state: generation 14862 (cycle)

This commit is contained in:
2026-09-24 13:37:19 +00:00
parent 6e4f70b071
commit 63e95f5e38
8 changed files with 1663 additions and 1617 deletions

View File

@@ -3204,7 +3204,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-24T13:31:51.604995+00:00",
"generatedAt": "2026-09-24T13:36:52.656597+00:00",
"summary": {
"activeBlockCount": 161,
"byGpuFramework": {

View File

@@ -396,99 +396,99 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-24T13:35:44.475445+00:00",
"generatedAt": "2026-09-24T13:37:15.488969+00:00",
"gpuStats": {
"Ascend_910-b4": {
"available": true,
"backlogHours": 1152.3221476510068,
"backlogHours": 1183.8620689655172,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.9384234278933614,
"queueFactor": 0.9146216912074664,
"queueWeight": 0.9146216912074664,
"recentSuccess": 53,
"recentSuccessRate": 0.35570469798657717,
"recentTerminal": 149,
"recentWilsonLowerBound": 0.2833482425162708,
"qualityFactor": 0.951483790913402,
"queueFactor": 0.9108877150795957,
"queueWeight": 0.9108877150795957,
"recentSuccess": 52,
"recentSuccessRate": 0.3586206896551724,
"recentTerminal": 145,
"recentWilsonLowerBound": 0.2851339669748648,
"running": 8,
"selectionWeight": 0.8583024226885341,
"selectionWeight": 0.8666948962403804,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.833333333333332,
"waiting": 28616
"throughputPerHour": 24.166666666666668,
"waiting": 28610
},
"Biren_166m": {
"available": true,
"backlogHours": 206.74285714285716,
"backlogHours": 211.22627737226279,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.3171560782273986,
"queueFactor": 1.1834856767466995,
"queueWeight": 1.1834856767466995,
"recentSuccess": 33,
"recentSuccessRate": 0.2357142857142857,
"recentTerminal": 140,
"recentWilsonLowerBound": 0.17305032975689183,
"qualityFactor": 0.28270338312158144,
"queueFactor": 1.1796354599600463,
"queueWeight": 1.1796354599600463,
"recentSuccess": 31,
"recentSuccessRate": 0.22627737226277372,
"recentTerminal": 137,
"recentWilsonLowerBound": 0.1642371904152058,
"running": 8,
"selectionWeight": 0.375349675875282,
"selectionWeight": 0.3334869353808879,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.333333333333332,
"waiting": 4824
"throughputPerHour": 22.833333333333332,
"waiting": 4823
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1420.2461538461537,
"backlogHours": 1442.0625,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.30570006009394524,
"queueFactor": 0.886386310265614,
"queueWeight": 0.886386310265614,
"recentSuccess": 17,
"recentSuccessRate": 0.26153846153846155,
"recentTerminal": 65,
"recentWilsonLowerBound": 0.17018055060319134,
"qualityFactor": 0.26744873871975483,
"queueFactor": 0.8843260089798054,
"queueWeight": 0.8843260089798054,
"recentSuccess": 16,
"recentSuccessRate": 0.25,
"recentTerminal": 64,
"recentWilsonLowerBound": 0.16014791974174092,
"running": 7,
"selectionWeight": 0.27096834831464855,
"selectionWeight": 0.23651187571872354,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.833333333333334,
"waiting": 15386
"throughputPerHour": 10.666666666666666,
"waiting": 15382
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 544.92,
"backlogHours": 544.56,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.26118326794349606,
"queueFactor": 1.0233581935064588,
"queueWeight": 1.0233581935064588,
"queueFactor": 1.0234182333346336,
"queueWeight": 1.0234182333346336,
"recentSuccess": 23,
"recentSuccessRate": 0.23,
"recentTerminal": 100,
