state: generation 10613 (cycle)
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T13:59:52.323200+00:00",
|
||||
"lastSyncTime": "2026-09-20T13:59:52.266077+00:00",
|
||||
"generatedAt": "2026-09-20T14:14:39.977491+00:00",
|
||||
"lastSyncTime": "2026-09-20T14:14:39.678936+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2893,13 +2893,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 12,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"ambiguous_runtime": 3,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"memory_capacity": 4,
|
||||
"model_load": 2,
|
||||
"tokenizer_compatibility": 4
|
||||
},
|
||||
"failureCount": 14,
|
||||
"failureCount": 15,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"pendingCount": 0,
|
||||
@@ -2909,8 +2909,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 14,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Iluvatar_bi-150|unknown|asr": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -3415,25 +3415,25 @@
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation": {
|
||||
"attributableFailureCount": 14,
|
||||
"decisionFailureRate": 0.6087,
|
||||
"decisionSuccessRate": 0.3913,
|
||||
"decisionTotal": 23,
|
||||
"decisionFailureRate": 0.56,
|
||||
"decisionSuccessRate": 0.44,
|
||||
"decisionTotal": 25,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4,
|
||||
"framework_architecture_unsupported": 13,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureRate": 0.6667,
|
||||
"failureRate": 0.6207,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 9,
|
||||
"successRate": 0.3333,
|
||||
"successCount": 11,
|
||||
"successRate": 0.3793,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 27,
|
||||
"total": 29,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
@@ -4410,21 +4410,21 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 13,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 37,
|
||||
"ambiguous_runtime": 38,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"memory_capacity": 4,
|
||||
"model_load": 2,
|
||||
"tokenizer_compatibility": 4
|
||||
},
|
||||
"failureCount": 50,
|
||||
"failureCount": 51,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 50,
|
||||
"unresolvedFailureCount": 37
|
||||
"total": 51,
|
||||
"unresolvedFailureCount": 38
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 1856,
|
||||
@@ -4459,9 +4459,9 @@
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3474,
|
||||
"decisionFailureRate": 0.9789,
|
||||
"decisionSuccessRate": 0.0211,
|
||||
"decisionTotal": 3549,
|
||||
"decisionFailureRate": 0.9783,
|
||||
"decisionSuccessRate": 0.0217,
|
||||
"decisionTotal": 3551,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1429,
|
||||
"architecture_compatibility": 112,
|
||||
@@ -4478,13 +4478,13 @@
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 5807,
|
||||
"failureRate": 0.9872,
|
||||
"failureRate": 0.9869,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 864,
|
||||
"successCount": 75,
|
||||
"successRate": 0.0128,
|
||||
"total": 5882,
|
||||
"successCount": 77,
|
||||
"successRate": 0.0131,
|
||||
"total": 5884,
|
||||
"unresolvedFailureCount": 1469
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -4618,7 +4618,7 @@
|
||||
"unresolvedFailureCount": 24
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T13:59:52.315429+00:00",
|
||||
"generatedAt": "2026-09-20T14:14:39.968836+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 75,
|
||||
@@ -4785,7 +4785,7 @@
|
||||
"decisionSuccessRate": 0.1701,
|
||||
"decisionTotal": 876,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 602,
|
||||
"ambiguous_runtime": 603,
|
||||
"architecture_compatibility": 15,
|
||||
"backend_operator": 11,
|
||||
"context_length": 29,
|
||||
@@ -4800,21 +4800,21 @@
|
||||
"日志缺失": 155,
|
||||
"验证失败": 30
|
||||
},
|
||||
"failureCount": 1854,
|
||||
"failureCount": 1855,
|
||||
"failureRate": 0.9256,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 21,
|
||||
"successCount": 149,
|
||||
"successRate": 0.0744,
|
||||
"total": 2003,
|
||||
"unresolvedFailureCount": 1106
|
||||
"total": 2004,
|
||||
"unresolvedFailureCount": 1107
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 964,
|
||||
"decisionFailureRate": 0.8501,
|
||||
"decisionSuccessRate": 0.1499,
|
||||
"decisionTotal": 1134,
|
||||
"decisionFailureRate": 0.8486,
|
||||
"decisionSuccessRate": 0.1514,
|
||||
"decisionTotal": 1136,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 344,
|
||||
"architecture_compatibility": 47,
|
||||
@@ -4832,13 +4832,13 @@
