state: generation 5113 (cycle)
This commit is contained in:
@@ -1317,7 +1317,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T10:11:24.891154+00:00",
|
||||
"generatedAt": "2026-09-10T10:14:42.769074+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -11,7 +11,7 @@
|
||||
"1": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 363,
|
||||
"listingErrors": 364,
|
||||
"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": 1,
|
||||
"nextAccountIndex": 2,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-10T10:11:24.857553+00:00",
|
||||
"updatedAt": "2026-09-10T10:14:42.744818+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-10T09:55:31.606910+00:00",
|
||||
"communityAttemptedAt": "2026-09-10T10:12:32.703769+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-10T09:55:31.606910+00:00",
|
||||
"communityUpdatedAt": "2026-09-10T10:12:32.703769+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-10T06:33:41.338309+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-10T10:09:53.593835+00:00",
|
||||
"generatedAt": "2026-09-10T10:12:32.703769+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 956.0,
|
||||
"backlogHours": 930.8344370860926,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.3379014737982085,
|
||||
"queueFactor": 0.9700376037311051,
|
||||
"queueWeight": 0.9700376037311051,
|
||||
"recentSuccess": 57,
|
||||
"recentSuccessRate": 0.3877551020408163,
|
||||
"recentTerminal": 147,
|
||||
"recentWilsonLowerBound": 0.31280467369206544,
|
||||
"running": 9,
|
||||
"selectionWeight": 1.297814739671528,
|
||||
"qualityFactor": 1.3622584203031827,
|
||||
"queueFactor": 0.9709110247350885,
|
||||
"queueWeight": 0.9709110247350885,
|
||||
"recentSuccess": 61,
|
||||
"recentSuccessRate": 0.40397350993377484,
|
||||
"recentTerminal": 151,
|
||||
"recentWilsonLowerBound": 0.32902953213007213,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.322631718810566,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.5,
|
||||
"waiting": 23422
|
||||
"throughputPerHour": 25.166666666666668,
|
||||
"waiting": 23426
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 986.7305389221557,
|
||||
"backlogHours": 993.0722891566264,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.7137066648013559,
|
||||
"queueFactor": 0.9654448462060424,
|
||||
"queueWeight": 0.9654448462060424,
|
||||
"recentSuccess": 50,
|
||||
"recentSuccessRate": 0.2994011976047904,
|
||||
"recentTerminal": 167,
|
||||
"recentWilsonLowerBound": 0.23508547032043003,
|
||||
"qualityFactor": 0.693434957788819,
|
||||
"queueFactor": 0.9615307316063288,
|
||||
"queueWeight": 0.9615307316063288,
|
||||
"recentSuccess": 51,
|
||||
"recentSuccessRate": 0.3072289156626506,
|
||||
"recentTerminal": 166,
|
||||
"recentWilsonLowerBound": 0.24206818397022814,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.6890444212353726,
|
||||
"selectionWeight": 0.6667590222840869,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 27.833333333333332,
|
||||
"waiting": 27464
|
||||
"throughputPerHour": 27.666666666666668,
|
||||
"waiting": 27475
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 138.64948453608247,
|
||||
"backlogHours": 137.26530612244898,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.2863889925797376,
|
||||
"queueFactor": 1.2958941073583854,
|
||||
"queueWeight": 1.2958941073583854,
|
||||
"qualityFactor": 0.2549279245705025,
|
||||
"queueFactor": 1.293826915137055,
|
||||
"queueWeight": 1.293826915137055,
|
||||
"recentSuccess": 40,
|
||||
"recentSuccessRate": 0.20618556701030927,
|
||||
"recentTerminal": 194,
|
||||
"recentWilsonLowerBound": 0.1552278646105189,
|
||||
"running": 10,
|
||||
"selectionWeight": 0.37112980789638633,
|
||||
"recentSuccessRate": 0.20408163265306123,
|
||||
"recentTerminal": 196,
|
||||
"recentWilsonLowerBound": 0.1536022459546319,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.32983261022934507,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 32.333333333333336,
|
||||
"waiting": 4483
|
||||
"throughputPerHour": 32.666666666666664,
|
||||
"waiting": 4484
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 955.5505617977527,
|
||||
"backlogHours": 966.2045454545455,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.09967539621214949,
|
||||
"queueFactor": 0.9701060278705724,
|
||||
"queueWeight": 0.9701060278705724,
|
||||
"qualityFactor": 0.09315158333660953,
|
||||
"queueFactor": 0.9654947962913524,
|
||||
"queueWeight": 0.9654947962913524,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.15730337078651685,
|
||||
"recentTerminal": 89,
|
||||
"recentWilsonLowerBound": 0.09607722097921383,
|
||||
"recentSuccessRate": 0.1590909090909091,
|
||||
"recentTerminal": 88,
|
||||
"recentWilsonLowerBound": 0.09719813761632919,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.09669570269579385,
|
||||
