state: generation 6045 (cycle)
This commit is contained in:
@@ -1345,7 +1345,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T05:23:45.197487+00:00",
|
||||
"generatedAt": "2026-09-12T05:26:58.502985+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 68,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -59,7 +59,7 @@
|
||||
"5": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 434,
|
||||
"listingErrors": 435,
|
||||
"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": "2026-09-12T05:23:45.170388+00:00",
|
||||
"updatedAt": "2026-09-12T05:26:58.479682+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-12T05:22:04.532130+00:00",
|
||||
"generatedAt": "2026-09-12T05:24:52.423017+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 884.4528301886793,
|
||||
"backlogHours": 878.9625,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.9163458507735535,
|
||||
"queueFactor": 0.9960704210844068,
|
||||
"queueWeight": 0.9960704210844068,
|
||||
"recentSuccess": 50,
|
||||
"recentSuccessRate": 0.31446540880503143,
|
||||
"recentTerminal": 159,
|
||||
"recentWilsonLowerBound": 0.24739421232895734,
|
||||
"qualityFactor": 1.014015144584712,
|
||||
"queueFactor": 0.9989652226496624,
|
||||
"queueWeight": 0.9989652226496624,
|
||||
"recentSuccess": 52,
|
||||
"recentSuccessRate": 0.325,
|
||||
"recentTerminal": 160,
|
||||
"recentWilsonLowerBound": 0.2572664012140889,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.9127449974389624,
|
||||
"selectionWeight": 1.0129658646801964,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 26.5,
|
||||
"waiting": 23438
|
||||
"throughputPerHour": 26.666666666666668,
|
||||
"waiting": 23439
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 977.6785714285714,
|
||||
"backlogHours": 977.5,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.5154467253063788,
|
||||
"queueFactor": 0.9812096947780926,
|
||||
"queueWeight": 0.9812096947780926,
|
||||
"recentSuccess": 64,
|
||||
"recentSuccessRate": 0.38095238095238093,
|
||||
"qualityFactor": 1.4194651148183985,
|
||||
"queueFactor": 0.983169520336647,
|
||||
"queueWeight": 0.983169520336647,
|
||||
"recentSuccess": 62,
|
||||
"recentSuccessRate": 0.36904761904761907,
|
||||
"recentTerminal": 168,
|
||||
"recentWilsonLowerBound": 0.31095618328018293,
|
||||
"recentWilsonLowerBound": 0.29976657074149565,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.486971018790332,
|
||||
"selectionWeight": 1.3955748360706084,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 28.0,
|
||||
"waiting": 27375
|
||||
"waiting": 27370
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 160.4823529411765,
|
||||
"backlogHours": 158.37209302325581,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.41505958715210767,
|
||||
"queueFactor": 1.286699560357579,
|
||||
"queueWeight": 1.286699560357579,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.22941176470588234,
|
||||
"recentTerminal": 170,
|
||||
"recentWilsonLowerBound": 0.17260330023616693,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.5340569883108152,
|
||||
"qualityFactor": 0.3837070523886028,
|
||||
"queueFactor": 1.2917965573099026,
|
||||
"queueWeight": 1.2917965573099026,
|
||||
"recentSuccess": 38,
|
||||
"recentSuccessRate": 0.22093023255813954,
|
||||
"recentTerminal": 172,
|
||||
"recentWilsonLowerBound": 0.1654034598109465,
|
||||
"running": 10,
|
||||
"selectionWeight": 0.49567144929112755,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 28.333333333333332,
|
||||
"waiting": 4547
|
||||
"throughputPerHour": 28.666666666666668,
|
||||
"waiting": 4540
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1304.5454545454545,
|
||||
"backlogHours": 1247.8260869565217,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.388473400394535,
|
||||
"queueFactor": 0.939663510993858,
|
||||
"queueWeight": 0.939663510993858,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.25757575757575757,
|
||||
"recentTerminal": 66,
|
||||
"recentWilsonLowerBound": 0.1674870734589668,
|
||||
"qualityFactor": 0.41740148673344624,
|
||||
"queueFactor": 0.9478133296427034,
|
