state: generation 19199 (cycle)
This commit is contained in:
@@ -3341,7 +3341,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-01T11:20:48.336767+00:00",
|
||||
"generatedAt": "2026-10-01T11:31:46.547588+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 168,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,121 +434,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-01T11:28:52.356496+00:00",
|
||||
"generatedAt": "2026-10-01T11:33:25.484466+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1361.3949579831933,
|
||||
"backlogHours": 1285.7619047619048,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9972328602905483,
|
||||
"queueWeight": 0.9972328602905483,
|
||||
"recentSuccess": 55,
|
||||
"recentSuccessRate": 0.46218487394957986,
|
||||
"recentTerminal": 119,
|
||||
"recentWilsonLowerBound": 0.3751921938244886,
|
||||
"queueFactor": 0.9989424120286321,
|
||||
"queueWeight": 0.9989424120286321,
|
||||
"recentSuccess": 56,
|
||||
"recentSuccessRate": 0.4444444444444444,
|
||||
"recentTerminal": 126,
|
||||
"recentWilsonLowerBound": 0.3606007929403117,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.4930821507263707,
|
||||
"selectionWeight": 2.4973560300715802,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.833333333333332,
|
||||
"throughputPerHour": 21.0,
|
||||
"waiting": 27001
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1480.8813559322034,
|
||||
"backlogHours": 1444.2148760330579,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.603782860161973,
|
||||
"queueFactor": 0.9847277157434504,
|
||||
"queueWeight": 0.9847277157434504,
|
||||
"recentSuccess": 46,
|
||||
"recentSuccessRate": 0.3898305084745763,
|
||||
"recentTerminal": 118,
|
||||
"recentWilsonLowerBound": 0.30663375206175597,
|
||||
"qualityFactor": 1.8438193010330917,
|
||||
"queueFactor": 0.9816795936522414,
|
||||
"queueWeight": 0.9816795936522414,
|
||||
"recentSuccess": 48,
|
||||
"recentSuccessRate": 0.39669421487603307,
|
||||
"recentTerminal": 121,
|
||||
"recentWilsonLowerBound": 0.3139973093025401,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.5792894324357973,
|
||||
"selectionWeight": 1.8100397822063252,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.666666666666668,
|
||||
"waiting": 29124
|
||||
"throughputPerHour": 20.166666666666668,
|
||||
"waiting": 29125
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 121.62244897959185,
|
||||
"backlogHours": 127.37967914438502,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.196524901678243,
|
||||
"qualityFactor": 0.25828954281928007,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.16326530612244897,
|
||||
"recentTerminal": 196,
|
||||
"recentWilsonLowerBound": 0.1180859283038741,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.2554823721817159,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.17647058823529413,
|
||||
"recentTerminal": 187,
|
||||
"recentWilsonLowerBound": 0.12850519475405223,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.3357764056650641,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 32.666666666666664,
|
||||
"waiting": 3973
|
||||
"throughputPerHour": 31.166666666666668,
|
||||
"waiting": 3970
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 2310.9,
|
||||
"backlogHours": 2201.285714285714,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.632218512376253,
|
||||
"queueFactor": 0.9211429413787131,
|
||||
"queueWeight": 0.9211429413787131,
|
||||
"qualityFactor": 0.6156009234584586,
|
||||
"queueFactor": 0.9215376285328026,
|
||||
"queueWeight": 0.9215376285328026,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.325,
|
||||
"recentTerminal": 40,
|
||||
"recentWilsonLowerBound": 0.20084316962661727,
|
||||
"recentSuccessRate": 0.30952380952380953,
|
||||
"recentTerminal": 42,
|
||||
"recentWilsonLowerBound": 0.1907092651972273,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.5823636200843361,
|
||||
"selectionWeight": 0.5672994151265113,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.666666666666667,
|
||||
"waiting": 15406
|
||||
"throughputPerHour": 7.0,
|
||||
"waiting": 15409
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 468.4285714285714,
|
||||
"backlogHours": 499.42857142857144,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.17279917910114562,
|
||||
"queueFactor": 1.170301320020962,
|
||||
"queueWeight": 1.170301320020962,
|
||||
"qualityFactor": 0.21817799964948006,
|
||||
"queueFactor": 1.1511807741776594,
|
||||
"queueWeight": 1.1511807741776594,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.16964285714285715,
|
||||
"recentTerminal": 112,
|
||||
"recentWilsonLowerBound": 0.11137815153115602,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.20222710740060934,
|
||||
"recentSuccessRate": 0.18095238095238095,
|
||||
"recentTerminal": 105,
|
||||
"recentWilsonLowerBound": 0.11901573432473685,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.2511623185450216,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 18.666666666666668,
|
||||
"waiting": 8744
|
||||
"throughputPerHour": 17.5,
|
||||
"waiting": 8740
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 40.900621118012424,
|
||||