"selectionWeight": 0.08993736897779675,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.833333333333334,
|
||||
"waiting": 14174
|
||||
"throughputPerHour": 14.666666666666666,
|
||||
"waiting": 14171
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 520.4117647058823,
|
||||
"backlogHours": 536.1212121212121,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.4403917754341886,
|
||||
"queueFactor": 1.0626865601649533,
|
||||
"queueWeight": 1.0626865601649533,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.2647058823529412,
|
||||
"recentTerminal": 102,
|
||||
"recentWilsonLowerBound": 0.188762815237447,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.4679984209610945,
|
||||
"qualityFactor": 0.38830228614877066,
|
||||
"queueFactor": 1.0546803392861905,
|
||||
"queueWeight": 1.0546803392861905,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.26262626262626265,
|
||||
"recentTerminal": 99,
|
||||
"recentWilsonLowerBound": 0.18598028163201125,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.4095347869009889,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.0,
|
||||
"waiting": 8847
|
||||
"throughputPerHour": 16.5,
|
||||
"waiting": 8846
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 38.61081081081081,
|
||||
"backlogHours": 42.30357142857143,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -539,197 +539,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.06486486486486487,
|
||||
"recentTerminal": 370,
|
||||
"recentWilsonLowerBound": 0.04397275967103884,
|
||||
"running": 3,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.06845238095238096,
|
||||
"recentTerminal": 336,
|
||||
"recentWilsonLowerBound": 0.04604288356283223,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 61.666666666666664,
|
||||
"waiting": 2381
|
||||
"throughputPerHour": 56.0,
|
||||
"waiting": 2369
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 55.07398568019094,
|
||||
"backlogHours": 66.5014409221902,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.11960257069739168,
|
||||
"qualityFactor": 0.15157046184085676,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 56,
|
||||
"recentSuccessRate": 0.13365155131264916,
|
||||
"recentTerminal": 419,
|
||||
"recentWilsonLowerBound": 0.10437557033723704,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.15548334190660917,
|
||||
"recentSuccess": 54,
|
||||
"recentSuccessRate": 0.15561959654178675,
|
||||
"recentTerminal": 347,
|
||||
"recentWilsonLowerBound": 0.1212718249457395,
|
||||
"running": 3,
|
||||
"selectionWeight": 0.1970416003931138,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 69.83333333333333,
|
||||
"throughputPerHour": 57.833333333333336,
|
||||
"waiting": 3846
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2444.684210526316,
|
||||
"backlogHours": 2266.0975609756097,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.19365337598774468,
|
||||
"queueFactor": 0.842604625418323,
|
||||
"queueWeight": 0.842604625418323,
|
||||
"qualityFactor": 0.14817793392123452,
|
||||
"queueFactor": 0.8496078341648329,
|
||||
"queueWeight": 0.8496078341648329,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.23684210526315788,
|
||||
"recentTerminal": 38,
|
||||
"recentWilsonLowerBound": 0.12993561496969508,
|
||||
"recentSuccessRate": 0.21951219512195122,
|
||||
"recentTerminal": 41,
|
||||
"recentWilsonLowerBound": 0.12003040155386345,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.16317323033514727,
|
||||
"selectionWeight": 0.12589313350983977,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.333333333333333,
|
||||
"waiting": 15483
|
||||
"throughputPerHour": 6.833333333333333,
|
||||
"waiting": 15485
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 687.0315789473684,
|
||||
"backlogHours": 679.875,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.29857338266061356,
|
||||
"queueFactor": 1.019320477556272,
|
||||
"queueWeight": 1.019320477556272,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.23157894736842105,
|
||||
"recentTerminal": 95,
|
||||
"recentWilsonLowerBound": 0.15819566451338007,
|
||||
"qualityFactor": 0.23409017310750907,
|
||||
"queueFactor": 1.0177613119918634,
|
||||
"queueWeight": 1.0177613119918634,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.21875,
|
||||
"recentTerminal": 96,
|
||||
"recentWilsonLowerBound": 0.1477623624877523,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.3043419629992082,
|
||||
"selectionWeight": 0.23824792170630085,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.833333333333334,
|
||||
"throughputPerHour": 16.0,
|
||||
"waiting": 10878
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 641.6074766355141,
|
||||
"backlogHours": 647.6037735849056,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.47750567640825037,
|
||||
"queueFactor": 1.0298330884026514,
|
||||
"queueWeight": 1.0298330884026514,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.27102803738317754,
