state: generation 9804 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T12:47:12.275973+00:00",
|
||||
"generatedAt": "2026-09-19T12:50:16.034387+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -83,7 +83,7 @@
|
||||
"8": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 715,
|
||||
"listingErrors": 716,
|
||||
"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": 8,
|
||||
"nextAccountIndex": 9,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-19T12:47:12.252163+00:00",
|
||||
"updatedAt": "2026-09-19T12:50:16.010780+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,320 +416,320 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-19T12:45:35.650545+00:00",
|
||||
"generatedAt": "2026-09-19T12:48:19.799326+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 478.9965870307167,
|
||||
"backlogHours": 477.38775510204084,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.21586929663521046,
|
||||
"queueFactor": 0.8046472231000348,
|
||||
"queueWeight": 0.8046472231000348,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.13310580204778158,
|
||||
"recentTerminal": 293,
|
||||
"recentWilsonLowerBound": 0.09891998521729493,
|
||||
"qualityFactor": 0.32631115986275594,
|
||||
"queueFactor": 0.804720380798742,
|
||||
"queueWeight": 0.804720380798742,
|
||||
"recentSuccess": 41,
|
||||
"recentSuccessRate": 0.13945578231292516,
|
||||
"recentTerminal": 294,
|
||||
"recentWilsonLowerBound": 0.10448917640552996,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.17369863009007977,
|
||||
"selectionWeight": 0.2625892408236361,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 48.833333333333336,
|
||||
"waiting": 23391
|
||||
"throughputPerHour": 49.0,
|
||||
"waiting": 23392
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 289.78856152513,
|
||||
"backlogHours": 288.76683937823833,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.09423137975965891,
|
||||
"queueFactor": 0.8676472483861871,
|
||||
"queueWeight": 0.8676472483861871,
|
||||
"recentSuccess": 51,
|
||||
"recentSuccessRate": 0.08838821490467938,
|
||||
"recentTerminal": 577,
|
||||
"recentWilsonLowerBound": 0.06786561727302878,
|
||||
"qualityFactor": 0.1315671208480616,
|
||||
"queueFactor": 0.8677479453501664,
|
||||
"queueWeight": 0.8677479453501664,
|
||||
"recentSuccess": 52,
|
||||
"recentSuccessRate": 0.08981001727115717,
|
||||
"recentTerminal": 579,
|
||||
"recentWilsonLowerBound": 0.06914489862007774,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.0817595973601019,
|
||||
"selectionWeight": 0.1141670987915425,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 96.16666666666667,
|
||||
"waiting": 27868
|
||||
"throughputPerHour": 96.5,
|
||||
"waiting": 27866
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 37.5859375,
|
||||
"backlogHours": 37.43005181347151,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.1786953537172251,
|
||||
"queueWeight": 1.1786953537172251,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.032552083333333336,
|
||||
"recentTerminal": 768,
|
||||
"recentWilsonLowerBound": 0.022144580970426802,
|
||||
"queueFactor": 1.1789425100984,
|
||||
"queueWeight": 1.1789425100984,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.03367875647668394,
|
||||
"recentTerminal": 772,
|
||||
"recentWilsonLowerBound": 0.023085184053386568,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.058934767685861256,
|
||||
"selectionWeight": 0.05894712550492,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 128.0,
|
||||
"waiting": 4811
|
||||
"throughputPerHour": 128.66666666666666,
|
||||
"waiting": 4816
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 98.7713004484305,
|
||||
"backlogHours": 98.68085106382978,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0196726341290263,
|
||||
"queueWeight": 1.0196726341290263,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.01905829596412556,
|
||||
"recentTerminal": 892,
|
||||
"recentWilsonLowerBound": 0.011932508994863127,
|
||||
"queueFactor": 1.0193909155315415,
|
||||
"queueWeight": 1.0193909155315415,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.020156774916013438,
|
||||
"recentTerminal": 893,
|
||||
"recentWilsonLowerBound": 0.012787450727466036,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.050983631706451316,
|
||||
"selectionWeight": 0.05096954577657708,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 148.66666666666666,
|
||||
"waiting": 14684
|
||||
"throughputPerHour": 148.83333333333334,
|
||||
"waiting": 14687
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 84.88540031397174,
|
||||
"backlogHours": 84.553125,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.043110770123691,
|
||||
"queueWeight": 1.043110770123691,
|
||||
"queueFactor": 1.0432928773822252,
|
||||
"queueWeight": 1.0432928773822252,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.03924646781789639,
|
||||
"recentTerminal": 637,
|
||||
"recentWilsonLowerBound": 0.026722469542415413,
|
||||
"recentSuccessRate": 0.0390625,
|
||||
"recentTerminal": 640,
|
||||
"recentWilsonLowerBound": 0.02659655474602655,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.052155538506184554,
|
||||
"selectionWeight": 0.052164643869111266,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 106.16666666666667,
|
||||
"waiting": 9012
|
||||
"throughputPerHour": 106.66666666666667,
|
||||
"waiting": 9019
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 63.048780487804876,
|
||||
"backlogHours": 61.56521739130435,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 24,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0906963909350629,
|
||||
"queueWeight": 1.0906963909350629,
|
||||
"queueFactor": 1.0941462578484729,
|
||||
"queueWeight": 1.0941462578484729,
|
||||
"recentSuccess": 11,
|
||||
"recentSuccessRate": 0.044715447154471545,
|
||||
"recentTerminal": 246,
|
||||
"recentWilsonLowerBound": 0.02514880316199299,
|
||||
"recentSuccessRate": 0.043478260869565216,
|
||||
"recentTerminal": 253,
|
||||
"recentWilsonLowerBound": 0.024448065140738544,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.05453481954675315,
|
||||
"selectionWeight": 0.05470731289242364,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 41.0,
|
||||
"waiting": 2585
|
||||
"throughputPerHour": 42.166666666666664,
|
||||
"waiting": 2596
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 115.734375,
|
||||
"backlogHours": 115.08880308880309,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.2209577782470068,
|
||||
"queueFactor": 0.9957172341520372,
|
||||
"queueWeight": 0.9957172341520372,
|
||||
"qualityFactor": 0.2884647308038784,
|
||||
"queueFactor": 0.9961408059487004,
|
||||
"queueWeight": 0.9961408059487004,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.13671875,
|
||||
"recentTerminal": 256,
|
||||
"recentWilsonLowerBound": 0.09997313788762838,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.22001146782048878,
|
||||
"recentSuccessRate": 0.13513513513513514,
|
||||
"recentTerminal": 259,
|
||||
"recentWilsonLowerBound": 0.09879507690356609,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.28735148943075034,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 42.666666666666664,
|
||||
"waiting": 4938
|
||||
"throughputPerHour": 43.166666666666664,
|
||||
"waiting": 4968
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2295.0,
|
||||
"backlogHours": 2241.767441860465,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.9727599575909835,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.7,
|
||||
"queueWeight": 0.7,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.40476190476190477,
|
||||
"recentTerminal": 42,
|
||||
"recentWilsonLowerBound": 0.2704264767120908,
|
||||
"recentSuccessRate": 0.3953488372093023,
|
||||
"recentTerminal": 43,
|
||||
"recentWilsonLowerBound": 0.263651061984564,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.3809319703136884,
|
||||
"selectionWeight": 1.75,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.0,
|
||||
"waiting": 16065
|
||||
"throughputPerHour": 7.166666666666667,
|
||||
"waiting": 16066
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 152.95673076923077,
|
||||
"backlogHours": 151.81861575179,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9549268193831144,
|
||||
"queueWeight": 0.9549268193831144,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.06971153846153846,
|
||||
"recentTerminal": 416,
|
||||
"recentWilsonLowerBound": 0.0489727599107355,
|
||||
"qualityFactor": 0.06622125140702059,
|
||||
"queueFactor": 0.9556017531631489,
|
||||
"queueWeight": 0.9556017531631489,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.07159904534606205,
|
||||
"recentTerminal": 419,
|
||||
"recentWilsonLowerBound": 0.05061012648046582,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.047746340969155726,
|
||||
"selectionWeight": 0.06328114394120651,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 69.33333333333333,
|
||||
"waiting": 10605
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 69.83333333333333,
|
||||
"waiting": 10602
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 153.3440366972477,
|
||||
"backlogHours": 153.27522935779817,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9545646470536836,
|
||||
"queueWeight": 0.9545646470536836,
|
||||
"queueFactor": 0.9542340198517159,
|
||||
"queueWeight": 0.9542340198517159,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.052752293577981654,
|
||||
"recentTerminal": 436,
|
||||
"recentWilsonLowerBound": 0.03540545563616003,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.04772823235268418,
|
||||
"selectionWeight": 0.047711700992585794,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 72.66666666666667,
|
||||
"waiting": 11143
|
||||
"waiting": 11138
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 109.20519480519481,
|
||||
"backlogHours": 109.23116883116883,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0044281714943715,
|
||||
"queueWeight": 1.0044281714943715,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.025974025974025976,
|
||||
"queueFactor": 1.0039768638200492,
|
||||
"queueWeight": 1.0039768638200492,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.025108225108225107,
|
||||
"recentTerminal": 1155,
|
||||
"recentWilsonLowerBound": 0.01825363327833703,
|
||||
"recentWilsonLowerBound": 0.01753793960754816,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.05022140857471857,
|
||||
"selectionWeight": 0.050198843191002464,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 192.5,
|
||||
"waiting": 21022
|
||||
"waiting": 21027
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 6334.0,
|
||||
"backlogHours": 5938.125,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 2.5,
|
||||
"qualityFactor": 1.8687607859954392,
|
||||
"queueFactor": 0.7,
|
||||
"queueWeight": 0.7,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.5333333333333333,
|
||||
"recentTerminal": 15,
|
||||
"recentWilsonLowerBound": 0.3011663015105079,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.4375,
|
||||
"recentTerminal": 16,
|
||||
"recentWilsonLowerBound": 0.2309836333518552,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.75,
|
||||
"selectionWeight": 1.3081325501968073,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 2.5,
|
||||
"throughputPerHour": 2.6666666666666665,
|
||||
"waiting": 15835
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 72.03668122270741,
|
||||
"backlogHours": 71.91630340017437,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0691098361876408,
|
||||
"queueWeight": 1.0691098361876408,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.004366812227074236,
|
||||
"recentTerminal": 1145,
|
||||
"recentWilsonLowerBound": 0.0018666124966613936,
|
||||
"queueFactor": 1.0689357167231361,
|
||||
"queueWeight": 1.0689357167231361,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.0052310374891020054,
|
||||
"recentTerminal": 1147,
|
||||
"recentWilsonLowerBound": 0.0023995379524277753,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.05345549180938204,
|
||||
"selectionWeight": 0.05344678583615681,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 190.83333333333334,
|
||||
"waiting": 13747
|
||||
"throughputPerHour": 191.16666666666666,
|
||||
"waiting": 13748
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 68.23880597014926,
|
||||
"backlogHours": 68.12539184952978,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0778309911761483,
|
||||
"queueWeight": 1.0778309911761483,
|
||||
"queueFactor": 1.0776539868161208,
|
||||
"queueWeight": 1.0776539868161208,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.018853102906520033,
|
||||
"recentTerminal": 1273,
|
||||
"recentWilsonLowerBound": 0.012701439171525457,
|
||||
"recentSuccessRate": 0.018808777429467086,
|
||||
"recentTerminal": 1276,
|
||||
"recentWilsonLowerBound": 0.012671501947191393,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.05389154955880742,
|
||||
"selectionWeight": 0.05388269934080604,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 212.16666666666666,
|
||||
"waiting": 14478
|
||||
"throughputPerHour": 212.66666666666666,
|
||||
"waiting": 14488
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-19T12:37:36.233780+00:00",
|
||||
"queueAttemptedAt": "2026-09-19T12:48:19.799326+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-19T12:37:36.233780+00:00",
|
||||
"queueUpdatedAt": "2026-09-19T12:48:19.799326+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Kunlunxin_p-800",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user