"backlogHours": 40.84472049689441,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -557,197 +557,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.015527950310559006,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.018633540372670808,
|
||||
"recentTerminal": 322,
|
||||
"recentWilsonLowerBound": 0.0066502778460104045,
|
||||
"running": 24,
|
||||
"recentWilsonLowerBound": 0.00856708840594813,
|
||||
"running": 26,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 53.666666666666664,
|
||||
"waiting": 2195
|
||||
"waiting": 2192
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 171.85714285714286,
|
||||
"backlogHours": 167.3903743315508,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.1961014722889785,
|
||||
"qualityFactor": 0.21938300776731717,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.16483516483516483,
|
||||
"recentTerminal": 182,
|
||||
"recentWilsonLowerBound": 0.11797021207184955,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.25493191397567205,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.1657754010695187,
|
||||
"recentTerminal": 187,
|
||||
"recentWilsonLowerBound": 0.11931407186804938,
|
||||
"running": 3,
|
||||
"selectionWeight": 0.28519791009751233,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 30.333333333333332,
|
||||
"waiting": 5213
|
||||
"throughputPerHour": 31.166666666666668,
|
||||
"waiting": 5217
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2194.046511627907,
|
||||
"backlogHours": 2194.186046511628,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.8052148190778137,
|
||||
"queueFactor": 0.9283405628293592,
|
||||
"queueWeight": 0.9283405628293592,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.3488372093023256,
|
||||
"qualityFactor": 0.7211388229260738,
|
||||
"queueFactor": 0.9219842838049899,
|
||||
"queueWeight": 0.9219842838049899,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.32558139534883723,
|
||||
"recentTerminal": 43,
|
||||
"recentWilsonLowerBound": 0.22418398748963103,
|
||||
"recentWilsonLowerBound": 0.20493115181779817,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.7475135783412382,
|
||||
"selectionWeight": 0.6648786611794696,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.166666666666667,
|
||||
"waiting": 15724
|
||||
"waiting": 15725
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 328.53333333333336,
|
||||
"backlogHours": 335.90909090909093,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.41988142625081604,
|
||||
"queueFactor": 1.2342617927308808,
|
||||
"queueWeight": 1.2342617927308808,
|
||||
"qualityFactor": 0.48218239409119706,
|
||||
"queueFactor": 1.2217469733310458,
|
||||
"queueWeight": 1.2217469733310458,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.22962962962962963,
|
||||
"recentTerminal": 135,
|
||||
"recentWilsonLowerBound": 0.16675002584299897,
|
||||
"recentSuccessRate": 0.23484848484848486,
|
||||
"recentTerminal": 132,
|
||||
"recentWilsonLowerBound": 0.17066718052506505,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.5182436018987313,
|
||||
"selectionWeight": 0.5891048805744376,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.5,
|
||||
"waiting": 7392
|
||||
"throughputPerHour": 22.0,
|
||||
"waiting": 7390
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 710.1136363636364,
|
||||
"backlogHours": 735.1058823529412,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 1.0269244685245595,
|
||||
"queueFactor": 1.0994994678649557,
|
||||
"queueWeight": 1.0994994678649557,
|
||||
"qualityFactor": 1.21452202953259,
|
||||
"queueFactor": 1.086330694386916,
|
||||
"queueWeight": 1.086330694386916,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.3409090909090909,
|
||||
"recentTerminal": 88,
|
||||
"recentWilsonLowerBound": 0.2503898646649058,
|
||||
"recentSuccessRate": 0.35294117647058826,
|
||||
"recentTerminal": 85,
|
||||
"recentWilsonLowerBound": 0.2597233193313943,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.1291029066802556,
|
||||
"selectionWeight": 1.319372559690345,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.666666666666666,
|
||||
"waiting": 10415
|
||||
"throughputPerHour": 14.166666666666666,
|
||||
"waiting": 10414
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2314.842105263158,
|
||||
"backlogHours": 2399.018181818182,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 1.9321196466130865,
|
||||
"queueFactor": 0.9209074691613414,
|
||||
"queueWeight": 0.9209074691613414,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.45614035087719296,
|
||||
"recentTerminal": 57,
|
||||
"recentWilsonLowerBound": 0.33372399504811395,
|
||||
"qualityFactor": 1.8403986026166008,
|
||||
"queueFactor": 0.9097236905568095,
|
||||
"queueWeight": 0.9097236905568095,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.43636363636363634,
|
||||
"recentTerminal": 55,
|
||||
"recentWilsonLowerBound": 0.31373238636001305,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.7793034138793629,
|
||||
"selectionWeight": 1.674254208867969,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.5,
|
||||
"throughputPerHour": 9.166666666666666,
|
||||
"waiting": 21991
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 3494.4827586206898,
