state: generation 8774 (cycle)
This commit is contained in:
@@ -1741,7 +1741,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-17T14:26:43.649470+00:00",
|
||||
"generatedAt": "2026-09-17T14:29:58.865605+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 84,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -75,7 +75,7 @@
|
||||
"7": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 641,
|
||||
"listingErrors": 642,
|
||||
"nextPage": 1,
|
||||
"recordsScanned": 0,
|
||||
"uniqueRecords": 0
|
||||
@@ -102,12 +102,12 @@
|
||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"failureLogsInspected": 0,
|
||||
"mode": "incremental_decision_only",
|
||||
"nextAccountIndex": 7,
|
||||
"nextAccountIndex": 8,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-17T14:26:43.574462+00:00",
|
||||
"updatedAt": "2026-09-17T14:29:58.839342+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-17T14:24:26.666353+00:00",
|
||||
"generatedAt": "2026-09-17T14:28:01.102963+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 969.6326530612245,
|
||||
"backlogHours": 968.7162162162161,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.4860864549490963,
|
||||
"queueFactor": 0.9859592177679982,
|
||||
"queueWeight": 0.9859592177679982,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.2653061224489796,
|
||||
"recentTerminal": 147,
|
||||
"recentWilsonLowerBound": 0.2005734668615306,
|
||||
"qualityFactor": 0.4745777812871076,
|
||||
"queueFactor": 0.9840069765313164,
|
||||
"queueWeight": 0.9840069765313164,
|
||||
"recentSuccess": 38,
|
||||
"recentSuccessRate": 0.25675675675675674,
|
||||
"recentTerminal": 148,
|
||||
"recentWilsonLowerBound": 0.19315446176106385,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.4792614208892303,
|
||||
"selectionWeight": 0.46698784769326707,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.5,
|
||||
"waiting": 23756
|
||||
"throughputPerHour": 24.666666666666668,
|
||||
"waiting": 23895
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1260.402985074627,
|
||||
"backlogHours": 1274.345864661654,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.2029737918280323,
|
||||
"queueFactor": 0.9479242267383988,
|
||||
"queueWeight": 0.9479242267383988,
|
||||
"recentSuccess": 51,
|
||||
"recentSuccessRate": 0.3805970149253731,
|
||||
"recentTerminal": 134,
|
||||
"recentWilsonLowerBound": 0.3028004403078444,
|
||||
"qualityFactor": 1.4336746979158852,
|
||||
"queueFactor": 0.9443534384180075,
|
||||
"queueWeight": 0.9443534384180075,
|
||||
"recentSuccess": 53,
|
||||
"recentSuccessRate": 0.39849624060150374,
|
||||
"recentTerminal": 133,
|
||||
"recentWilsonLowerBound": 0.3192652583897698,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.1403280014051471,
|
||||
"selectionWeight": 1.3538956305497643,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.333333333333332,
|
||||
"waiting": 28149
|
||||
"throughputPerHour": 22.166666666666668,
|
||||
"waiting": 28248
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 177.0989010989011,
|
||||
"backlogHours": 172.33155080213902,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.11460405371137106,
|
||||
"queueFactor": 1.2723824096379284,
|
||||
"queueWeight": 1.2723824096379284,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.14835164835164835,
|
||||
"recentTerminal": 182,
|
||||
"recentWilsonLowerBound": 0.10400160797952315,
|
||||
"qualityFactor": 0.1258979621135053,
|
||||
"queueFactor": 1.2748906722072169,
|
||||
"queueWeight": 1.2748906722072169,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.1497326203208556,
|
||||
"recentTerminal": 187,
|
||||
"recentWilsonLowerBound": 0.10567088261451653,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.14582018201554886,
|
||||
"selectionWeight": 0.16050613754840548,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 30.333333333333332,
|
||||
"waiting": 5372
|
||||
"throughputPerHour": 31.166666666666668,
|
||||
"waiting": 5371
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1552.4745762711864,
|
||||
"backlogHours": 1526.4,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.9794689948311461,
|
||||
"queueFactor": 0.9187479052668788,
|
||||
"queueWeight": 0.9187479052668788,
|
||||
"qualityFactor": 0.9986869918278154,
|
||||
"queueFactor": 0.9191309902778371,
|
||||
"queueWeight": 0.9191309902778371,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.3898305084745763,
|
||||
"recentTerminal": 59,
|
||||
"recentWilsonLowerBound": 0.27579176065584404,
|
||||
