state: generation 5193 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T13:47:00.396636+00:00",
|
||||
"lastSyncTime": "2026-09-10T13:47:00.004718+00:00",
|
||||
"generatedAt": "2026-09-10T13:55:41.106863+00:00",
|
||||
"lastSyncTime": "2026-09-10T13:55:40.785159+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1492,30 +1492,30 @@
|
||||
"unresolvedFailureCount": 31
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 25,
|
||||
"decisionFailureRate": 0.9615,
|
||||
"decisionSuccessRate": 0.0385,
|
||||
"decisionTotal": 26,
|
||||
"attributableFailureCount": 26,
|
||||
"decisionFailureRate": 0.963,
|
||||
"decisionSuccessRate": 0.037,
|
||||
"decisionTotal": 27,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 26,
|
||||
"backend_operator": 3,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 2,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 78,
|
||||
"failureRate": 0.9873,
|
||||
"failureCount": 79,
|
||||
"failureRate": 0.9875,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0127,
|
||||
"successRate": 0.0125,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 79,
|
||||
"total": 80,
|
||||
"unresolvedFailureCount": 53
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
@@ -1905,29 +1905,29 @@
|
||||
"unresolvedFailureCount": 56
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 43,
|
||||
"decisionFailureRate": 0.9773,
|
||||
"decisionSuccessRate": 0.0227,
|
||||
"decisionTotal": 44,
|
||||
"attributableFailureCount": 44,
|
||||
"decisionFailureRate": 0.9778,
|
||||
"decisionSuccessRate": 0.0222,
|
||||
"decisionTotal": 45,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 24,
|
||||
"backend_operator": 25,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 4,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 59,
|
||||
"failureRate": 0.9833,
|
||||
"failureCount": 60,
|
||||
"failureRate": 0.9836,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0167,
|
||||
"successRate": 0.0164,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 60,
|
||||
"total": 61,
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Mthreads_s4000|llamacpp|text-generation": {
|
||||
@@ -2291,13 +2291,13 @@
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 125,
|
||||
"decisionFailureRate": 0.7225,
|
||||
"decisionSuccessRate": 0.2775,
|
||||
"decisionTotal": 173,
|
||||
"attributableFailureCount": 126,
|
||||
"decisionFailureRate": 0.7241,
|
||||
"decisionSuccessRate": 0.2759,
|
||||
"decisionTotal": 174,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 117,
|
||||
"backend_operator": 3,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 88,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 26,
|
||||
@@ -2305,24 +2305,24 @@
|
||||
"参数/模板问题": 56,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 971,
|
||||
"failureCount": 972,
|
||||
"failureRate": 0.9529,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 48,
|
||||
"successRate": 0.0471,
|
||||
"total": 1019,
|
||||
"total": 1020,
|
||||
"unresolvedFailureCount": 846
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 237,
|
||||
"attributableFailureCount": 238,
|
||||
"decisionFailureRate": 0.9958,
|
||||
"decisionSuccessRate": 0.0042,
|
||||
"decisionTotal": 238,
|
||||
"decisionTotal": 239,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 172,
|
||||
"backend_operator": 30,
|
||||
"backend_operator": 31,
|
||||
"framework_architecture_unsupported": 169,
|
||||
"memory_capacity": 6,
|
||||
"model_load": 18,
|
||||
@@ -2332,14 +2332,14 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 434,
|
||||
"failureCount": 435,
|
||||
"failureRate": 0.9977,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0023,
|
||||
"total": 435,
|
||||
"total": 436,
|
||||
"unresolvedFailureCount": 196
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2443,7 +2443,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T13:47:00.392689+00:00",
|
||||
"generatedAt": "2026-09-10T13:55:41.102757+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2494,27 +2494,27 @@
|
||||
"unresolvedFailureCount": 218
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 26,
|
||||
"decisionFailureRate": 0.963,
|
||||
"decisionSuccessRate": 0.037,
|
||||
"decisionTotal": 27,
|
||||
"attributableFailureCount": 27,
|
||||
"decisionFailureRate": 0.9643,
|
||||
"decisionSuccessRate": 0.0357,
|
||||
"decisionTotal": 28,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 26,