|
||||
"recentTerminal": 107,
|
||||
"recentWilsonLowerBound": 0.19583435081989597,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.4917511454653056,
|
||||
"qualityFactor": 0.48636140141075157,
|
||||
"queueFactor": 1.0252125012380666,
|
||||
"queueWeight": 1.0252125012380666,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.2830188679245283,
|
||||
"recentTerminal": 106,
|
||||
"recentWilsonLowerBound": 0.20602338401321438,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.498623788845968,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.833333333333332,
|
||||
"waiting": 11442
|
||||
"throughputPerHour": 17.666666666666668,
|
||||
"waiting": 11441
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1687.1052631578948,
|
||||
"backlogHours": 1646.7692307692307,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 1.1539386803872704,
|
||||
"queueFactor": 0.8908117296553819,
|
||||
"queueWeight": 0.8908117296553819,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.39473684210526316,
|
||||
"recentTerminal": 76,
|
||||
"recentWilsonLowerBound": 0.2924641219449393,
|
||||
"running": 6,
|
||||
"selectionWeight": 1.0279421117920333,
|
||||
"qualityFactor": 1.1764880394075659,
|
||||
"queueFactor": 0.8912825161918063,
|
||||
"queueWeight": 0.8912825161918063,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.41025641025641024,
|
||||
"recentTerminal": 78,
|
||||
"recentWilsonLowerBound": 0.3078173313444522,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.0485832200327403,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.666666666666666,
|
||||
"waiting": 21370
|
||||
"throughputPerHour": 13.0,
|
||||
"waiting": 21408
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 6520.153846153847,
|
||||
"backlogHours": 6519.2307692307695,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.1450186480466729,
|
||||
"queueFactor": 0.7273083564883461,
|
||||
"queueWeight": 0.7273083564883461,
|
||||
"qualityFactor": 1.0431152775592887,
|
||||
"queueFactor": 0.7250715180106461,
|
||||
"queueWeight": 0.7250715180106461,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.5384615384615384,
|
||||
"recentTerminal": 13,
|
||||
"recentWilsonLowerBound": 0.29143432431832045,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.8327816310593337,
|
||||
"selectionWeight": 0.7563331777600099,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 2.1666666666666665,
|
||||
"waiting": 14127
|
||||
"waiting": 14125
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 874.0,
|
||||
"backlogHours": 849.2112676056338,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.47924957412798147,
|
||||
"queueFactor": 0.9831743484860425,
|
||||
"queueWeight": 0.9831743484860425,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.2898550724637681,
|
||||
"recentTerminal": 69,
|
||||
"recentWilsonLowerBound": 0.19615912140759176,
|
||||
"qualityFactor": 0.4673723835663126,
|
||||
"queueFactor": 0.9843690188958909,
|
||||
"queueWeight": 0.9843690188958909,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.29577464788732394,
|
||||
"recentTerminal": 71,
|
||||
"recentWilsonLowerBound": 0.20232738733765723,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.4711858878054915,
|
||||
"selectionWeight": 0.4600668946702052,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.5,
|
||||
"waiting": 10051
|
||||
"throughputPerHour": 11.833333333333334,
|
||||
"waiting": 10049
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 491.60377358490564,
|
||||
"backlogHours": 501.00000000000006,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 1.0718030110198982,
|
||||
"queueWeight": 1.0718030110198982,
|
||||
"recentSuccess": 54,
|
||||
"recentSuccessRate": 0.5094339622641509,
|
||||
"recentTerminal": 106,
|
||||
"recentWilsonLowerBound": 0.4156133994571823,
|
||||
"queueFactor": 1.0654538424606883,
|
||||
"queueWeight": 1.0654538424606883,
|
||||
"recentSuccess": 55,
|
||||
"recentSuccessRate": 0.5288461538461539,
|
||||
"recentTerminal": 104,
|
||||
"recentWilsonLowerBound": 0.4336003819768207,
|
||||
"running": 6,
|
||||
"selectionWeight": 2.6795075275497453,
|
||||
"selectionWeight": 2.663634606151721,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.666666666666668,
|
||||
"waiting": 8685
|
||||
"throughputPerHour": 17.333333333333332,
|
||||
"waiting": 8684
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-10T10:01:19.100487+00:00",
|
||||
"queueAttemptedAt": "2026-09-10T10:12:32.703769+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-10T10:01:19.100487+00:00",
|
||||
"queueUpdatedAt": "2026-09-10T10:12:32.703769+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Iluvatar_mrv-100",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-10T09:47:33.599443+00:00",
|
||||
"lastSyncTime": "2026-09-10T09:47:33.262404+00:00",
|
||||
"generatedAt": "2026-09-10T10:12:25.956598+00:00",