"recentSuccessRate": 0.38333333333333336,
|
||||
"recentTerminal": 60,
|
||||
"recentWilsonLowerBound": 0.2708808958488825,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.8998850872749709,
|
||||
"selectionWeight": 0.9179241637762942,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.833333333333334,
|
||||
"waiting": 15266
|
||||
"throughputPerHour": 10.0,
|
||||
"waiting": 15264
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 489.72413793103453,
|
||||
"backlogHours": 494.295652173913,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.20647970327711795,
|
||||
"queueFactor": 1.092338673601178,
|
||||
"queueWeight": 1.092338673601178,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.19827586206896552,
|
||||
"recentTerminal": 116,
|
||||
"recentWilsonLowerBound": 0.13591176378176467,
|
||||
"qualityFactor": 0.2504139391388145,
|
||||
"queueFactor": 1.0885030354416176,
|
||||
"queueWeight": 1.0885030354416176,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.20869565217391303,
|
||||
"recentTerminal": 115,
|
||||
"recentWilsonLowerBound": 0.14444439637630882,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.22554576520329184,
|
||||
"selectionWeight": 0.27257633286949207,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.333333333333332,
|
||||
"waiting": 9468
|
||||
"throughputPerHour": 19.166666666666668,
|
||||
"waiting": 9474
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 31.559251559251557,
|
||||
"backlogHours": 33.97315436241611,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -539,197 +539,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.02702702702702703,
|
||||
"recentTerminal": 481,
|
||||
"recentWilsonLowerBound": 0.01586141321028799,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.03131991051454139,
|
||||
"recentTerminal": 447,
|
||||
"recentWilsonLowerBound": 0.018746501698089283,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 80.16666666666667,
|
||||
"waiting": 2530
|
||||
"throughputPerHour": 74.5,
|
||||
"waiting": 2531
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 77.24324324324324,
|
||||
"backlogHours": 80.45454545454545,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.08228961202354745,
|
||||
"qualityFactor": 0.10089393263442666,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 40,
|
||||
"recentSuccessRate": 0.12012012012012012,
|
||||
"recentTerminal": 333,
|
||||
"recentWilsonLowerBound": 0.08946464308208478,
|
||||
"recentSuccess": 42,
|
||||
"recentSuccessRate": 0.12727272727272726,
|
||||
"recentTerminal": 330,
|
||||
"recentWilsonLowerBound": 0.09555405686762881,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.10697649563061169,
|
||||
"selectionWeight": 0.13116211242475465,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 55.5,
|
||||
"waiting": 4287
|
||||
"throughputPerHour": 55.0,
|
||||
"waiting": 4425
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2588.108108108108,
|
||||
"backlogHours": 2455.6923076923076,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.8857168398178822,
|
||||
"queueFactor": 0.850947319185044,
|
||||
"queueWeight": 0.850947319185044,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.40540540540540543,
|
||||
"recentTerminal": 37,
|
||||
"recentWilsonLowerBound": 0.2634629583994014,
|
||||
"running": 3,
|
||||
"selectionWeight": 0.7536983704000758,
|
||||
"qualityFactor": 0.6797280010418584,
|
||||
"queueFactor": 0.8558577162907214,
|
||||
"queueWeight": 0.8558577162907214,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.358974358974359,
|
||||
"recentTerminal": 39,
|
||||
"recentWilsonLowerBound": 0.22741884696491108,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.581750454670542,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.166666666666667,
|
||||
"waiting": 15960
|
||||
"throughputPerHour": 6.5,
|
||||
"waiting": 15962
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 507.22727272727275,
|
||||
"backlogHours": 499.70149253731347,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.37044922843869704,
|
||||
"queueFactor": 1.0865998654282938,
|
||||
"queueWeight": 1.0865998654282938,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.24242424242424243,
|
||||
"recentTerminal": 132,
|
||||
"recentWilsonLowerBound": 0.17727358005868543,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.40253008176950344,
|
||||
"qualityFactor": 0.32038324084802067,
|
||||
"queueFactor": 1.0867285231182435,
|
||||
"queueWeight": 1.0867285231182435,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.22388059701492538,