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 1684,
|
||||
"failureRate": 0.9083,
|
||||
"failureRate": 0.9073,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 7,
|
||||
"successCount": 170,
|
||||
"successRate": 0.0917,
|
||||
"total": 1854,
|
||||
"successCount": 172,
|
||||
"successRate": 0.0927,
|
||||
"total": 1856,
|
||||
"unresolvedFailureCount": 713
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
@@ -7094,9 +7094,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"modelType": "mpt",
|
||||
@@ -7108,8 +7109,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|none": {
|
||||
"attributableFailureCount": 5,
|
||||
@@ -8450,23 +8451,23 @@
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 0.3333,
|
||||
"failureRate": 0.2,
|
||||
"framework": "vllm",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 2,
|
||||
"successRate": 0.6667,
|
||||
"successCount": 4,
|
||||
"successRate": 0.8,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 3,
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|muse_glimmer|none": {
|
||||
@@ -11240,13 +11241,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 12,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"ambiguous_runtime": 3,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"memory_capacity": 4,
|
||||
"model_load": 2,
|
||||
"tokenizer_compatibility": 4
|
||||
},
|
||||
"failureCount": 14,
|
||||
"failureCount": 15,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -11258,8 +11259,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 14,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation": {
|
||||
"attributableFailureCount": 9,
|
||||
@@ -11559,22 +11560,22 @@
|
||||
"decisionTotal": 9,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 3,
|
||||
"platform_infrastructure": 4,
|
||||
"platform_infrastructure": 3,
|
||||
"tokenizer_compatibility": 6
|
||||
},
|
||||
"failureCount": 13,
|
||||
"failureCount": 12,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-09-16T02:03:21+00:00",
|
||||
"lastTerminalAt": "2026-09-19T23:13:47.695526+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 13,
|
||||
"total": 12,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -11967,12 +11968,13 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"lastTerminalAt": "2026-09-20T12:01:00.670989+00:00",
|
||||
"lastTerminalAt": "2026-09-20T14:14:39.678925+00:00",
|
||||
"modelType": "mpt",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
@@ -11982,8 +11984,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|none": {
|
||||
"attributableFailureCount": 5,
|
||||
@@ -15904,9 +15906,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "transformers",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
@@ -15919,8 +15922,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|transformers|text-generation|qwen3_5|none|33": {
|
||||
"attributableFailureCount": 3,
|
||||
@@ -17908,7 +17911,7 @@
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
@@ -17919,11 +17922,11 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 2,
|
||||
"successCount": 4,
|
||||
"successRate": 1.0,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|muse_glimmer|none|34": {
|
||||
@@ -21939,15 +21942,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15859,
|
||||
"totalRecords": 15964,
|
||||
"terminalRecords": 15862,
|
||||
"totalRecords": 15967,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5754,
|
||||
"decisionFailureRate": 0.8619,
|
||||
"decisionSuccessRate": 0.1381,
|
||||
"decisionTotal": 6676,
|
||||
"decisionFailureRate": 0.8616,
|
||||
"decisionSuccessRate": 0.1384,
|
||||
"decisionTotal": 6678,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3759,
|
||||
"ambiguous_runtime": 3760,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
@@ -21963,15 +21966,15 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 14937,
|
||||
"failureRate": 0.9419,
|
||||
"failureCount": 14938,
|
||||
"failureRate": 0.9417,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 922,
|
||||
"successRate": 0.0581,
|
||||
"total": 15859,
|
||||
"unresolvedFailureCount": 8261
|
||||
"successCount": 924,
|
||||
"successRate": 0.0583,
|
||||
"total": 15862,
|
||||
"unresolvedFailureCount": 8262
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
@@ -22016,13 +22019,12 @@
|
||||
"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 Iluvatar_mrv-100|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 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": 15964,
|
||||
"summarizedRecords": 15967,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user