state: generation 11770 (cycle)
This commit is contained in:
@@ -2850,7 +2850,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T21:15:49.262140+00:00",
|
||||
"generatedAt": "2026-09-21T21:18:50.100950+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 143,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,7 +434,7 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-21T21:17:48.389977+00:00",
|
||||
"generatedAt": "2026-09-21T21:19:02.061951+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-21T21:17:48.389977+00:00",
|
||||
"catalogUpdatedAt": "2026-09-21T21:19:02.061951+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-21T21:17:48.389977+00:00",
|
||||
"generatedAt": "2026-09-21T21:19:02.061951+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6829,6 +6829,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-21T21:17:48.389977+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-21T21:19:02.061951+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T21:08:12.512892+00:00",
|
||||
"lastSyncTime": "2026-09-21T21:08:12.157607+00:00",
|
||||
"generatedAt": "2026-09-21T21:18:50.026923+00:00",
|
||||
"lastSyncTime": "2026-09-21T21:18:49.765067+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -4688,16 +4688,16 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 624,
|
||||
"attributableFailureCount": 625,
|
||||
"decisionFailureRate": 0.963,
|
||||
"decisionSuccessRate": 0.037,
|
||||
"decisionTotal": 648,
|
||||
"decisionTotal": 649,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 129,
|
||||
"architecture_compatibility": 20,
|
||||
"backend_operator": 43,
|
||||
"context_length": 46,
|
||||
"framework_architecture_unsupported": 192,
|
||||
"framework_architecture_unsupported": 193,
|
||||
"memory_capacity": 84,
|
||||
"model_load": 61,
|
||||
"platform_infrastructure": 3,
|
||||
@@ -4706,7 +4706,7 @@
|
||||
"tokenizer_compatibility": 78,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 765,
|
||||
"failureCount": 766,
|
||||
"failureRate": 0.9696,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -4716,7 +4716,7 @@
|
||||
"successRate": 0.0304,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 789,
|
||||
"total": 790,
|
||||
"unresolvedFailureCount": 138
|
||||
},
|
||||
"MetaX_c-500|vllm|unknown": {
|
||||
@@ -5506,17 +5506,17 @@
|
||||
"unresolvedFailureCount": 6446
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3545,
|
||||
"attributableFailureCount": 3546,
|
||||
"decisionFailureRate": 0.9758,
|
||||
"decisionSuccessRate": 0.0242,
|
||||
"decisionTotal": 3633,
|
||||
"decisionTotal": 3634,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1498,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 84,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1311,
|
||||
"framework_architecture_unsupported": 1312,
|
||||
"memory_capacity": 722,
|
||||
"model_load": 208,
|
||||
"platform_infrastructure": 865,
|
||||
@@ -5525,14 +5525,14 @@
|
||||
"tokenizer_compatibility": 412,
|
||||
"参数/模板问题": 46
|
||||
},
|
||||
"failureCount": 5954,
|
||||
"failureCount": 5955,
|
||||
"failureRate": 0.9854,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 865,
|
||||
"successCount": 88,
|
||||
"successRate": 0.0146,
|
||||
"total": 6042,
|
||||
"total": 6043,
|
||||
"unresolvedFailureCount": 1544
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -5679,7 +5679,7 @@
|
||||
"unresolvedFailureCount": 119
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T21:08:12.500869+00:00",
|
||||
"generatedAt": "2026-09-21T21:18:50.016376+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 99,
|
||||
@@ -5948,16 +5948,16 @@
|
||||
"unresolvedFailureCount": 170
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 659,
|
||||
"decisionFailureRate": 0.8197,
|
||||
"decisionSuccessRate": 0.1803,
|
||||
"decisionTotal": 804,
|
||||
"attributableFailureCount": 660,
|
||||
"decisionFailureRate": 0.8199,
|
||||
"decisionSuccessRate": 0.1801,
|
||||
"decisionTotal": 805,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 301,
|
||||
"architecture_compatibility": 21,
|
||||
"backend_operator": 43,
|
||||
"context_length": 59,
|
||||
"framework_architecture_unsupported": 196,
|
||||
"framework_architecture_unsupported": 197,
|
||||
"memory_capacity": 85,
|
||||
"model_load": 61,
|
||||
"platform_infrastructure": 5,
|
||||
@@ -5968,14 +5968,14 @@
|
||||
"日志缺失": 15,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 1426,
|
||||
"failureRate": 0.9077,
|
||||
"failureCount": 1427,
|
||||
"failureRate": 0.9078,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 5,
|
||||
"successCount": 145,
|
||||
"successRate": 0.0923,
|
||||
"total": 1571,
|
||||
"successRate": 0.0922,
|
||||
"total": 1572,
|
||||
"unresolvedFailureCount": 762
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -15454,14 +15454,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|muse_glimmer|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "muse_glimmer",
|
||||
@@ -15473,7 +15473,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors": {
|
||||
@@ -35281,6 +35281,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|muse_glimmer|none|35": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 35,
|
||||
"modelType": "muse_glimmer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -38329,20 +38353,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16417,
|
||||
"totalRecords": 16611,
|
||||
"terminalRecords": 16418,
|
||||
"totalRecords": 16612,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5920,
|
||||
"attributableFailureCount": 5921,
|
||||
"decisionFailureRate": 0.862,
|
||||
"decisionSuccessRate": 0.138,
|
||||
"decisionTotal": 6868,
|
||||
"decisionTotal": 6869,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4040,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 105,
|
||||
"context_length": 321,
|
||||
"framework_architecture_unsupported": 2092,
|
||||
"framework_architecture_unsupported": 2093,
|
||||
"memory_capacity": 1199,
|
||||
"model_load": 500,
|
||||
"platform_infrastructure": 925,
|
||||
@@ -38353,31 +38377,31 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15469,
|
||||
"failureCount": 15470,
|
||||
"failureRate": 0.9423,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 925,
|
||||
"successCount": 948,
|
||||
"successRate": 0.0577,
|
||||
"total": 16417,
|
||||
"total": 16418,
|
||||
"unresolvedFailureCount": 8624
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 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 Cambricon_mlu-370-x8 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Kunlunxin_p-800 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。",
|
||||
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"GPU Iluvatar_bi-100 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-b3 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 Cambricon_mlu-370-x4 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 Cambricon_mlu-370-x8 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 Ascend_910-b4 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。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高(≥50%),建议重点关注。",
|
||||
"组合 Iluvatar_bi-150|vllm|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 Sunrise_pt-200-x1|vllm_fix_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 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。",
|
||||
@@ -38417,6 +38441,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16611,
|
||||
"summarizedRecords": 16612,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user