|
||||
"recentTerminal": 134,
|
||||
"recentWilsonLowerBound": 0.16156310605767124,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.34816960615860604,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.0,
|
||||
"waiting": 11159
|
||||
"throughputPerHour": 22.333333333333332,
|
||||
"waiting": 11160
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 654.0,
|
||||
"backlogHours": 654.1698113207547,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.5156181503850966,
|
||||
"queueFactor": 1.0459559003683037,
|
||||
"queueWeight": 1.0459559003683037,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.2830188679245283,
|
||||
"qualityFactor": 0.455246085185165,
|
||||
"queueFactor": 1.0436961664235465,
|
||||
"queueWeight": 1.0436961664235465,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.2641509433962264,
|
||||
"recentTerminal": 106,
|
||||
"recentWilsonLowerBound": 0.20602338401321438,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.5393138467322831,
|
||||
"recentWilsonLowerBound": 0.18953748624976913,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.475138593887084,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.666666666666668,
|
||||
"waiting": 11554
|
||||
"waiting": 11557
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 3351.2727272727275,
|
||||
"backlogHours": 3429.488372093023,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8185940254271765,
|
||||
"queueWeight": 0.8185940254271765,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.5681818181818182,
|
||||
"recentTerminal": 44,
|
||||
"recentWilsonLowerBound": 0.42223890740554393,
|
||||
"running": 5,
|
||||
"selectionWeight": 2.0464850635679412,
|
||||
"queueFactor": 0.8140353462835409,
|
||||
"queueWeight": 0.8140353462835409,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.5581395348837209,
|
||||
"recentTerminal": 43,
|
||||
"recentWilsonLowerBound": 0.4110735806551172,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.035088365708852,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.333333333333333,
|
||||
"waiting": 24576
|
||||
"throughputPerHour": 7.166666666666667,
|
||||
"waiting": 24578
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 4235.727272727273,
|
||||
"backlogHours": 4437.714285714285,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.46895956398548644,
|
||||
"queueFactor": 0.7903343138069905,
|
||||
"queueWeight": 0.7903343138069905,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.36363636363636365,
|
||||
"recentTerminal": 22,
|
||||
"recentWilsonLowerBound": 0.19732972772607896,
|
||||
"qualityFactor": 0.3674311747148611,
|
||||
"queueFactor": 0.7831658872135457,
|
||||
"queueWeight": 0.7831658872135457,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.3333333333333333,
|
||||
"recentTerminal": 21,
|
||||
"recentWilsonLowerBound": 0.17194536432683688,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.37063483520569485,
|
||||
"selectionWeight": 0.2877595619354795,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 3.6666666666666665,
|
||||
"waiting": 15531
|
||||
"throughputPerHour": 3.5,
|
||||
"waiting": 15532
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1655.2941176470588,
|
||||
"backlogHours": 1688.6399999999999,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.13004608014046856,
|
||||
"queueFactor": 0.9099525799454833,
|
||||
"queueWeight": 0.9099525799454833,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.19607843137254902,
|
||||
"recentTerminal": 51,
|
||||
"recentWilsonLowerBound": 0.11015224836299274,
|
||||
"qualityFactor": 0.10594808089886878,
|
||||
"queueFactor": 0.9053095509250129,
|
||||
"queueWeight": 0.9053095509250129,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.18,
|
||||
"recentTerminal": 50,
|
||||
"recentWilsonLowerBound": 0.0977008273245379,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.11833576613561644,
|
||||
"selectionWeight": 0.09591580953992183,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.5,
|
||||
"waiting": 14070
|
||||
"throughputPerHour": 8.333333333333334,
|
||||
"waiting": 14072
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 795.173076923077,
|
||||
"backlogHours": 771.2777777777778,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.5386567596485563,
|
||||
"queueFactor": 1.0157358625444561,
|
||||
"queueWeight": 1.0157358625444561,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.28846153846153844,
|
||||
"recentTerminal": 104,
|
||||