||||
"queueWeight": 0.9478133296427034,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.2608695652173913,
|
||||
"recentTerminal": 69,
|
||||
"recentWilsonLowerBound": 0.17185419574593985,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.36503427934245153,
|
||||
"selectionWeight": 0.3956186929386424,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.0,
|
||||
"throughputPerHour": 11.5,
|
||||
"waiting": 14350
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 438.0,
|
||||
"backlogHours": 437.95041322314046,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.6296132926586824,
|
||||
"queueFactor": 1.10680249244991,
|
||||
"queueWeight": 1.10680249244991,
|
||||
"recentSuccess": 34,
|
||||
"recentSuccessRate": 0.2809917355371901,
|
||||
"qualityFactor": 0.6898130517816887,
|
||||
"queueFactor": 1.109001619037338,
|
||||
"queueWeight": 1.109001619037338,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.2892561983471074,
|
||||
"recentTerminal": 121,
|
||||
"recentWilsonLowerBound": 0.2085956290113622,
|
||||
"recentWilsonLowerBound": 0.21593930152944865,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.6968575615942243,
|
||||
"selectionWeight": 0.7650037912589799,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.166666666666668,
|
||||
"waiting": 8833
|
||||
"waiting": 8832
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 53.87412587412587,
|
||||
"backlogHours": 52.067796610169495,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -540,146 +540,146 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.04195804195804196,
|
||||
"recentTerminal": 286,
|
||||
"recentWilsonLowerBound": 0.024161851162364332,
|
||||
"running": 24,
|
||||
"recentSuccessRate": 0.04067796610169491,
|
||||
"recentTerminal": 295,
|
||||
"recentWilsonLowerBound": 0.023419917869188952,
|
||||
"running": 25,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 47.666666666666664,
|
||||
"waiting": 2568
|
||||
"throughputPerHour": 49.166666666666664,
|
||||
"waiting": 2560
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 127.71428571428572,
|
||||
"backlogHours": 126.22826086956522,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.24918672916041318,
|
||||
"qualityFactor": 0.2661699121267484,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 34,
|
||||
"recentSuccessRate": 0.18681318681318682,
|
||||
"recentTerminal": 182,
|
||||
"recentWilsonLowerBound": 0.1368763435750513,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.32394274790853717,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.19021739130434784,
|
||||
"recentTerminal": 184,
|
||||
"recentWilsonLowerBound": 0.14006970590718926,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.3460208857647729,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 30.333333333333332,
|
||||
"waiting": 3874
|
||||
"throughputPerHour": 30.666666666666668,
|
||||
"waiting": 3871
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2437.7368421052633,
|
||||
"backlogHours": 2573.1666666666665,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.4015731172683705,
|
||||
"queueFactor": 0.8555457178201032,
|
||||
"queueWeight": 0.8555457178201032,
|
||||
"recentSuccess": 11,
|
||||
"recentSuccessRate": 0.2894736842105263,
|
||||
"recentTerminal": 38,
|
||||
"recentWilsonLowerBound": 0.1700310626365613,
|
||||
"qualityFactor": 0.3492655511714374,
|
||||
"queueFactor": 0.8503069596278054,
|
||||
"queueWeight": 0.8503069596278054,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.2777777777777778,
|
||||
"recentTerminal": 36,
|
||||
"recentWilsonLowerBound": 0.15848170025813796,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.3435641608706246,
|
||||
"selectionWeight": 0.29698292891931466,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.333333333333333,
|
||||
"throughputPerHour": 6.0,
|
||||
"waiting": 15439
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 853.3246753246752,
|
||||
"backlogHours": 876.08,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.42725683886644744,
|
||||
"queueFactor": 1.0014380750691798,
|
||||