|
||||
"lastSyncTime": "2026-09-10T10:12:25.704447+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2147,12 +2147,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 44,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 51,
|
||||
"ambiguous_runtime": 52,
|
||||
"framework_architecture_unsupported": 38,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 5
|
||||
},
|
||||
"failureCount": 95,
|
||||
"failureCount": 96,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2162,8 +2162,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 95,
|
||||
"unresolvedFailureCount": 51
|
||||
"total": 96,
|
||||
"unresolvedFailureCount": 52
|
||||
},
|
||||
"hygon_k100-ai|llamacpp|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -2325,7 +2325,7 @@
|
||||
"decisionSuccessRate": 0.0042,
|
||||
"decisionTotal": 236,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 157,
|
||||
"ambiguous_runtime": 158,
|
||||
"backend_operator": 29,
|
||||
"framework_architecture_unsupported": 169,
|
||||
"memory_capacity": 6,
|
||||
@@ -2336,15 +2336,15 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 21
|
||||
},
|
||||
"failureCount": 414,
|
||||
"failureCount": 415,
|
||||
"failureRate": 0.9976,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0024,
|
||||
"total": 415,
|
||||
"unresolvedFailureCount": 178
|
||||
"total": 416,
|
||||
"unresolvedFailureCount": 179
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2447,7 +2447,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-10T09:47:33.595423+00:00",
|
||||
"generatedAt": "2026-09-10T10:12:25.950299+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2731,22 +2731,22 @@
|
||||
"decisionSuccessRate": 0.2167,
|
||||
"decisionTotal": 60,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 52,
|
||||
"ambiguous_runtime": 53,
|
||||
"framework_architecture_unsupported": 40,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 6,
|
||||
"参数/模板问题": 13,
|
||||
"验证失败": 130
|
||||
},
|
||||
"failureCount": 242,
|
||||
"failureRate": 0.949,
|
||||
"failureCount": 243,
|
||||
"failureRate": 0.9492,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 13,
|
||||
"successRate": 0.051,
|
||||
"total": 255,
|
||||
"unresolvedFailureCount": 195
|
||||
"successRate": 0.0508,
|
||||
"total": 256,
|
||||
"unresolvedFailureCount": 196
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"attributableFailureCount": 38,
|
||||
@@ -4504,18 +4504,18 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 9,
|
||||
"consecutiveFailures": 9,
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 8,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 9,
|
||||
"decisionTotal": 8,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 8
|
||||
"tokenizer_compatibility": 7
|
||||
},
|
||||
"failureCount": 10,
|
||||
"failureCount": 9,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-09-08T18:27:21+00:00",
|
||||
@@ -4527,7 +4527,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 10,
|
||||
"total": 9,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -4605,21 +4605,20 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Vastai_va16|vllm|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,
|
||||
"framework_architecture_unsupported": 1
|
||||
"ambiguous_runtime": 20
|
||||
},
|
||||
"failureCount": 20,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T09:47:33.262382+00:00",
|
||||
"lastTerminalAt": "2026-09-10T10:12:25.704447+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4628,7 +4627,7 @@
|
||||
"targetGpu": "Vastai_va16",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 19
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"hygon_k100-ai|llamacpp|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -7056,15 +7055,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1553,
|
||||
"totalRecords": 1640,
|
||||
"terminalRecords": 1554,
|
||||
"totalRecords": 1641,
|
||||
"totals": {
|
||||
"attributableFailureCount": 405,
|
||||
"decisionFailureRate": 0.8882,
|
||||
"decisionSuccessRate": 0.1118,
|
||||
"decisionTotal": 456,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 327,
|
||||
"ambiguous_runtime": 328,
|
||||
"backend_operator": 34,
|
||||
"framework_architecture_unsupported": 271,
|
||||
"memory_capacity": 11,
|
||||
@@ -7076,21 +7075,21 @@
|
||||
"参数/模板问题": 95,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1502,
|
||||
"failureCount": 1503,
|
||||
"failureRate": 0.9672,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 51,
|
||||
"successRate": 0.0328,
|
||||
"total": 1553,
|
||||
"unresolvedFailureCount": 1095
|
||||
"total": 1554,
|
||||
"unresolvedFailureCount": 1096
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_mrv-100 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 Iluvatar_bi-150 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 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。",
|
||||
@@ -7098,7 +7097,7 @@