"recentWilsonLowerBound": 0.15843154746876406,
"running": 7,
"selectionWeight": 0.2672840372567695,
"selectionWeight": 0.26729971865529895,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.666666666666668,
"waiting": 9082
"waiting": 9076
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 53.02173913043478,
"backlogHours": 52.38709677419355,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -498,19 +498,19 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 12,
"recentSuccessRate": 0.043478260869565216,
"recentTerminal": 276,
"recentWilsonLowerBound": 0.02504337022584559,
"recentSuccessRate": 0.043010752688172046,
"recentTerminal": 279,
"recentWilsonLowerBound": 0.024772233291548575,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 46.0,
"waiting": 2439
"throughputPerHour": 46.5,
"waiting": 2436
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 100.68243243243242,
"backlogHours": 102.47422680412372,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
@@ -519,104 +519,104 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 30,
"recentSuccessRate": 0.10135135135135136,
"recentTerminal": 296,
"recentWilsonLowerBound": 0.07191899900443502,
"running": 8,
"recentSuccess": 29,
"recentSuccessRate": 0.09965635738831616,
"recentTerminal": 291,
"recentWilsonLowerBound": 0.07028546464040038,
"running": 5,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 49.333333333333336,
"waiting": 4967
"throughputPerHour": 48.5,
"waiting": 4970
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 3702.0000000000005,
"backlogHours": 4184.347826086956,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.2314663769527514,
"queueFactor": 0.767736380919533,
"queueWeight": 0.767736380919533,
"qualityFactor": 1.6689592169541345,
"queueFactor": 0.7537300739505735,
"queueWeight": 0.7537300739505735,
"recentSuccess": 13,
"recentSuccessRate": 0.5,
"recentTerminal": 26,
"recentWilsonLowerBound": 0.3206030631500208,
"recentSuccessRate": 0.5652173913043478,
"recentTerminal": 23,
"recentWilsonLowerBound": 0.36811049305016963,
"running": 2,
"selectionWeight": 0.9454415394657948,
"selectionWeight": 1.257944754015331,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 4.333333333333333,
"waiting": 16042
"throughputPerHour": 3.8333333333333335,
"waiting": 16040
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 568.373831775701,
"backlogHours": 553.0363636363637,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.496961390016157,
"queueFactor": 1.0169098923184685,
"queueWeight": 1.0169098923184685,
"recentSuccess": 31,
"recentSuccessRate": 0.2897196261682243,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.21224200748413424,
"qualityFactor": 0.5502380275326447,
"queueFactor": 1.021049877466962,
"queueWeight": 1.021049877466962,
"recentSuccess": 33,
"recentSuccessRate": 0.3,
"recentTerminal": 110,
"recentWilsonLowerBound": 0.22229769508028016,
"running": 8,
"selectionWeight": 0.5053649536077667,
"selectionWeight": 0.5618204705898698,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.833333333333332,
"waiting": 10136
"throughputPerHour": 18.333333333333332,
"waiting": 10139
},
"MetaX_c-500": {
"available": true,
"backlogHours": 635.6,
"backlogHours": 635.4285714285714,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.47572336165355805,
"qualityFactor": 0.5645126985819736,
"queueFactor": 1.0,
"queueWeight": 1.0,
"recentSuccess": 30,
"recentSuccessRate": 0.2857142857142857,
"recentSuccess": 32,
"recentSuccessRate": 0.3047619047619048,
