
||||
"failureCount": 95,
|
||||
"failureRate": 0.9794,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0208,
|
||||
"total": 96,
|
||||
"successRate": 0.0206,
|
||||
"total": 97,
|
||||
"unresolvedFailureCount": 74
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
@@ -4471,20 +4471,21 @@
|
||||
"unresolvedFailureCount": 9
|
||||
},
|
||||
"Cambricon_mlu-370-x4|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": 20
|
||||
"ambiguous_runtime": 19,
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 20,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-12T20:49:10.452723+00:00",
|
||||
"lastTerminalAt": "2026-09-12T22:34:15.509071+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4493,7 +4494,7 @@
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 20
|
||||
"unresolvedFailureCount": 19
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4660,9 +4661,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 5
|
||||
"ambiguous_runtime": 4
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 4,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -4674,8 +4675,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 5
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 6,
|
||||
@@ -4948,9 +4949,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastTerminalAt": "2026-09-09T13:57:00.114030+00:00",
|
||||
@@ -4963,8 +4964,8 @@
|
||||
"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|qwen3_5|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -7271,17 +7272,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1740,
|
||||
"totalRecords": 1827,
|
||||
"terminalRecords": 1741,
|
||||
"totalRecords": 1828,
|
||||
"totals": {
|
||||
"attributableFailureCount": 496,
|
||||
"decisionFailureRate": 0.8953,
|
||||
"decisionSuccessRate": 0.1047,
|
||||
"decisionTotal": 554,
|
||||
"attributableFailureCount": 497,
|
||||
"decisionFailureRate": 0.8955,
|
||||
"decisionSuccessRate": 0.1045,
|
||||
"decisionTotal": 555,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 408,
|
||||
"backend_operator": 42,
|
||||
"framework_architecture_unsupported": 308,
|
||||
"framework_architecture_unsupported": 309,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 73,
|
||||
"platform_infrastructure": 4,
|
||||
@@ -7291,20 +7292,21 @@
|
||||
"参数/模板问题": 101,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1682,
|
||||
"failureCount": 1683,
|
||||
"failureRate": 0.9667,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 58,
|
||||
"successRate": 0.0333,
|
||||
"total": 1740,
|
||||
"total": 1741,
|
||||
"unresolvedFailureCount": 1182
|
||||
},
|
||||
"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。",
|
||||
@@ -7313,7 +7315,6 @@
|
||||
"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。",
|
||||
@@ -7336,6 +7337,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1827,
|
||||
"summarizedRecords": 1828,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user