|
||||
"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 Mthreads_s4000 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 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-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 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。",
|
||||
@@ -7119,6 +7118,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1640,
|
||||
"summarizedRecords": 1641,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"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": "2026-09-10T10:12:25.704447+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:11:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477783", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T09:47:33.262404+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:47:22+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493608", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"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": "2026-09-10T09:47:33.262382+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:43:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477720", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-10T09:29:56.132283+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:27:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532020", "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": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-09-07T20:52:41.332062+00:00", "modelId": "kurakurai/Luth-LFM2-700M-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:51:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "3987175", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-07T20:52:41.332106+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:51:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4478705", "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_mtp"], "framework": "vllm", "lastSyncTime": "2026-09-07T20:52:41.332123+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:41:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4585069", "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": "2026-09-07T20:39:52.300695+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-07T20:37:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458004", "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": "062b91b8b9eb8525a00ec1bf0fe1c474a08335ba702f720e1bd923b0ca3c7a60",
|
||||
".modelhub_state/architecture_history_backfill.json": "2dc249bf7849dafb9c23c0a0bbf3092d64a91b93385f39de89eeeb3dd3751966",
|
||||
".modelhub_state/market_intelligence.json": "eec7bd2b99408f6f0161f1d749eb7b2ce49a2b8c2170cad9f34f8df4a43e673e",
|
||||
".modelhub_state/official_capabilities.json": "6a53bc95e873a6d91a242ebebf10d59921589ec6966a385a155c6a922861da26",
|
||||
".modelhub_state/outcome_checkpoint.json": "a00336937dc7191e2c0d2cf88591047d307db2e2e403cad9a516b0a0c7e87db2",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "ac159017684226a8e0f6ff11d203326b33f682e210e2c49f7f6ab448ea52c6ed",
|
||||
".modelhub_state/architecture_history_backfill.json": "97940270489da928fbd421043b0eaa98e94cc4aa9d4c91faa0bce1da67eb5edf",
|
||||
".modelhub_state/market_intelligence.json": "190d1e007b8c3a4e0f1eaf775ca1ebc346383e8b73b44aaeb9de76f0f7b2f791",
|
||||
".modelhub_state/official_capabilities.json": "863967d1659e9853aec2ec2ca871d49561d0c75305c94793c668f5d93c5d008d",
|
||||
".modelhub_state/outcome_checkpoint.json": "904a8312bd83cdeb54fb4211e6f66fc94ebecab6196b38521881cbed723cf5d1",
|
||||
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
|
||||
".modelhub_state/recent_outcomes.jsonl": "fecfd285d8d66afeb4983b5ae2c15cc5c9bf80ecfc51b35a14589a5800c201f9",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "e1d523bf79532f80ce40bcd35c6444bb9531957ada892398793d354f780e4eab",
|
||||
".modelhub_state/recovery_intents.jsonl": "5e87a84cfcd11ace451b7c7d4c91bc292ba6b9b78a118b4e234ee94053a567ab",
|
||||
".modelhub_state/recent_outcomes.jsonl": "ad7d4dad969130d9fe9de98048755291976791298e5a8527f6c8b3ee38631c76",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "266c14c3ca3fbe9d121a7bfe3817d45fb705d0d419e40b922367e7252b7a6a12",
|
||||
".modelhub_state/recovery_intents.jsonl": "f93b35b075682d03f0b37cc12615110c69ffbf1950c11f5a88d10acb0de8a484",
|
||||
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
|
||||
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
|
||||
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
||||
"ledger/submissions.jsonl": "76cbabbced897a94b01593ff4cb86c58b9b0394b6c8fa89dd11a295e4678f70f",
|
||||
"outcomes/submissions.jsonl": "7e7dceeb82e33a52f232d56ceba319292e0b24b25bc8ec08e03fa95367ce1163"
|
||||
},
|
||||
"generation": 5112,
|
||||
"generation": 5113,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-10T10:11:24.990386+00:00",
|
||||
"updatedAt": "2026-09-10T10:14:43.357073+00:00",
|
||||
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user