"queueWeight": 1.0014380750691798,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.2597402597402597,
|
||||
"recentTerminal": 77,
|
||||
"recentWilsonLowerBound": 0.17489066479540774,
|
||||
"qualityFactor": 0.4002061750535524,
|
||||
"queueFactor": 0.9994575576267849,
|
||||
"queueWeight": 0.9994575576267849,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.25333333333333335,
|
||||
"recentTerminal": 75,
|
||||
"recentWilsonLowerBound": 0.1685991964794815,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.42787126627455785,
|
||||
"selectionWeight": 0.399989086266181,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.833333333333334,
|
||||
"throughputPerHour": 12.5,
|
||||
"waiting": 10951
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 717.8526315789474,
|
||||
"backlogHours": 710.3125,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.6556818571583368,
|
||||
"queueFactor": 1.0277463676383123,
|
||||
"queueWeight": 1.0277463676383123,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.29473684210526313,
|
||||
"recentTerminal": 95,
|
||||
"recentWilsonLowerBound": 0.21247799848789717,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.6738746470208234,
|
||||
"qualityFactor": 0.713725661283317,
|
||||
"queueFactor": 1.0314032668151931,
|
||||
"queueWeight": 1.0314032668151931,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.3020833333333333,
|
||||
"recentTerminal": 96,
|
||||
"recentWilsonLowerBound": 0.2193102457465474,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.7361389786574472,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.833333333333334,
|
||||
"waiting": 11366
|
||||
"throughputPerHour": 16.0,
|
||||
"waiting": 11365
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2149.423728813559,
|
||||
"backlogHours": 2113.4,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 1.8089204513812898,
|
||||
"queueFactor": 0.8718523433903407,
|
||||
"queueWeight": 0.8718523433903407,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.4576271186440678,
|
||||
"recentTerminal": 59,
|
||||
"recentWilsonLowerBound": 0.33701102140242434,
|
||||
"qualityFactor": 1.5910079720760786,
|
||||
"queueFactor": 0.8757873457541018,
|
||||
"queueWeight": 0.8757873457541018,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.43333333333333335,
|
||||
"recentTerminal": 60,
|
||||
"recentWilsonLowerBound": 0.3157220039440064,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.5771115345434903,
|
||||
"selectionWeight": 1.393384648938125,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.833333333333334,
|
||||
"waiting": 21136
|
||||
"throughputPerHour": 10.0,
|
||||
"waiting": 21134
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 3180.8888888888887,
|
||||
"backlogHours": 2961.5172413793107,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.22893187505635637,
|
||||
"queueFactor": 0.8220703227443635,
|
||||
"queueWeight": 0.8220703227443635,
|
||||
"qualityFactor": 0.19707109144572443,
|
||||
"queueFactor": 0.8325662110192891,
|
||||
"queueWeight": 0.8325662110192891,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.25925925925925924,
|
||||
"recentTerminal": 27,
|
||||
"recentWilsonLowerBound": 0.13170208422866778,
|
||||
"recentSuccessRate": 0.2413793103448276,
|
||||
"recentTerminal": 29,
|
||||
"recentWilsonLowerBound": 0.12218268185062132,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.1881981004140512,
|
||||
"selectionWeight": 0.16407473190640262,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 4.5,
|
||||
"throughputPerHour": 4.833333333333333,
|
||||
"waiting": 14314
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -690,15 +690,15 @@
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 2.039735030278724,
|
||||
"queueFactor": 0.9985776072563051,
|
||||
"queueWeight": 0.9985776072563051,
|
||||
"qualityFactor": 2.070966142008892,
|
||||
"queueFactor": 1.0005447076646292,
|
||||
"queueWeight": 1.0005447076646292,
|
||||
"recentSuccess": 34,
|
||||
"recentSuccessRate": 0.4657534246575342,
|
||||
"recentTerminal": 73,
|
||||
"recentWilsonLowerBound": 0.35591852872281665,
|
||||
"running": 16,