|
||||
"backlogHours": 3379.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.318117518467474,
|
||||
"queueFactor": 0.8657385692693731,
|
||||
"queueWeight": 0.8657385692693731,
|
||||
"qualityFactor": 0.32087594583868173,
|
||||
"queueFactor": 0.8641642716056375,
|
||||
"queueWeight": 0.8641642716056375,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.27586206896551724,
|
||||
"recentTerminal": 29,
|
||||
"recentWilsonLowerBound": 0.1469858133850274,
|
||||
"recentSuccessRate": 0.26666666666666666,
|
||||
"recentTerminal": 30,
|
||||
"recentWilsonLowerBound": 0.14182495553910618,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.2754066052975543,
|
||||
"selectionWeight": 0.2772895280114544,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 4.833333333333333,
|
||||
"waiting": 16890
|
||||
"throughputPerHour": 5.0,
|
||||
"waiting": 16895
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1589.5862068965519,
|
||||
"backlogHours": 1562.9491525423728,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.16592348170252316,
|
||||
"queueFactor": 0.9743199350976998,
|
||||
"queueWeight": 0.9743199350976998,
|
||||
"qualityFactor": 0.17414984739163408,
|
||||
"queueFactor": 0.9701140803813901,
|
||||
"queueWeight": 0.9701140803813901,
|
||||
"recentSuccess": 11,
|
||||
"recentSuccessRate": 0.1896551724137931,
|
||||
"recentTerminal": 58,
|
||||
"recentWilsonLowerBound": 0.10934140042567435,
|
||||
"recentSuccessRate": 0.1864406779661017,
|
||||
"recentTerminal": 59,
|
||||
"recentWilsonLowerBound": 0.10742612239043586,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.16166255592358675,
|
||||
"selectionWeight": 0.16894521905089452,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 9.666666666666666,
|
||||
"waiting": 15366
|
||||
"throughputPerHour": 9.833333333333334,
|
||||
"waiting": 15369
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1311.5581395348836,
|
||||
"backlogHours": 1267.685393258427,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.900332715956737,
|
||||
"queueFactor": 1.0028271177482153,
|
||||
"queueWeight": 1.0028271177482153,
|
||||
"qualityFactor": 0.9075656811036013,
|
||||
"queueFactor": 1.001066233206901,
|
||||
"queueWeight": 1.001066233206901,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.32558139534883723,
|
||||
"recentTerminal": 86,
|
||||
"recentWilsonLowerBound": 0.23585553745183332,
|
||||
"recentSuccessRate": 0.3146067415730337,
|
||||
"recentTerminal": 89,
|
||||
"recentWilsonLowerBound": 0.22750896837627055,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.9028780625573172,
|
||||
"selectionWeight": 0.9085333577702376,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.333333333333334,
|
||||
"waiting": 18799
|
||||
"throughputPerHour": 14.833333333333334,
|
||||
"waiting": 18804
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-10-01T11:19:43.366906+00:00",
|
||||
"queueAttemptedAt": "2026-10-01T11:33:25.484466+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-10-01T11:19:43.366906+00:00",
|
||||
"queueUpdatedAt": "2026-10-01T11:33:25.484466+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Cambricon_mlu-370-x4",
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-10-01T11:28:52.356496+00:00",
|
||||
"catalogUpdatedAt": "2026-10-01T11:33:25.484466+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-10-01T11:28:52.356496+00:00",
|
||||
"generatedAt": "2026-10-01T11:33:25.484466+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6704,6 +6704,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-10-01T11:28:52.356496+00:00",
|
||||
"taskTreeUpdatedAt": "2026-10-01T11:33:25.484466+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-01T11:20:48.248679+00:00",
|
||||
"lastSyncTime": "2026-10-01T11:20:47.959583+00:00",
|
||||
"generatedAt": "2026-10-01T11:31:46.457624+00:00",
|
||||
"lastSyncTime": "2026-10-01T11:31:46.146618+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -3469,25 +3469,25 @@
|
||||
"decisionSuccessRate": 0.087,
|
||||
"decisionTotal": 46,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 81,
|
||||
"ambiguous_runtime": 83,
|
||||
"context_length": 8,
|
||||
"framework_architecture_unsupported": 33,
|
||||
"memory_capacity": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"参数/模板问题": 8
|
||||
},
|
||||
"failureCount": 132,
|
||||
"failureRate": 0.9706,
|
||||
"failureCount": 134,
|
||||
"failureRate": 0.971,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 4,
|
||||
"successRate": 0.0294,
|
||||
"successRate": 0.029,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 136,
|
||||
"unresolvedFailureCount": 89
|
||||
"total": 138,
|
||||
"unresolvedFailureCount": 91
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation": {
|
||||
"attributableFailureCount": 70,
|
||||
@@ -6194,7 +6194,7 @@
|
||||
"decisionSuccessRate": 0.0658,
|
||||
"decisionTotal": 152,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 193,
|
||||
"ambiguous_runtime": 195,
|
||||
"backend_operator": 15,
|
||||
"context_length": 8,
|
||||
"framework_architecture_unsupported": 86,
|
||||
@@ -6206,18 +6206,18 @@
|
||||
"tokenizer_compatibility": 2,
|
||||
"参数/模板问题": 29
|
||||
},
|
||||
"failureCount": 367,
|