"recentTerminal": 105,
"recentWilsonLowerBound": 0.20806999151103064,
"recentWilsonLowerBound": 0.22490075875702692,
"running": 4,
"selectionWeight": 0.47572336165355805,
"selectionWeight": 0.5645126985819736,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.5,
"waiting": 11123
"waiting": 11120
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 2499.72,
"backlogHours": 2499.6,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.5,
"queueFactor": 0.8143177071630086,
"queueWeight": 0.8143177071630086,
"queueFactor": 0.8142906224384582,
"queueWeight": 0.8142906224384582,
"recentSuccess": 29,
"recentSuccessRate": 0.58,
"recentTerminal": 50,
"recentWilsonLowerBound": 0.4423319668777783,
"running": 4,
"selectionWeight": 2.035794267907521,
"selectionWeight": 2.0357265560961455,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.333333333333334,
"waiting": 20831
"waiting": 20830
},
"Sunrise_pt-200-x1": {
"available": true,
@@ -627,14 +627,14 @@
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.8667295268164948,
"queueFactor": 0.731681191925064,
"queueWeight": 0.731681191925064,
"queueFactor": 0.7316515871166086,
"queueWeight": 0.7316515871166086,
"recentSuccess": 9,
"recentSuccessRate": 0.47368421052631576,
"recentTerminal": 19,
"recentWilsonLowerBound": 0.2732950548744854,
"running": 2,
"selectionWeight": 0.6341696932577396,
"selectionWeight": 0.6341440338961156,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 3.1666666666666665,
@@ -642,52 +642,52 @@
},
"Vastai_va16": {
"available": true,
"backlogHours": 603.986013986014,
"backlogHours": 591.5342465753425,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.8432142496213593,
"queueFactor": 1.0076821160966638,
"queueWeight": 1.0076821160966638,
"qualityFactor": 0.8039000579371001,
"queueFactor": 1.0107948647055496,
"queueWeight": 1.0107948647055496,
"recentSuccess": 49,
"recentSuccessRate": 0.34265734265734266,
"recentTerminal": 143,
"recentWilsonLowerBound": 0.2698994070063999,
"recentSuccessRate": 0.3356164383561644,
"recentTerminal": 146,
"recentWilsonLowerBound": 0.2641049442736961,
"running": 16,
"selectionWeight": 0.8496919193813118,
"selectionWeight": 0.8125780502993145,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.833333333333332,
"waiting": 14395
"throughputPerHour": 24.333333333333332,
"waiting": 14394
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 754.781954887218,
"backlogHours": 749.1492537313434,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.2536017524512272,
"queueFactor": 0.9745505187309582,
"queueWeight": 0.9745505187309582,
"recentSuccess": 29,
"recentSuccessRate": 0.21804511278195488,
"recentTerminal": 133,
"recentWilsonLowerBound": 0.15632434518405217,
"qualityFactor": 0.22722168855526817,
"queueFactor": 0.9756066638794528,
"queueWeight": 0.9756066638794528,
"recentSuccess": 28,
"recentSuccessRate": 0.208955223880597,
"recentTerminal": 134,
"recentWilsonLowerBound": 0.14871120011463207,
"running": 6,
"selectionWeight": 0.2471477194024235,
"selectionWeight": 0.22167899353246123,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.166666666666668,
"submissionEligible": false,
"throughputPerHour": 22.333333333333332,
"waiting": 16731
}
},
"queueAttemptedAt": "2026-09-24T13:27:02.197783+00:00",
"queueAttemptedAt": "2026-09-24T13:37:15.488969+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-24T13:27:02.197783+00:00",
"queueUpdatedAt": "2026-09-24T13:37:15.488969+00:00",
"supportedGpus": [
"Vastai_va16",
"Cambricon_mlu-370-x4",