"recentWilsonLowerBound": 0.21015782725460305,
|
||||
"qualityFactor": 0.5715767218244637,
|
||||
"queueFactor": 1.018230355876376,
|
||||
"queueWeight": 1.018230355876376,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.28703703703703703,
|
||||
"recentTerminal": 108,
|
||||
"recentWilsonLowerBound": 0.21019243295848952,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.5471329883770282,
|
||||
"selectionWeight": 0.581996768873976,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.333333333333332,
|
||||
"waiting": 13783
|
||||
"throughputPerHour": 18.0,
|
||||
"waiting": 13883
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-17T14:17:02.084753+00:00",
|
||||
"queueAttemptedAt": "2026-09-17T14:28:01.102963+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-17T14:17:02.084753+00:00",
|
||||
"queueUpdatedAt": "2026-09-17T14:28:01.102963+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Kunlunxin_p-800",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-17T14:16:49.674258+00:00",
|
||||
"lastSyncTime": "2026-09-17T14:16:49.448224+00:00",
|
||||
"generatedAt": "2026-09-17T14:27:48.141824+00:00",
|
||||
"lastSyncTime": "2026-09-17T14:27:45.251792+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1815,21 +1815,21 @@
|
||||
"decisionSuccessRate": 0.1,
|
||||
"decisionTotal": 10,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 5,
|
||||
"ambiguous_runtime": 6,
|
||||
"framework_architecture_unsupported": 9
|
||||
},
|
||||
"failureCount": 14,
|
||||
"failureRate": 0.9333,
|
||||
"failureCount": 15,
|
||||
"failureRate": 0.9375,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0667,
|
||||
"successRate": 0.0625,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 5
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation": {
|
||||
"attributableFailureCount": 48,
|
||||
@@ -2304,16 +2304,16 @@
|
||||
"unresolvedFailureCount": 73
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation": {
|
||||
"attributableFailureCount": 5,
|
||||
"attributableFailureCount": 6,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 5,
|
||||
"decisionTotal": 6,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 4,
|
||||
"framework_architecture_unsupported": 5,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 6,
|
||||
"failureCount": 7,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2323,7 +2323,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 6,
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
@@ -2837,14 +2837,14 @@
|
||||
"unresolvedFailureCount": 909
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 396,
|
||||
"decisionFailureRate": 0.9565,
|
||||
"decisionSuccessRate": 0.0435,
|
||||
"decisionTotal": 414,
|
||||
"attributableFailureCount": 397,
|
||||
"decisionFailureRate": 0.9566,
|
||||
"decisionSuccessRate": 0.0434,
|
||||
"decisionTotal": 415,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 230,
|
||||
"backend_operator": 38,
|
||||
"framework_architecture_unsupported": 297,
|
||||
"framework_architecture_unsupported": 298,
|
||||
"memory_capacity": 7,
|
||||
"model_load": 31,
|
||||
"platform_infrastructure": 2,
|
||||
@@ -2853,14 +2853,14 @@
|
||||
"tokenizer_compatibility": 9,
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 668,
|
||||
"failureCount": 669,
|
||||
"failureRate": 0.9738,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 18,
|
||||
"successRate": 0.0262,
|
||||
"total": 686,
|
||||
"total": 687,
|
||||
"unresolvedFailureCount": 270
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2958,21 +2958,21 @@
|
||||
"decisionSuccessRate": 0.0714,
|
||||
"decisionTotal": 14,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 8,
|
||||
"ambiguous_runtime": 9,
|
||||
"framework_architecture_unsupported": 13
|
||||
},
|
||||
"failureCount": 21,
|
||||
"failureRate": 0.9545,
|
||||
"failureCount": 22,
|
||||
"failureRate": 0.9565,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0455,
|
||||
"total": 22,
|
||||
"unresolvedFailureCount": 8
|
||||
"successRate": 0.0435,
|
||||
"total": 23,
|
||||
"unresolvedFailureCount": 9
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-17T14:16:49.668209+00:00",
|
||||
"generatedAt": "2026-09-17T14:27:48.135902+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 57,
|
||||
@@ -2980,22 +2980,22 @@
|
||||
"decisionSuccessRate": 0.05,
|
||||
"decisionTotal": 60,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 37,
|
||||
"ambiguous_runtime": 38,
|
||||
"framework_architecture_unsupported": 55,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 10,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 131,