||||
"failureRate": 0.9735,
|
||||
"failureCount": 369,
|
||||
"failureRate": 0.9736,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0265,
|
||||
"total": 377,
|
||||
"unresolvedFailureCount": 222
|
||||
"successRate": 0.0264,
|
||||
"total": 379,
|
||||
"unresolvedFailureCount": 224
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-01T11:20:48.234237+00:00",
|
||||
"generatedAt": "2026-10-01T11:31:46.442787+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 113,
|
||||
@@ -6225,7 +6225,7 @@
|
||||
"decisionSuccessRate": 0.163,
|
||||
"decisionTotal": 135,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 149,
|
||||
"ambiguous_runtime": 151,
|
||||
"context_length": 8,
|
||||
"framework_architecture_unsupported": 99,
|
||||
"memory_capacity": 2,
|
||||
@@ -6236,15 +6236,15 @@
|
||||
"日志缺失": 3,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 332,
|
||||
"failureRate": 0.9379,
|
||||
"failureCount": 334,
|
||||
"failureRate": 0.9382,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 22,
|
||||
"successRate": 0.0621,
|
||||
"total": 354,
|
||||
"unresolvedFailureCount": 218
|
||||
"successRate": 0.0618,
|
||||
"total": 356,
|
||||
"unresolvedFailureCount": 220
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 327,
|
||||
@@ -6986,9 +6986,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "mistral",
|
||||
@@ -7000,8 +7000,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mpt|none": {
|
||||
"attributableFailureCount": 2,
|
||||
@@ -7607,9 +7607,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 15
|
||||
"ambiguous_runtime": 16
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureCount": 16,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "starcoder2",
|
||||
@@ -7621,8 +7621,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 15
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 16
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation|bailing_hybrid|none": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -23894,9 +23894,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"参数/模板问题": 11
|
||||
"参数/模板问题": 10
|
||||
},
|
||||
"failureCount": 11,
|
||||
"failureCount": 10,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -23908,8 +23908,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 11
|
||||
"total": 10,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
@@ -23919,11 +23919,11 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 13,
|
||||
"ambiguous_runtime": 14,
|
||||
"context_length": 2,
|
||||
"framework_architecture_unsupported": 2
|
||||
},
|
||||
"failureCount": 17,
|
||||
"failureCount": 18,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -23935,8 +23935,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 13
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 14
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
@@ -24802,12 +24802,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastTerminalAt": "2026-09-30T15:29:22.559006+00:00",
|
||||
"lastTerminalAt": "2026-10-01T11:31:46.146588+00:00",
|
||||
"modelType": "mistral",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
@@ -24817,8 +24817,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|phi3small|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -28621,9 +28621,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
"ambiguous_runtime": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
@@ -28636,8 +28636,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors|33": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -29508,9 +29508,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4
|
||||
"ambiguous_runtime": 5
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 31,
|
||||
@@ -29523,8 +29523,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 5
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|32": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -54378,15 +54378,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17196,
|
||||
"totalRecords": 17417,
|
||||
"terminalRecords": 17198,
|
||||
"totalRecords": 17419,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6168,
|
||||
"decisionFailureRate": 0.8635,
|
||||
"decisionSuccessRate": 0.1365,
|
||||
"decisionTotal": 7143,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4486,
|
||||
"ambiguous_runtime": 4488,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 128,
|
||||
@@ -54402,30 +54402,30 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16221,
|
||||
"failureCount": 16223,
|
||||
"failureRate": 0.9433,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 944,
|
||||
"successCount": 975,
|
||||
"successRate": 0.0567,
|
||||
"total": 17196,
|
||||
"unresolvedFailureCount": 9109
|
||||
"total": 17198,
|
||||
"unresolvedFailureCount": 9111
|
||||
},
|
||||
"warnings": [
|
||||
"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 Biren_166m 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 Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-100 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-x8 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 Kunlunxin_p-800 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 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 MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -54470,6 +54470,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17417,
|
||||
"summarizedRecords": 17419,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -153,6 +153,7 @@
|
||||
{"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": "2026-09-30T01:23:45.362482+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T13:01:28.899242+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5001186", "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_tokenizer_patch", "lastSyncTime": "2026-09-23T19:00:27.302859+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:49:01.259499+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5001065", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-24T01:02:06.567778+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:49:01.257127+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5001059", "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_tokenizer_patch", "lastSyncTime": "2026-10-01T11:31:46.146588+00:00", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221450, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221450}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:49:01.251589+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5001057", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-23T16:10:53.658817+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42709318472, "estimatedRequiredGiB": 47.753, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 42728540075, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553707056, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 42728540075}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:49:01.249214+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5001061", "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_tokenizer_patch", "lastSyncTime": "2026-09-23T10:22:44.160467+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:49:01.247906+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5001064", "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": ["lfm2_moe"], "framework": "vllm", "lastSyncTime": "2026-09-23T18:42:51.656977+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16936006912, "estimatedRequiredGiB": 18.948, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 16953948786, "modelscopeLicense": "other", "modelscopeParams": 8467856832, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16953948786}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T12:49:01.246640+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5001066", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569092+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:33+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857814", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569134+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:33+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857813", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569144+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:33+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4923523", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:36:00.569235+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:16:33+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4795478", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.22.1",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "4580862add77e16fc92b867fae99b3d86556c41be38b7f979bf70bdd24c927b4",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "206a40fe95e5dfcecd3d4a045df07f3c78f46b31dc3e728e26d5a4d832f380ed",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "2367e54146ea654b61ff235a8e87a454460f27476afee9b03ef6e0eba506cf25",
|
||||
".modelhub_state/official_capabilities.json": "a3cf411270e06aabb8918d3708739eb6c5dbddb09ca8545f63301a37f6a67914",
|
||||
".modelhub_state/outcome_checkpoint.json": "c75d564acce070315a61fea5ce4726c7ba85fd5c85f92625c0cd117f582e9c48",
|
||||
".modelhub_state/market_intelligence.json": "deadebb9d1a11dd78cae44721d70db55b870f0bdc128ce42a837cb32e7844664",
|
||||
".modelhub_state/official_capabilities.json": "0c5ca16d85e8648d4a6c8f377f84c6078b9e54aee727fea2d63e7456391d43e8",
|
||||
".modelhub_state/outcome_checkpoint.json": "c7f0b0cc94d0f08035287cea2ef57c160f114208c44903cbb236e4c0f9cb5d7e",
|
||||
".modelhub_state/queue_cleanup_latest.json": "05a1b3ebbbe8095e2f42ed6517a8c002726299deda90003a645472de6c83714e",
|
||||
".modelhub_state/recent_outcomes.jsonl": "440d33489519195b7f226e593d8d8873568261b88946f6b39984a1def0a5b590",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "cac110bc3709ef78e96689ae6e84b614efa2d43cd27216eefae5039861734624",
|
||||
".modelhub_state/recovery_intents.jsonl": "bae87527faeed1da92c886e53e45815860baac03e7be773d98849eee5cda226f",
|
||||
".modelhub_state/recent_outcomes.jsonl": "2523ec2f7019354108df01107e7f0a74a17201a51201d3993b38b265a6fafd64",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "6ba9612bb8a16acb9d3922373c61d5df5384835028311b224a29d94106363dd0",
|
||||
".modelhub_state/recovery_intents.jsonl": "9aee34d48e43c117b6fed733b4df34e1b861f490631bf9d77288ab0d1580c0ad",
|
||||
".modelhub_state/routing_intelligence.json": "be70813f166dbb5be16db60ed04936b987ed15d3c008065b231ff723a2ff8af2",
|
||||
".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
|
||||
".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd",
|
||||
"ledger/submissions.jsonl": "59e1cb91f2f0b133bf51838c6d0ab57abf3606b2cb42605e4e2d80a43435666c",
|
||||
"outcomes/submissions.jsonl": "a3e7af589461293d1c9717ea5f6d428ba9ac1de6d5a41d73705c3f40a98ab498"
|
||||
"outcomes/submissions.jsonl": "e09807d1ddf91895c6930d5266c9de48c26a467ae03cec371934d70d03fec5ed"
|
||||
},
|
||||
"generation": 19198,
|
||||
"generation": 19199,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-10-01T11:30:43.864609+00:00",
|
||||
"updatedAt": "2026-10-01T11:33:42.337745+00:00",
|
||||
"writerId": "a812d0e025c3474eb16b828a4d987334"
|
||||
}
|
||||
|
||||
@@ -279,7 +279,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T14:18:03.258951+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T06:16:07.269550+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4972172", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T16:51:24.761939+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T08:49:13.744928+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974217", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T21:06:45.850274+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:01:42.205703+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979280", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754909+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457730, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096457730}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:38:07.337494+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4980575", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T23:08:35.573457+00:00", "modelId": "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245331488, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256941144, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256941144}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:06:16.550878+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4980890", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.191977+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683241105, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703487237, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703487237}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.438915+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981854", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192042+00:00", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.480303+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981856", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -356,7 +355,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T19:10:15.559190+00:00", "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325202, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325202}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:07:40.941920+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999639", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T19:13:53.564409+00:00", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236742}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:10:31.847181+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999689", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T19:58:46.051807+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4018332584, "estimatedRequiredGiB": 4.494, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4020783717, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4020783717}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T11:57:55.153765+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5000419", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T20:50:04.063136+00:00", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221450, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221450}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T12:49:01.251589+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5001057", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T22:22:17.565308+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T14:18:50.561697+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5002167", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T23:56:03.457453+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51304360808, "estimatedRequiredGiB": 57.349, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 20341994707, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 51315158961}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T15:54:32.713857+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5003279", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-22T00:21:56.762809+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51304360808, "estimatedRequiredGiB": 57.349, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 51315158961, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 51315158961}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T16:21:12.297298+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5003635", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user