state: generation 25760 (intent)
This commit is contained in:
@@ -2354,7 +2354,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-19T02:47:23.805887+00:00",
|
||||
"generatedAt": "2026-10-19T03:26:50.515773+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 117,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-10-19T02:49:18.766093+00:00",
|
||||
"communityAttemptedAt": "2026-10-19T03:28:56.963961+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-10-19T02:49:18.766093+00:00",
|
||||
"communityUpdatedAt": "2026-10-19T03:28:56.963961+00:00",
|
||||
"frameworkAttemptedAt": "2026-10-19T01:48:00.272571+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -452,320 +452,320 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-19T02:49:18.766093+00:00",
|
||||
"generatedAt": "2026-10-19T03:28:56.963961+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1109.205298013245,
|
||||
"backlogHours": 1164.0833333333333,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.648001587309626,
|
||||
"queueFactor": 1.0022990109562744,
|
||||
"queueWeight": 1.0022990109562744,
|
||||
"recentSuccess": 47,
|
||||
"recentSuccessRate": 0.31125827814569534,
|
||||
"recentTerminal": 151,
|
||||
"recentWilsonLowerBound": 0.24286165023873077,
|
||||
"qualityFactor": 1.793413579405791,
|
||||
"queueFactor": 0.9980941325540378,
|
||||
"queueWeight": 0.9980941325540378,
|
||||
"recentSuccess": 45,
|
||||
"recentSuccessRate": 0.3125,
|
||||
"recentTerminal": 144,
|
||||
"recentWilsonLowerBound": 0.24249648086200354,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.6517903610148086,
|
||||
"selectionWeight": 1.789995570847655,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 25.166666666666668,
|
||||
"waiting": 27915
|
||||
"throughputPerHour": 24.0,
|
||||
"waiting": 27938
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1483.5813953488373,
|
||||
"backlogHours": 1428.44776119403,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9595163630040601,
|
||||
"queueWeight": 0.9595163630040601,
|
||||
"queueFactor": 0.9679199890781939,
|
||||
"queueWeight": 0.9679199890781939,
|
||||
"recentSuccess": 48,
|
||||
"recentSuccessRate": 0.37209302325581395,
|
||||
"recentTerminal": 129,
|
||||
"recentWilsonLowerBound": 0.29351051285070046,
|
||||
"recentSuccessRate": 0.3582089552238806,
|
||||
"recentTerminal": 134,
|
||||
"recentWilsonLowerBound": 0.282018738346317,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.39879090751015,
|
||||
"selectionWeight": 2.419799972695485,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 21.5,
|
||||
"waiting": 31897
|
||||
"throughputPerHour": 22.333333333333332,
|
||||
"waiting": 31902
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 137.82266009852216,
|
||||
"backlogHours": 134.4519230769231,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.1628969218708145,
|
||||
"qualityFactor": 0.22716727448624852,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.12315270935960591,
|
||||
"recentTerminal": 203,
|
||||
"recentWilsonLowerBound": 0.0848243264868977,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.1346153846153846,
|
||||
"recentTerminal": 208,
|
||||
"recentWilsonLowerBound": 0.09480386377239655,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.21176599843205887,
|
||||
"selectionWeight": 0.29531745683212307,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 33.833333333333336,
|
||||
"waiting": 4663
|
||||
"throughputPerHour": 34.666666666666664,
|
||||
"waiting": 4661
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1496.0,
|
||||
"backlogHours": 1197.2,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.5960405352848994,
|
||||
"queueFactor": 0.9583173546346874,
|
||||
"queueWeight": 0.9583173546346874,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.2361111111111111,
|
||||
"recentTerminal": 72,
|
||||
"recentWilsonLowerBound": 0.15296584625945536,
|
||||
"qualityFactor": 0.45825527282445755,
|
||||
"queueFactor": 0.9939032414909885,
|
||||
"queueWeight": 0.9939032414909885,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.2,
|
||||
"recentTerminal": 90,
|
||||
"recentWilsonLowerBound": 0.13042296962596497,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.5711959890292678,
|
||||
"selectionWeight": 0.45546140109056565,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.0,
|
||||
"waiting": 17952
|
||||
"throughputPerHour": 15.0,
|
||||
"waiting": 17958
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 529.5,
|
||||
"backlogHours": 497.9495798319328,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.9246029413716053,
|
||||
"queueFactor": 1.1198740919002994,
|
||||
"queueWeight": 1.1198740919002994,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.25892857142857145,
|
||||
"recentTerminal": 112,
|
||||
"recentWilsonLowerBound": 0.18675273129699618,
|
||||
"qualityFactor": 0.6575652765236037,
|
||||
"queueFactor": 1.1336821474719825,
|
||||
"queueWeight": 1.1336821474719825,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.2184873949579832,
|
||||
"recentTerminal": 119,
|
||||
"recentWilsonLowerBound": 0.15368839845214263,
|
||||
"running": 7,
|
||||
"selectionWeight": 1.0354388793368723,
|
||||
"selectionWeight": 0.7454700147922871,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.666666666666668,
|
||||
"waiting": 9884
|
||||
"throughputPerHour": 19.833333333333332,
|
||||
"waiting": 9876
