state: generation 10711 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T15:35:52.077496+00:00",
|
||||
"lastSyncTime": "2026-09-20T15:35:51.777956+00:00",
|
||||
"generatedAt": "2026-09-20T16:12:47.839143+00:00",
|
||||
"lastSyncTime": "2026-09-20T16:12:47.264793+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -4316,16 +4316,16 @@
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 647,
|
||||
"attributableFailureCount": 648,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 647,
|
||||
"decisionTotal": 648,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 152,
|
||||
"ambiguous_runtime": 153,
|
||||
"architecture_compatibility": 30,
|
||||
"attention_backend": 1,
|
||||
"context_length": 42,
|
||||
"framework_architecture_unsupported": 220,
|
||||
"framework_architecture_unsupported": 221,
|
||||
"memory_capacity": 58,
|
||||
"model_load": 56,
|
||||
"platform_infrastructure": 3,
|
||||
@@ -4333,7 +4333,7 @@
|
||||
"runtime_memory": 52,
|
||||
"tokenizer_compatibility": 79
|
||||
},
|
||||
"failureCount": 802,
|
||||
"failureCount": 804,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -4343,8 +4343,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 802,
|
||||
"unresolvedFailureCount": 152
|
||||
"total": 804,
|
||||
"unresolvedFailureCount": 153
|
||||
},
|
||||
"hygon_k100-ai|vllm|unknown": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4467,17 +4467,17 @@
|
||||
"unresolvedFailureCount": 6405
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3476,
|
||||
"attributableFailureCount": 3477,
|
||||
"decisionFailureRate": 0.9778,
|
||||
"decisionSuccessRate": 0.0222,
|
||||
"decisionTotal": 3555,
|
||||
"decisionTotal": 3556,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1434,
|
||||
"ambiguous_runtime": 1435,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 84,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1261,
|
||||
"framework_architecture_unsupported": 1262,
|
||||
"memory_capacity": 720,
|
||||
"model_load": 199,
|
||||
"platform_infrastructure": 864,
|
||||
@@ -4486,15 +4486,15 @@
|
||||
"tokenizer_compatibility": 408,
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 5814,
|
||||
"failureCount": 5816,
|
||||
"failureRate": 0.9866,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 864,
|
||||
"successCount": 79,
|
||||
"successRate": 0.0134,
|
||||
"total": 5893,
|
||||
"unresolvedFailureCount": 1474
|
||||
"total": 5895,
|
||||
"unresolvedFailureCount": 1475
|
||||
},
|
||||
"vllm-customized": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -4627,7 +4627,7 @@
|
||||
"unresolvedFailureCount": 24
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T15:35:52.067113+00:00",
|
||||
"generatedAt": "2026-09-20T16:12:47.830442+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 75,
|
||||
@@ -5007,16 +5007,16 @@
|
||||
"unresolvedFailureCount": 1303
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"attributableFailureCount": 682,
|
||||
"attributableFailureCount": 683,
|
||||
"decisionFailureRate": 0.9579,
|
||||
"decisionSuccessRate": 0.0421,
|
||||
"decisionTotal": 712,
|
||||
"decisionTotal": 713,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 297,
|
||||
"ambiguous_runtime": 298,
|
||||
"architecture_compatibility": 32,
|
||||
"attention_backend": 1,
|
||||
"context_length": 46,
|
||||
"framework_architecture_unsupported": 235,
|
||||
"framework_architecture_unsupported": 236,
|
||||
"memory_capacity": 58,
|
||||
"model_load": 57,
|
||||
"platform_infrastructure": 4,
|
||||
@@ -5027,15 +5027,15 @@
|
||||
"日志缺失": 66,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 1452,
|
||||
"failureCount": 1454,
|
||||
"failureRate": 0.9798,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 30,
|
||||
"successRate": 0.0202,
|
||||
"total": 1482,
|
||||
"unresolvedFailureCount": 766
|
||||
"total": 1484,
|
||||
"unresolvedFailureCount": 767
|
||||
}
|
||||
},
|
||||
"observedGpuMemoryGiB": {
|
||||
@@ -11304,14 +11304,14 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 11,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4,
|
||||
"ambiguous_runtime": 3,
|
||||
"framework_architecture_unsupported": 7,
|
||||
"model_load": 1,
|
||||
"runtime_memory": 2,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureRate": 0.9375,
|
||||
"failureCount": 14,
|
||||
"failureRate": 0.9333,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T06:27:54.872472+00:00",
|
||||
@@ -11319,11 +11319,11 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0625,
|
||||
"successRate": 0.0667,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 5
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
@@ -11550,9 +11550,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12
|
||||
"ambiguous_runtime": 11
|
||||
},
|
||||
"failureCount": 12,
|
||||
"failureCount": 11,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -11564,8 +11564,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation",
|
||||
"total": 12,
|
||||
"unresolvedFailureCount": 12
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 11
|
||||
},
|
||||
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -11879,22 +11879,22 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 11,
|
||||
"consecutiveFailures": 11,
|
||||
"attributableFailureCount": 12,
|
||||
"consecutiveFailures": 12,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 11,
|
||||
"decisionTotal": 12,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"framework_architecture_unsupported": 10,
|
||||
"ambiguous_runtime": 8,
|
||||
"framework_architecture_unsupported": 11,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureCount": 20,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T12:21:49.901980+00:00",
|
||||
"lastTerminalAt": "2026-09-20T16:12:47.264764+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -11902,8 +11902,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 7
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 8
|
||||
}
|
||||
},
|
||||
"recentProfileCombinationStats": {
|
||||
@@ -22546,20 +22546,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15879,
|
||||
"totalRecords": 15984,
|
||||
"terminalRecords": 15881,
|
||||
"totalRecords": 15986,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5758,
|
||||
"decisionFailureRate": 0.8613,
|
||||
"decisionSuccessRate": 0.1387,
|
||||
"decisionTotal": 6685,
|
||||
"attributableFailureCount": 5759,
|
||||
"decisionFailureRate": 0.8614,
|
||||
"decisionSuccessRate": 0.1386,
|
||||
"decisionTotal": 6686,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3770,
|
||||
"ambiguous_runtime": 3771,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
"context_length": 318,
|
||||
"framework_architecture_unsupported": 1986,
|
||||
"framework_architecture_unsupported": 1987,
|
||||
"memory_capacity": 1195,
|
||||
"model_load": 479,
|
||||
"platform_infrastructure": 922,
|
||||
@@ -22570,15 +22570,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 14952,
|
||||
"failureCount": 14954,
|
||||
"failureRate": 0.9416,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 927,
|
||||
"successRate": 0.0584,
|
||||
"total": 15879,
|
||||
"unresolvedFailureCount": 8272
|
||||
"total": 15881,
|
||||
"unresolvedFailureCount": 8273
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -22623,12 +22623,12 @@
|
||||
"组合 Cambricon_mlu-370-x4|unknown|visual-multi-modal 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。",
|
||||
"组合 Iluvatar_bi-150|transformers|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 Cambricon_mlu-370-x8|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 Ascend_910-b3|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-b3|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 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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 15984,
|
||||
"summarizedRecords": 15986,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user