|
||||
"backend_operator": 3,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 79,
|
||||
"failureRate": 0.9875,
|
||||
"failureCount": 80,
|
||||
"failureRate": 0.9877,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0125,
|
||||
"total": 80,
|
||||
"successRate": 0.0123,
|
||||
"total": 81,
|
||||
"unresolvedFailureCount": 53
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -2650,27 +2650,27 @@
|
||||
"unresolvedFailureCount": 86
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 43,
|
||||
"decisionFailureRate": 0.8113,
|
||||
"decisionSuccessRate": 0.1887,
|
||||
"decisionTotal": 53,
|
||||
"attributableFailureCount": 44,
|
||||
"decisionFailureRate": 0.8148,
|
||||
"decisionSuccessRate": 0.1852,
|
||||
"decisionTotal": 54,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 24,
|
||||
"backend_operator": 25,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 4,
|
||||
"参数/模板问题": 17,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 115,
|
||||
"failureRate": 0.92,
|
||||
"failureCount": 116,
|
||||
"failureRate": 0.9206,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 10,
|
||||
"successRate": 0.08,
|
||||
"total": 125,
|
||||
"successRate": 0.0794,
|
||||
"total": 126,
|
||||
"unresolvedFailureCount": 72
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -3729,14 +3729,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 6,
|
||||
"attributableFailureCount": 7,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 6,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 6
|
||||
"backend_operator": 7
|
||||
},
|
||||
"failureCount": 6,
|
||||
"failureCount": 7,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "starcoder2",
|
||||
@@ -3748,7 +3748,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": {
|
||||
@@ -4084,31 +4084,31 @@
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 6,
|
||||
"consecutiveFailures": 5,
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 6,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.8571,
|
||||
"decisionSuccessRate": 0.1429,
|
||||
"decisionTotal": 7,
|
||||
"decisionFailureRate": 0.875,
|
||||
"decisionSuccessRate": 0.125,
|
||||
"decisionTotal": 8,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 10,
|
||||
"backend_operator": 3,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureRate": 0.9412,
|
||||
"failureCount": 17,
|
||||
"failureRate": 0.9444,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T11:57:54.623286+00:00",
|
||||
"lastTerminalAt": "2026-09-10T13:55:40.785120+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0588,
|
||||
"successRate": 0.0556,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 17,
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -6715,14 +6715,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|31": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
"backend_operator": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 31,
|
||||
@@ -6735,7 +6735,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|32": {
|
||||
@@ -7099,16 +7099,16 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1592,
|
||||
"totalRecords": 1679,
|
||||
"terminalRecords": 1594,
|
||||
"totalRecords": 1681,
|
||||
"totals": {
|
||||
"attributableFailureCount": 416,
|
||||
"decisionFailureRate": 0.8908,
|
||||
"decisionSuccessRate": 0.1092,
|
||||
"decisionTotal": 467,
|
||||
"attributableFailureCount": 418,
|
||||
"decisionFailureRate": 0.8913,
|
||||
"decisionSuccessRate": 0.1087,
|
||||
"decisionTotal": 469,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 351,
|
||||
"backend_operator": 36,
|
||||
"backend_operator": 38,
|
||||
"framework_architecture_unsupported": 272,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 48,
|
||||
@@ -7119,21 +7119,21 @@
|
||||
"参数/模板问题": 98,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1541,
|
||||
"failureCount": 1543,
|
||||
"failureRate": 0.968,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 51,
|
||||
"successRate": 0.032,
|
||||
"total": 1592,
|
||||
"total": 1594,
|
||||
"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。",
|
||||
@@ -7141,7 +7141,7 @@
|
||||
"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。",
|
||||
@@ -7162,6 +7162,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1679,
|
||||
"summarizedRecords": 1681,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user