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 108.92783505154638,
|
||||
"backlogHours": 92.08695652173913,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 24,
|
||||
"qualityFactor": 0.054113992289815505,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.08247422680412371,
|
||||
"recentTerminal": 194,
|
||||
"recentWilsonLowerBound": 0.05140122441505211,
|
||||
"running": 25,
|
||||
"selectionWeight": 0.07034818997676016,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.07391304347826087,
|
||||
"recentTerminal": 230,
|
||||
"recentWilsonLowerBound": 0.04665639409037411,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 32.333333333333336,
|
||||
"waiting": 3522
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 38.333333333333336,
|
||||
"waiting": 3530
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 631.8648648648648,
|
||||
"backlogHours": 450.4615384615385,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0905748072213115,
|
||||
"queueWeight": 1.0905748072213115,
|
||||
"queueFactor": 1.1508545944949382,
|
||||
"queueWeight": 1.1508545944949382,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.06756756756756757,
|
||||
"recentTerminal": 74,
|
||||
"recentWilsonLowerBound": 0.02920365554856204,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.05452874036106558,
|
||||
"recentSuccessRate": 0.04807692307692308,
|
||||
"recentTerminal": 104,
|
||||
"recentWilsonLowerBound": 0.020707736946876363,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.057542729724746916,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 12.333333333333334,
|
||||
"waiting": 7793
|
||||
"throughputPerHour": 17.333333333333332,
|
||||
"waiting": 7808
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 1990.4081632653063,
|
||||
"backlogHours": 1840.075471698113,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.23275233126620512,
|
||||
"queueFactor": 0.9181375942579925,
|
||||
"queueWeight": 0.9181375942579925,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.1836734693877551,
|
||||
"recentTerminal": 49,
|
||||
"recentWilsonLowerBound": 0.09976228838458356,
|
||||
"qualityFactor": 0.2895126287659876,
|
||||
"queueFactor": 0.931845189966558,
|
||||
"queueWeight": 0.931845189966558,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.18867924528301888,
|
||||
"recentTerminal": 53,
|
||||
"recentWilsonLowerBound": 0.10585211943149556,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.2136986654866929,
|
||||
"selectionWeight": 0.26978095055015927,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.166666666666666,
|
||||
"waiting": 16255
|
||||
"throughputPerHour": 8.833333333333334,
|
||||
"waiting": 16254
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 466.7317073170732,
|
||||
"backlogHours": 395.83448275862065,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.9684838277689244,
|
||||
"queueFactor": 1.1412715633963326,
|
||||
"queueWeight": 1.1412715633963326,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.7272081281707242,
|
||||
"queueFactor": 1.17338915384685,
|
||||
"queueWeight": 1.17338915384685,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.2601626016260163,
|
||||
"recentTerminal": 123,
|
||||
"recentWilsonLowerBound": 0.1907305189906578,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.105303052241905,
|
||||
"recentSuccessRate": 0.2206896551724138,
|
||||
"recentTerminal": 145,
|
||||
"recentWilsonLowerBound": 0.16088432964348773,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.8532981301847977,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.5,
|
||||
"waiting": 9568
|
||||
"throughputPerHour": 24.166666666666668,
|
||||
"waiting": 9566
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 781.8876404494382,
|
||||
"backlogHours": 702.7878787878788,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 1.0526471949343927,
|
||||
"queueFactor": 1.0562760674294265,
|
||||
"queueWeight": 1.0562760674294265,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.2808988764044944,
|
||||
"recentTerminal": 89,
|
||||
"recentWilsonLowerBound": 0.19809358040575942,
|
||||
"qualityFactor": 0.7193327216995511,
|
||||
"queueFactor": 1.076577933429139,
|
||||
"queueWeight": 1.076577933429139,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.23232323232323232,
|
||||
"recentTerminal": 99,
|
||||
"recentWilsonLowerBound": 0.16009001362979594,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.1118860394559174,
|
||||
"selectionWeight": 0.7744177349752607,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.833333333333334,
|
||||
"waiting": 11598
|
||||
"throughputPerHour": 16.5,
|
||||
"waiting": 11596
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2230.714285714286,
|
||||
"backlogHours": 2029.090909090909,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.10389044782563478,
|
||||
"queueFactor": 0.9025733369468546,
|
||||
"queueWeight": 0.9025733369468546,
|
||||
"qualityFactor": 0.09155806333001384,
|
||||
"queueFactor": 0.9182773821609704,
|
||||
"queueWeight": 0.9182773821609704,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.12857142857142856,
|
||||
"recentTerminal": 70,
|
||||
"recentWilsonLowerBound": 0.06914021991242263,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.09376874817088628,
|
||||
"recentSuccessRate": 0.11688311688311688,
|
||||
"recentTerminal": 77,
|
||||