|
||||
"failureRate": 0.9776,
|
||||
"failureCount": 132,
|
||||
"failureRate": 0.9778,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0224,
|
||||
"total": 134,
|
||||
"unresolvedFailureCount": 74
|
||||
"successRate": 0.0222,
|
||||
"total": 135,
|
||||
"unresolvedFailureCount": 75
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 63,
|
||||
@@ -3139,13 +3139,13 @@
|
||||
"unresolvedFailureCount": 53
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 113,
|
||||
"decisionFailureRate": 0.8433,
|
||||
"decisionSuccessRate": 0.1567,
|
||||
"decisionTotal": 134,
|
||||
"attributableFailureCount": 114,
|
||||
"decisionFailureRate": 0.8444,
|
||||
"decisionSuccessRate": 0.1556,
|
||||
"decisionTotal": 135,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 24,
|
||||
"framework_architecture_unsupported": 67,
|
||||
"framework_architecture_unsupported": 68,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 44,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -3153,14 +3153,14 @@
|
||||
"参数/模板问题": 3,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 188,
|
||||
"failureRate": 0.8995,
|
||||
"failureCount": 189,
|
||||
"failureRate": 0.9,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 21,
|
||||
"successRate": 0.1005,
|
||||
"total": 209,
|
||||
"successRate": 0.1,
|
||||
"total": 210,
|
||||
"unresolvedFailureCount": 74
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
@@ -3378,9 +3378,11 @@
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {},
|
||||
"failureCount": 0,
|
||||
"failureRate": 0.0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 0.5,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
@@ -3388,11 +3390,11 @@
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 1,
|
||||
"successRate": 1.0,
|
||||
"successRate": 0.5,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -5162,14 +5164,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|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": "qwen3_5",
|
||||
@@ -5181,7 +5183,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|rwkv7|none": {
|
||||
@@ -7858,6 +7860,30 @@
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none|30": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 30,
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -10291,6 +10317,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation|qwen3_5|none|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -13042,17 +13092,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 2138,
|
||||
"totalRecords": 2241,
|
||||
"terminalRecords": 2140,
|
||||
"totalRecords": 2243,
|
||||
"totals": {
|
||||
"attributableFailureCount": 703,
|
||||
"decisionFailureRate": 0.8821,
|
||||
"decisionSuccessRate": 0.1179,
|
||||
"decisionTotal": 797,
|
||||
"attributableFailureCount": 704,
|
||||
"decisionFailureRate": 0.8822,
|
||||
"decisionSuccessRate": 0.1178,
|
||||
"decisionTotal": 798,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 525,
|
||||
"ambiguous_runtime": 526,
|
||||
"backend_operator": 50,
|
||||
"framework_architecture_unsupported": 468,
|
||||
"framework_architecture_unsupported": 469,
|
||||
"memory_capacity": 12,
|
||||
"model_load": 86,
|
||||
"platform_infrastructure": 10,
|
||||
@@ -13062,15 +13112,15 @@
|
||||
"参数/模板问题": 133,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 2044,
|
||||
"failureRate": 0.956,
|
||||
"failureCount": 2046,
|
||||
"failureRate": 0.9561,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 10,
|
||||
"successCount": 94,
|
||||
"successRate": 0.044,
|
||||
"total": 2138,
|
||||
"unresolvedFailureCount": 1331
|
||||
"successRate": 0.0439,
|
||||
"total": 2140,
|
||||
"unresolvedFailureCount": 1332
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -13080,11 +13130,11 @@
|
||||
"GPU Biren_166m 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 hygon_k100-ai 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。",
|
||||
"GPU Cambricon_mlu-370-x4 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 Cambricon_mlu-370-x8 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。",
|
||||
"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。",
|
||||
"组合 Ascend_910-b4|vllm_tokenizer_patch|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|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -13110,6 +13160,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 2241,
|
||||
"summarizedRecords": 2243,
|
||||
"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