|
||||
"selectionWeight": 2.036833725972595,
|
||||
"selectionWeight": 2.072094213139632,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.166666666666666,
|
||||
@@ -706,30 +706,30 @@
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 613.2,
|
||||
"backlogHours": 643.2592592592592,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 1.052327508126327,
|
||||
"queueWeight": 1.052327508126327,
|
||||
"recentSuccess": 42,
|
||||
"recentSuccessRate": 0.49411764705882355,
|
||||
"recentTerminal": 85,
|
||||
"recentWilsonLowerBound": 0.39040653316034707,
|
||||
"running": 6,
|
||||
"selectionWeight": 2.6308187703158175,
|
||||
"queueFactor": 1.0468585738565983,
|
||||
"queueWeight": 1.0468585738565983,
|
||||
"recentSuccess": 40,
|
||||
"recentSuccessRate": 0.49382716049382713,
|
||||
"recentTerminal": 81,
|
||||
"recentWilsonLowerBound": 0.38771930018551176,
|
||||
"running": 7,
|
||||
"selectionWeight": 2.6171464346414957,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.166666666666666,
|
||||
"waiting": 8687
|
||||
"throughputPerHour": 13.5,
|
||||
"waiting": 8684
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-12T05:13:24.404700+00:00",
|
||||
"queueAttemptedAt": "2026-09-12T05:24:52.423017+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-12T05:13:24.404700+00:00",
|
||||
"queueUpdatedAt": "2026-09-12T05:24:52.423017+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Iluvatar_mrv-100",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-12T04:58:37.438591+00:00",
|
||||
"lastSyncTime": "2026-09-12T04:58:37.211400+00:00",
|
||||
"generatedAt": "2026-09-12T05:24:46.168423+00:00",
|
||||
"lastSyncTime": "2026-09-12T05:24:45.924629+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1800,19 +1800,19 @@
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Iluvatar_bi-150|vllm|text-generation": {
|
||||
"attributableFailureCount": 20,
|
||||
"attributableFailureCount": 21,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 20,
|
||||
"decisionTotal": 21,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 10,
|
||||
"model_load": 5,
|
||||
"model_load": 6,
|
||||
"repository_structure": 1,
|
||||
"runtime_memory": 2
|
||||
},
|
||||
"failureCount": 27,
|
||||
"failureCount": 28,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -1822,7 +1822,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 27,
|
||||
"total": 28,
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
@@ -2377,30 +2377,30 @@
|
||||
"unresolvedFailureCount": 862
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 254,
|
||||
"decisionFailureRate": 0.9883,
|
||||
"decisionSuccessRate": 0.0117,
|
||||
"decisionTotal": 257,
|
||||
"attributableFailureCount": 255,
|
||||
"decisionFailureRate": 0.9884,
|
||||
"decisionSuccessRate": 0.0116,
|
||||
"decisionTotal": 258,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 195,
|
||||
"backend_operator": 33,
|
||||
"framework_architecture_unsupported": 174,
|
||||
"memory_capacity": 6,
|
||||
"model_load": 22,
|
||||
"model_load": 23,
|
||||
"platform_infrastructure": 1,
|
||||
"repository_structure": 7,
|
||||
"runtime_memory": 6,
|
||||
"tokenizer_compatibility": 6,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 474,
|
||||
"failureCount": 475,
|
||||
"failureRate": 0.9937,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0063,
|
||||
"total": 477,
|
||||
"total": 478,
|
||||
"unresolvedFailureCount": 219
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2505,7 +2505,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T04:58:37.432031+00:00",
|
||||
"generatedAt": "2026-09-12T05:24:46.164331+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2644,28 +2644,28 @@
|
||||
"unresolvedFailureCount": 27
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"attributableFailureCount": 25,
|
||||
"decisionFailureRate": 0.7576,
|
||||
"decisionSuccessRate": 0.2424,
|
||||
"decisionTotal": 33,
|
||||
"attributableFailureCount": 26,
|
||||
"decisionFailureRate": 0.7647,
|
||||
"decisionSuccessRate": 0.2353,
|
||||
"decisionTotal": 34,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"backend_operator": 5,