View File

@@ -1,5 +1,5 @@
{
"catalogUpdatedAt": "2026-09-24T13:35:44.475445+00:00",
"catalogUpdatedAt": "2026-09-24T13:37:15.488969+00:00",
"configuredTaskTypes": [
"text-generation"
],
@@ -56,7 +56,7 @@
"time-series-forecasting"
],
"errors": [],
"generatedAt": "2026-09-24T13:35:44.475445+00:00",
"generatedAt": "2026-09-24T13:37:15.488969+00:00",
"gpuCatalog": {
"Ascend_910-b3": {
"canVerify": true,
@@ -6206,6 +6206,6 @@
"updateTime": "2025-12-22 08:59:53"
}
],
"taskTreeUpdatedAt": "2026-09-24T13:35:44.475445+00:00",
"taskTreeUpdatedAt": "2026-09-24T13:37:15.488969+00:00",
"version": 1
}

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-24T13:31:51.521367+00:00",
"lastSyncTime": "2026-09-24T13:31:51.262642+00:00",
"generatedAt": "2026-09-24T13:36:52.571887+00:00",
"lastSyncTime": "2026-09-24T13:36:52.257909+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3787,23 +3787,23 @@
"decisionSuccessRate": 0.3636,
"decisionTotal": 22,
"failureBreakdown": {
"ambiguous_runtime": 27,
"ambiguous_runtime": 28,
"framework_architecture_unsupported": 11,
"model_load": 3,
"验证失败": 3
},
"failureCount": 44,
"failureRate": 0.8462,
"failureCount": 45,
"failureRate": 0.8491,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 8,
"successRate": 0.1538,
"successRate": 0.1509,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 52,
"unresolvedFailureCount": 30
"total": 53,
"unresolvedFailureCount": 31
},
"Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 18,
@@ -5955,22 +5955,22 @@
"decisionSuccessRate": 0.4167,
"decisionTotal": 48,
"failureBreakdown": {
"ambiguous_runtime": 73,
"ambiguous_runtime": 74,
"framework_architecture_unsupported": 22,
"model_load": 5,
"tokenizer_compatibility": 1,
"参数/模板问题": 3,
"验证失败": 3
},
"failureCount": 107,
"failureRate": 0.8425,
"failureCount": 108,
"failureRate": 0.8438,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 20,
"successRate": 0.1575,
"total": 127,
"unresolvedFailureCount": 79
"successRate": 0.1562,
"total": 128,
"unresolvedFailureCount": 80
},
"vllm-patch-tokenizer": {
"attributableFailureCount": 55,
@@ -6073,7 +6073,7 @@
"unresolvedFailureCount": 195
}
},
"generatedAt": "2026-09-24T13:31:51.508599+00:00",
"generatedAt": "2026-09-24T13:36:52.509287+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 102,
@@ -6165,7 +6165,7 @@
"decisionSuccessRate": 0.09,
"decisionTotal": 811,
"failureBreakdown": {
"ambiguous_runtime": 458,
"ambiguous_runtime": 459,
"architecture_compatibility": 53,
"context_length": 48,
"framework_architecture_unsupported": 291,
@@ -6178,15 +6178,15 @@
"日志缺失": 13,
"验证失败": 42
},
"failureCount": 1552,
"failureCount": 1553,
"failureRate": 0.9551,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 15,
"successCount": 73,
"successRate": 0.0449,
"total": 1625,
"unresolvedFailureCount": 799
"total": 1626,
"unresolvedFailureCount": 800
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 60,
@@ -10768,6 +10768,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -32859,6 +32882,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen2|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 33,
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -50002,15 +50049,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 16988,
"totalRecords": 17208,
"terminalRecords": 16989,
"totalRecords": 17209,
"totals": {
"attributableFailureCount": 6098,
"decisionFailureRate": 0.8635,
"decisionSuccessRate": 0.1365,
"decisionTotal": 7062,
"failureBreakdown": {
"ambiguous_runtime": 4370,
"ambiguous_runtime": 4371,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 127,
@@ -50026,15 +50073,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16024,
"failureCount": 16025,
"failureRate": 0.9433,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 934,
"successCount": 964,
"successRate": 0.0567,
"total": 16988,
"unresolvedFailureCount": 8992
"total": 16989,
"unresolvedFailureCount": 8993
},
"warnings": [
"GPU Iluvatar_mrv-100 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -50045,11 +50092,11 @@
"GPU Vastai_va16 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 Kunlunxin_p-800 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 Iluvatar_bi-150 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 Ascend_910-b3 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 hygon_k100-ai 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 Sunrise_pt-200-x1 本地统计失败率偏高(≥50%),建议重点关注。",
"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-x4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -50092,6 +50139,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17208,
"summarizedRecords": 17209,
"version": 1
}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff