state: generation 5696 (cycle)
This commit is contained in:
@@ -1307,7 +1307,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-11T12:58:51.046322+00:00",
|
||||
"generatedAt": "2026-09-11T13:02:03.266082+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -59,7 +59,7 @@
|
||||
"5": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 408,
|
||||
"listingErrors": 409,
|
||||
"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": 5,
|
||||
"nextAccountIndex": 6,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-11T12:58:51.020108+00:00",
|
||||
"updatedAt": "2026-09-11T13:02:03.242820+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-11T12:44:43.908786+00:00",
|
||||
"communityAttemptedAt": "2026-09-11T13:00:10.673737+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-11T12:44:43.908786+00:00",
|
||||
"communityUpdatedAt": "2026-09-11T13:00:10.673737+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-11T07:37:13.408660+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -416,73 +416,73 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-11T12:57:07.665064+00:00",
|
||||
"generatedAt": "2026-09-11T13:00:10.673737+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1500.4468085106384,
|
||||
"backlogHours": 1602.5454545454545,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.489102091634684,
|
||||
"queueFactor": 0.8951137923319757,
|
||||
"queueWeight": 0.8951137923319757,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.3404255319148936,
|
||||
"recentTerminal": 94,
|
||||
"recentWilsonLowerBound": 0.2525882883005792,
|
||||
"qualityFactor": 1.6724092473877556,
|
||||
"queueFactor": 0.8900473589730369,
|
||||
"queueWeight": 0.8900473589730369,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.3522727272727273,
|
||||
"recentTerminal": 88,
|
||||
"recentWilsonLowerBound": 0.26056180662975564,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.3329158204125993,
|
||||
"selectionWeight": 1.488523433759556,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.666666666666666,
|
||||
"waiting": 23507
|
||||
"throughputPerHour": 14.666666666666666,
|
||||
"waiting": 23504
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1142.7083333333333,
|
||||
"backlogHours": 1119.2244897959183,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9324402892625299,
|
||||
"queueWeight": 0.9324402892625299,
|
||||
"queueFactor": 0.9392843550735585,
|
||||
"queueWeight": 0.9392843550735585,
|
||||
"recentSuccess": 57,
|
||||
"recentSuccessRate": 0.3958333333333333,
|
||||
"recentTerminal": 144,
|
||||
"recentWilsonLowerBound": 0.3196634619191859,
|
||||
"recentSuccessRate": 0.3877551020408163,
|
||||
"recentTerminal": 147,
|
||||
"recentWilsonLowerBound": 0.31280467369206544,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.3311007231563248,
|
||||
"selectionWeight": 2.348210887683896,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.0,
|
||||
"waiting": 27425
|
||||
"throughputPerHour": 24.5,
|
||||
"waiting": 27421
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 120.65454545454546,
|
||||
"backlogHours": 124.98113207547169,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.19854148808235733,
|
||||
"qualityFactor": 0.22628039248646548,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.1409090909090909,
|
||||
"recentTerminal": 220,
|
||||
"recentWilsonLowerBound": 0.10107707459457875,
|
||||
"recentSuccessRate": 0.14622641509433962,
|
||||
"recentTerminal": 212,
|
||||
"recentWilsonLowerBound": 0.1049661102224358,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.25810393450706454,
|
||||
"selectionWeight": 0.29416451023240514,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 36.666666666666664,
|
||||
"waiting": 4424
|
||||
"throughputPerHour": 35.333333333333336,
|
||||
"waiting": 4416
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
@@ -492,15 +492,15 @@
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.5949447631423909,
|
||||
"queueFactor": 0.8949466667650737,
|
||||
"queueWeight": 0.8949466667650737,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.2631578947368421,
|
||||
"qualityFactor": 0.748403323088131,
|
||||
"queueFactor": 0.8987118840541278,
|
||||
"queueWeight": 0.8987118840541278,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.2807017543859649,
|
||||
"recentTerminal": 57,
|
||||
"recentWilsonLowerBound": 0.16645642421847712,
|
||||
"recentWilsonLowerBound": 0.18079248284972232,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.532443832683619,
|
||||
"selectionWeight": 0.6725989605249043,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.5,
|
||||
@@ -508,29 +508,29 @@
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 487.21100917431187,
|
||||
"backlogHours": 482.72727272727275,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.38908713026604547,
|
||||
"queueFactor": 1.0596288537051675,
|
||||
"queueWeight": 1.0596288537051675,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.2018348623853211,
|
||||
"recentTerminal": 109,
|
||||
"recentWilsonLowerBound": 0.13723625011246085,
|
||||
"qualityFactor": 0.5052810900101117,
|
||||
"queueFactor": 1.065563643000895,
|
||||
"queueWeight": 1.065563643000895,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.21818181818181817,
|
||||
"recentTerminal": 110,
|
||||
"recentWilsonLowerBound": 0.15122852088416214,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.4122879498352429,
|
||||
"selectionWeight": 0.5384091590106377,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.166666666666668,
|
||||
"waiting": 8851
|
||||
"throughputPerHour": 18.333333333333332,
|
||||
"waiting": 8850
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 93.09803921568627,
|
||||
"backlogHours": 96.44897959183673,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -539,126 +539,126 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.058823529411764705,
|
||||
"recentTerminal": 153,
|
||||
"recentWilsonLowerBound": 0.0312522751489112,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.047619047619047616,
|
||||
"recentTerminal": 147,
|
||||
"recentWilsonLowerBound": 0.023255121206704133,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 25.5,
|
||||
"waiting": 2374
|
||||
"throughputPerHour": 24.5,
|
||||
"waiting": 2363
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 169.2608695652174,
|
||||
"backlogHours": 178.16793893129773,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.20140060990254338,
|
||||
"queueFactor": 1.2417319463093723,
|
||||
"queueWeight": 1.2417319463093723,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.15217391304347827,
|
||||
"recentTerminal": 138,
|
||||
"recentWilsonLowerBound": 0.101736119387597,
|
||||
"running": 3,
|
||||
"selectionWeight": 0.25008557132217984,
|
||||
"qualityFactor": 0.2081559371657485,
|
||||
"queueFactor": 1.2374003540467242,
|
||||
"queueWeight": 1.2374003540467242,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.15267175572519084,
|
||||
"recentTerminal": 131,
|
||||
"recentWilsonLowerBound": 0.10105740445609404,
|
||||
"running": 0,
|
||||
"selectionWeight": 0.2575722303458249,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.0,
|
||||
"waiting": 3893
|
||||
"throughputPerHour": 21.833333333333332,
|
||||
"waiting": 3890
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2022.5217391304348,
|
||||
"backlogHours": 2114.318181818182,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.5158632090936941,
|
||||
"queueFactor": 0.8559085403920494,
|
||||
"queueWeight": 0.8559085403920494,
|
||||
"qualityFactor": 0.5995939486497788,
|
||||
"queueFactor": 0.8538058334066982,
|
||||
"queueWeight": 0.8538058334066982,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.2608695652173913,
|
||||
"recentTerminal": 46,
|
||||
"recentWilsonLowerBound": 0.15600735194449333,
|
||||
"recentSuccessRate": 0.2727272727272727,
|
||||
"recentTerminal": 44,
|
||||
"recentWilsonLowerBound": 0.16346223395491324,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.44153172633734233,
|
||||
"selectionWeight": 0.5119368110325374,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.666666666666667,
|
||||
"waiting": 15506
|
||||
"throughputPerHour": 7.333333333333333,
|
||||
"waiting": 15505
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 768.9176470588236,
|
||||
"backlogHours": 768.4941176470588,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.4596148465980881,
|
||||
"queueFactor": 0.9895309112348554,
|
||||
"queueWeight": 0.9895309112348554,
|
||||
"qualityFactor": 0.48207824390957715,
|
||||
"queueFactor": 0.9937761899832644,
|
||||
"queueWeight": 0.9937761899832644,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.2235294117647059,
|
||||
"recentTerminal": 85,
|
||||
"recentWilsonLowerBound": 0.14803142707080863,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.4548030979712744,
|
||||
"selectionWeight": 0.4790778805062824,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.166666666666666,
|
||||
"waiting": 10893
|
||||
"waiting": 10887
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 664.7184466019417,
|
||||
"backlogHours": 705.8350515463917,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.498916418037125,
|
||||
"queueFactor": 1.0113830710390326,
|
||||
"queueWeight": 1.0113830710390326,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.22330097087378642,
|
||||
"recentTerminal": 103,
|
||||
"recentWilsonLowerBound": 0.1536565519868537,
|
||||
"qualityFactor": 0.4689604693832955,
|
||||
"queueFactor": 1.0065357069359708,
|
||||
"queueWeight": 1.0065357069359708,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.21649484536082475,
|
||||
"recentTerminal": 97,
|
||||
"recentWilsonLowerBound": 0.14618670657065766,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.5045956190661812,
|
||||
"selectionWeight": 0.47202545757574005,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.166666666666668,
|
||||
"throughputPerHour": 16.166666666666668,
|
||||
"waiting": 11411
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 349.1835616438356,
|
||||
"backlogHours": 352.060773480663,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.1139181261904485,
|
||||
"queueWeight": 1.1139181261904485,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.0684931506849315,
|
||||
"recentTerminal": 365,
|
||||
"recentWilsonLowerBound": 0.046820378183121604,
|
||||
"queueFactor": 1.1172285455495654,
|
||||
"queueWeight": 1.1172285455495654,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.07458563535911603,
|
||||
"recentTerminal": 362,
|
||||
"recentWilsonLowerBound": 0.051762818981093604,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.055695906309522425,
|
||||
"selectionWeight": 0.055861427277478275,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 60.833333333333336,
|
||||
"waiting": 21242
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 60.333333333333336,
|
||||
"waiting": 21241
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
@@ -668,15 +668,15 @@
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.9211738874385227,
|
||||
"queueFactor": 0.7525784786309571,
|
||||
"queueWeight": 0.7525784786309571,
|
||||
"qualityFactor": 0.9661957033778044,
|
||||
"queueFactor": 0.7557447248491299,
|
||||
"queueWeight": 0.7557447248491299,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.3888888888888889,
|
||||
"recentTerminal": 18,
|
||||
"recentWilsonLowerBound": 0.2030499192693116,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.6932556427630479,
|
||||
"selectionWeight": 0.7301973059996703,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 3.0,
|
||||
@@ -684,52 +684,52 @@
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1012.4262295081968,
|
||||
"backlogHours": 1029.5,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.6102265980224827,
|
||||
"queueFactor": 0.9495259349830687,
|
||||
"queueWeight": 0.9495259349830687,
|
||||
"qualityFactor": 0.6648816215681561,
|
||||
"queueFactor": 0.9511318320955872,
|
||||
"queueWeight": 0.9511318320955872,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.26229508196721313,
|
||||
"recentTerminal": 61,
|
||||
"recentWilsonLowerBound": 0.16838645195913182,
|
||||
"recentSuccessRate": 0.26666666666666666,
|
||||
"recentTerminal": 60,
|
||||
"recentWilsonLowerBound": 0.17132496487078855,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.5794259810388351,
|
||||
"selectionWeight": 0.6323900748488052,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 10.166666666666666,
|
||||
"waiting": 10293
|
||||
"throughputPerHour": 10.0,
|
||||
"waiting": 10295
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 533.8775510204082,
|
||||
"backlogHours": 528.3636363636364,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 1.9859127470286533,
|
||||
"queueFactor": 1.0451896263987595,
|
||||
"queueWeight": 1.0451896263987595,
|
||||
"recentSuccess": 37,
|
||||
"recentSuccessRate": 0.37755102040816324,
|
||||
"recentTerminal": 98,
|
||||
"recentWilsonLowerBound": 0.2879039439886928,
|
||||
"qualityFactor": 2.3372886671563107,
|
||||
"queueFactor": 1.0512227020655878,
|
||||
"queueWeight": 1.0512227020655878,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.3939393939393939,
|
||||
"recentTerminal": 99,
|
||||
"recentWilsonLowerBound": 0.3033806904872684,
|
||||
"running": 6,
|
||||
"selectionWeight": 2.075655402127412,
|
||||
"selectionWeight": 2.457010908195333,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 16.333333333333332,
|
||||
"waiting": 8720
|
||||
"throughputPerHour": 16.5,
|
||||
"waiting": 8718
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-11T12:47:40.384786+00:00",
|
||||
"queueAttemptedAt": "2026-09-11T13:00:10.673737+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-11T12:47:40.384786+00:00",
|
||||
"queueUpdatedAt": "2026-09-11T13:00:10.673737+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Iluvatar_mrv-100",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-11T12:50:33.981130+00:00",
|
||||
"lastSyncTime": "2026-09-11T12:50:33.752023+00:00",
|
||||
"generatedAt": "2026-09-11T12:59:52.891244+00:00",
|
||||
"lastSyncTime": "2026-09-11T12:59:52.253401+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1541,24 +1541,24 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 33,
|
||||
"ambiguous_runtime": 34,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 92,
|
||||
"failureRate": 0.9787,
|
||||
"failureCount": 93,
|
||||
"failureRate": 0.9789,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0213,
|
||||
"successRate": 0.0211,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 94,
|
||||
"unresolvedFailureCount": 72
|
||||
"total": 95,
|
||||
"unresolvedFailureCount": 73
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2295,7 +2295,7 @@
|
||||
"decisionSuccessRate": 0.2609,
|
||||
"decisionTotal": 184,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 128,
|
||||
"ambiguous_runtime": 129,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 89,
|
||||
"memory_capacity": 5,
|
||||
@@ -2305,15 +2305,15 @@
|
||||
"参数/模板问题": 57,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 995,
|
||||
"failureCount": 996,
|
||||
"failureRate": 0.954,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 48,
|
||||
"successRate": 0.046,
|
||||
"total": 1043,
|
||||
"unresolvedFailureCount": 858
|
||||
"total": 1044,
|
||||
"unresolvedFailureCount": 859
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 241,
|
||||
@@ -2443,7 +2443,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-11T12:50:33.976285+00:00",
|
||||
"generatedAt": "2026-09-11T12:59:52.887160+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2523,21 +2523,21 @@
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 22,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 33,
|
||||
"ambiguous_runtime": 34,
|
||||
"framework_architecture_unsupported": 18,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 92,
|
||||
"failureRate": 0.9787,
|
||||
"failureCount": 93,
|
||||
"failureRate": 0.9789,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0213,
|
||||
"total": 94,
|
||||
"unresolvedFailureCount": 72
|
||||
"successRate": 0.0211,
|
||||
"total": 95,
|
||||
"unresolvedFailureCount": 73
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"attributableFailureCount": 17,
|
||||
@@ -4133,21 +4133,20 @@
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 19,
|
||||
"tokenizer_compatibility": 1
|
||||
"ambiguous_runtime": 20
|
||||
},
|
||||
"failureCount": 20,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-11T03:33:48.898214+00:00",
|
||||
"lastTerminalAt": "2026-09-11T12:59:52.253401+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4156,7 +4155,7 @@
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 19
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -6938,15 +6937,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1654,
|
||||
"totalRecords": 1741,
|
||||
"terminalRecords": 1655,
|
||||
"totalRecords": 1742,
|
||||
"totals": {
|
||||
"attributableFailureCount": 434,
|
||||
"decisionFailureRate": 0.8912,
|
||||
"decisionSuccessRate": 0.1088,
|
||||
"decisionTotal": 487,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 391,
|
||||
"ambiguous_runtime": 392,
|
||||
"backend_operator": 40,
|
||||
"framework_architecture_unsupported": 273,
|
||||
"memory_capacity": 11,
|
||||
@@ -6958,31 +6957,30 @@
|
||||
"参数/模板问题": 99,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1601,
|
||||
"failureCount": 1602,
|
||||
"failureRate": 0.968,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 53,
|
||||
"successRate": 0.032,
|
||||
"total": 1654,
|
||||
"unresolvedFailureCount": 1163
|
||||
"total": 1655,
|
||||
"unresolvedFailureCount": 1164
|
||||
},
|
||||
"warnings": [
|
||||
"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 Iluvatar_mrv-100 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 Mthreads_s4000 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 MetaX_c-500 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 Cambricon_mlu-370-x4 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 Biren_166m 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 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 Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"组合 Iluvatar_mrv-100|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 Cambricon_mlu-370-x4|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 Mthreads_s4000|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。",
|
||||
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -6997,10 +6995,11 @@
|
||||
"组合 hygon_k100-ai|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|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 Vastai_va16|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-x4|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 hygon_k100-ai|vllm-patch-tokenizer|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": 1741,
|
||||
"summarizedRecords": 1742,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-11T12:59:52.253401+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T12:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4531547", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-11T12:50:33.752023+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T12:47:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523324", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-11T11:19:08.306651+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:13:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4578314", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-11T11:19:08.306628+00:00", "modelId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457980", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-08T10:00:15.603853+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:43:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4268342", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-08T09:34:21.991823+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332983", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T09:05:31.097966+00:00", "modelId": "amd/Qwen2.5-Coder-1.5B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T08:59:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079918", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T08:12:43.104884+00:00", "modelId": "nv-community/Qwen3-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T08:03:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079088", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "2962f658d0d19055c30e9444af4a4bb320ec4779a2f6b32c0e01f7e0a91b89d4",
|
||||
".modelhub_state/architecture_history_backfill.json": "839bd5f41bd6af35d61ff23fbe578f8051009c76762a1c144150a98195feb992",
|
||||
".modelhub_state/market_intelligence.json": "d5cea7de0d961bc8bdd0e19aa106089d947b578c4e67571fcebd6cb72ecfb8aa",
|
||||
".modelhub_state/official_capabilities.json": "b59506ce175bac8ddd7dc26b805417d3ffc8cc986c1937588f4b5b5f663aac74",
|
||||
".modelhub_state/outcome_checkpoint.json": "53ebe66afa934975d2a4207edcd2c0f7dde6df13ef7e42d9be3dec631f961154",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "1676820f57a618823b97f0ea1c27a58a61979de39e15b4d89292fb15b1e03791",
|
||||
".modelhub_state/architecture_history_backfill.json": "82613f9812dc2a9cb10d81933af4bffb8d9ba8f19ef0476bf79515d83364b04d",
|
||||
".modelhub_state/market_intelligence.json": "2b0eb17d366af9c07b824b8acadb27c1cbe8249683f874d996a01ca6f53dcb94",
|
||||
".modelhub_state/official_capabilities.json": "d599b39f43757def3a73d137b3ebeb93d37238f652bfd6f44729369039bce121",
|
||||
".modelhub_state/outcome_checkpoint.json": "40633343daecca7a91472d185efed3015ee85b4b13ea8402099d80d440549212",
|
||||
".modelhub_state/queue_cleanup_latest.json": "9092a0b045d21453d0210c81bf56fa209d341915359e8357a6e260c821f48c9b",
|
||||
".modelhub_state/recent_outcomes.jsonl": "b8d8e0b8bd0359a3e4a51d5ed0462beb114f22e565ce6087128d91d229780b46",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "62610261aafec5c3758b820f3f0210aa03b2a6733733d4e91c2e2e5a59700b16",
|
||||
".modelhub_state/recovery_intents.jsonl": "1fc0aa67da15ff7c32cfe74f5b5bd7ecd3384d6e3035b055b314b3529e785aa2",
|
||||
".modelhub_state/recent_outcomes.jsonl": "0794ebabd88bc7ab78c5a8767a5c665f73b166e08bacdecf60a48b77a78639d7",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "05f8f1b52578b662192934217d84e6e95013b7c222335f4b4f4ba19d4e6a13d8",
|
||||
".modelhub_state/recovery_intents.jsonl": "41c463093c906af3430433662760f5cf1c5cba6a784854c6fd94c6010cae2b84",
|
||||
".modelhub_state/routing_intelligence.json": "01755a7ae15e8408cf0586a62b0684ec4e7e2d46c2715b9b2bfe968c7d40353e",
|
||||
".modelhub_state/submission_exclusions.jsonl": "3790b5c148f222a4de26d50a3d8afc58891c8da251a82d20dbaf4fc35e6dbd89",
|
||||
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
|
||||
"ledger/submissions.jsonl": "0f2922a5f34c5777fcbb7e7ea1512bd1784eed2b74f5d6c3f05103cb3bbea37e",
|
||||
"outcomes/submissions.jsonl": "9b436339a59d073250c1f14e08f71c1148a29e5b3db2301e39b71ed36893e02b"
|
||||
},
|
||||
"generation": 5695,
|
||||
"generation": 5696,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-11T12:58:51.126967+00:00",
|
||||
"updatedAt": "2026-09-11T13:02:05.302163+00:00",
|
||||
"writerId": "18252d8a8ef94333abd55823b2d81c42"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user