|
||||
"framework_architecture_unsupported": 11,
|
||||
"model_load": 6,
|
||||
"model_load": 7,
|
||||
"repository_structure": 1,
|
||||
"runtime_memory": 2,
|
||||
"参数/模板问题": 2,
|
||||
"验证失败": 30
|
||||
},
|
||||
"failureCount": 69,
|
||||
"failureRate": 0.8961,
|
||||
"failureCount": 70,
|
||||
"failureRate": 0.8974,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 8,
|
||||
"successRate": 0.1039,
|
||||
"total": 77,
|
||||
"successRate": 0.1026,
|
||||
"total": 78,
|
||||
"unresolvedFailureCount": 44
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
@@ -4415,24 +4415,24 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_bi-150|vllm|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
"consecutiveFailures": 7,
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 8,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 7,
|
||||
"decisionTotal": 8,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2,
|
||||
"backend_operator": 1,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"model_load": 2,
|
||||
"model_load": 3,
|
||||
"repository_structure": 1
|
||||
},
|
||||
"failureCount": 9,
|
||||
"failureCount": 10,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-12T04:41:36.246914+00:00",
|
||||
"lastTerminalAt": "2026-09-12T05:24:45.924629+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4440,7 +4440,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Iluvatar_bi-150",
|
||||
"taskType": "text-generation",
|
||||
"total": 9,
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
@@ -7241,19 +7241,19 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1687,
|
||||
"totalRecords": 1774,
|
||||
"terminalRecords": 1688,
|
||||
"totalRecords": 1775,
|
||||
"totals": {
|
||||
"attributableFailureCount": 459,
|
||||
"decisionFailureRate": 0.8913,
|
||||
"decisionSuccessRate": 0.1087,
|
||||
"decisionTotal": 515,
|
||||
"attributableFailureCount": 460,
|
||||
"decisionFailureRate": 0.8915,
|
||||
"decisionSuccessRate": 0.1085,
|
||||
"decisionTotal": 516,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 394,
|
||||
"backend_operator": 41,
|
||||
"framework_architecture_unsupported": 281,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 66,
|
||||
"model_load": 67,
|
||||
"platform_infrastructure": 4,
|
||||
"repository_structure": 7,
|
||||
"runtime_memory": 6,
|
||||
@@ -7261,21 +7261,20 @@
|
||||
"参数/模板问题": 101,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1631,
|
||||
"failureCount": 1632,
|
||||
"failureRate": 0.9668,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 56,
|
||||
"successRate": 0.0332,
|
||||
"total": 1687,
|
||||
"total": 1688,
|
||||
"unresolvedFailureCount": 1168
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 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 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。",
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -7284,6 +7283,7 @@
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 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 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。",
|
||||
"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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -7305,6 +7305,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1774,
|
||||
"summarizedRecords": 1775,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T05:24:45.924629+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Lite-Preview-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T05:21:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080073", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T04:58:37.211377+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T04:55:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080069", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-12T04:58:37.211400+00:00", "modelId": "AI-ModelScope/bitnet-b1.58-2B-4T-bf16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T04:55:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079952", "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": "2026-09-12T04:41:36.246914+00:00", "modelId": "LLM-Research/Phi-4-mini-flash-reasoning", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T04:35:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080064", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T14:58:38.614336+00:00", "modelId": "ModelCloud.AI/Qwen2.5-0.5B-Instruct-gptqmodel-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T14:37:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079085", "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", "failureUnsupportedModelTypes": ["zaya"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T03:01:10.207494+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950378091, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T14:03:45.031522+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4720262", "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", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-08T13:51:23.322093+00:00", "modelId": "mlx-community/Ornith-1.0-9B-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T13:35:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080063", "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": "2026-09-08T13:51:23.322073+00:00", "modelId": "amd/Qwen3-4B-awq-quant-onnx-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T13:31:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080049", "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": "c27d38efd8a8b5591ca3446e0f463706e91dfea9ba72cb0d617960d2aac4a357",
|
||||
".modelhub_state/architecture_history_backfill.json": "e3cb86500b69a86787976da61807953afac6713576b5b0d36f3d18d23a5ec444",
|
||||
".modelhub_state/market_intelligence.json": "905067957c205e921bcb287c54484609bd7416ea6d27037f05e298cf9e85d1ae",
|
||||
".modelhub_state/official_capabilities.json": "852386a30929b52413545889c8958fad396443a7c8cc5f847a9c97022c9514ae",
|
||||
".modelhub_state/outcome_checkpoint.json": "79ac47b0e40f922dc55a499156de6c37d5bb080165177f67b1153c156ae2bb80",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "49c23d9db03c4a0cc5131e41fea3b8f0f3e4dcdb59fc5bcbddc300de362aed05",
|
||||
".modelhub_state/architecture_history_backfill.json": "1a75589abb15be5ab2449aa71ef8b1cb6ba3882831a2835744dc7bfea6ab8aed",
|
||||
".modelhub_state/market_intelligence.json": "58e18b03ceb903aa9e7d7ccc430d7934aa02ef32898e87c1b02165d3c11800b4",
|
||||
".modelhub_state/official_capabilities.json": "a661a769c04a578f395ee5367b8c0f8c2cf1f36cc6297f09c060ebc1769fff8f",
|
||||
".modelhub_state/outcome_checkpoint.json": "ac70f9752426fb48ac87b51fd41fa713d5c644756cef4250a574f00189bbbf67",
|
||||
".modelhub_state/queue_cleanup_latest.json": "dbff8ecbdcba815a2302661742ce4689464c0250a7ef3678d448f0d7a5dc07da",
|
||||
".modelhub_state/recent_outcomes.jsonl": "abc1a7a783d437377381de807de50e3eaf2b378ca3348805c9634c567af9d6b4",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "670c227540038625f21440773562dee0cbd5ca3e6c5b4ca0a28b0d802beee809",
|
||||
".modelhub_state/recovery_intents.jsonl": "3e1cab91d9f54064416e83db09baad250fdd3bd9649e04f3b448f45bc51d70c3",
|
||||
".modelhub_state/recent_outcomes.jsonl": "b817f8236b8f532d9d5db1b72f9f8822c28790efde660bdfb0261201f85e0e09",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "edb0ca717a8cdb13ba0cdae9c3db82f15a7605fcef8d6e46f00bd3274b422cbe",
|
||||
".modelhub_state/recovery_intents.jsonl": "36f9c64f6b31f029ee61b887ddb6a5641edbde7a90a36de569c62911119bf8b3",
|
||||
".modelhub_state/routing_intelligence.json": "6d24ffe4cc3d16ae087ed7ad3d2070ebc65adb255a4b9c8f38d6858392a3664e",
|
||||
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
|
||||
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
|
||||
"ledger/submissions.jsonl": "9abf2a6c9d9d6fa7f53fa3d613fee8c7159979641411c2b94002ec2b88d34f29",
|
||||
"outcomes/submissions.jsonl": "2a1f4e15e4d43bfc432d85aaa9fcafeab327d5cda6e5269ddeb1f50c4e5c6fbb"
|
||||
},
|
||||
"generation": 6044,
|
||||
"generation": 6045,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-12T05:23:45.309910+00:00",
|
||||
"updatedAt": "2026-09-12T05:26:59.157154+00:00",
|
||||
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user