"recentWilsonLowerBound": 0.06272491064586316,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.08407569871041345,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.666666666666666,
|
||||
"waiting": 26025
|
||||
"throughputPerHour": 12.833333333333334,
|
||||
"waiting": 26040
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 2661.8571428571427,
|
||||
"backlogHours": 2430.6521739130435,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.3308564780672129,
|
||||
"queueFactor": 0.8789645921924727,
|
||||
"queueWeight": 0.8789645921924727,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.21428571428571427,
|
||||
"recentTerminal": 42,
|
||||
"recentWilsonLowerBound": 0.11705668531051239,
|
||||
"qualityFactor": 0.20687843446992596,
|
||||
"queueFactor": 0.8937389614019566,
|
||||
"queueWeight": 0.8937389614019566,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.17391304347826086,
|
||||
"recentTerminal": 46,
|
||||
"recentWilsonLowerBound": 0.09085683568889252,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.2908111293185856,
|
||||
"selectionWeight": 0.18489531715961438,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.0,
|
||||
"waiting": 18633
|
||||
"throughputPerHour": 7.666666666666667,
|
||||
"waiting": 18635
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1516.4347826086957,
|
||||
"backlogHours": 1434.986301369863,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9563690906515119,
|
||||
"queueWeight": 0.9563690906515119,
|
||||
"queueFactor": 0.9672571527053375,
|
||||
"queueWeight": 0.9672571527053375,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.07246376811594203,
|
||||
"recentTerminal": 69,
|
||||
"recentWilsonLowerBound": 0.031347309217669046,
|
||||
"recentSuccessRate": 0.0684931506849315,
|
||||
"recentTerminal": 73,
|
||||
"recentWilsonLowerBound": 0.02960860206637889,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.0478184545325756,
|
||||
"selectionWeight": 0.048362857635266876,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 11.5,
|
||||
"waiting": 17439
|
||||
"throughputPerHour": 12.166666666666666,
|
||||
"waiting": 17459
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1143.4285714285713,
|
||||
"backlogHours": 1134.6614173228345,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.7069118391566762,
|
||||
"queueFactor": 0.9977408096211435,
|
||||
"queueWeight": 0.9977408096211435,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.23015873015873015,
|
||||
"recentTerminal": 126,
|
||||
"recentWilsonLowerBound": 0.16529948502667766,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.7053147907309537,
|
||||
"qualityFactor": 0.690796965640468,
|
||||
"queueFactor": 1.0019341285846621,
|
||||
"queueWeight": 1.0019341285846621,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.2204724409448819,
|
||||
"recentTerminal": 127,
|
||||
"recentWilsonLowerBound": 0.15717143105153952,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.6921330557979111,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 21.0,
|
||||
"waiting": 24012
|
||||
"throughputPerHour": 21.166666666666668,
|
||||
"waiting": 24017
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-10-19T02:49:18.766093+00:00",
|
||||
"queueAttemptedAt": "2026-10-19T03:28:56.963961+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-10-19T02:49:18.766093+00:00",
|
||||
"queueUpdatedAt": "2026-10-19T03:28:56.963961+00:00",
|
||||
"supportedGpus": [
|
||||
"Cambricon_mlu-370-x4",
|
||||
"Vastai_va16",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -3641,6 +3641,18 @@
|
||||
{"batchId": "d4debad08e8c4b43b9c38b497c2d9149", "completedAt": "2026-10-18T19:22:12.634975+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-18T19:00:28.942994+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bfaa2493467043aebea252e03349a551", "lastModified": "2026-10-17T05:31:37+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16", "reason": null, "reconciledAt": "2026-10-19T03:21:31.016263+00:00", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5633182", "taskType": "text-generation"}
|
||||
{"batchId": "d4debad08e8c4b43b9c38b497c2d9149", "completedAt": "2026-10-18T19:22:12.634977+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-18T19:00:28.943037+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2c2708e531504ae18896e86b5a003d92", "lastModified": "2026-10-16T16:00:26+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-32B-FP8", "reason": null, "reconciledAt": "2026-10-19T03:21:31.017221+00:00", "repoId": "IFM/Jais-3-32B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5633102", "taskType": "text-generation"}
|
||||
{"batchId": "d4debad08e8c4b43b9c38b497c2d9149", "completedAt": "2026-10-18T19:22:12.634982+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-18T19:00:28.943121+00:00", "framework": "vllm_tokenizer_patch", "intentId": "50efdfa4765c4c5a80df646c55cacc19", "lastModified": "2026-10-16T05:43:29+00:00", "modelAddress": "https://modelscope.cn/models/rapid-mlx/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-MLX-3bit", "reason": null, "reconciledAt": "2026-10-19T03:21:31.014958+00:00", "repoId": "rapid-mlx/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-MLX-3bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5633141", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.455769+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3a3c5942594f4a77b151d2a4142339ad", "lastModified": "2026-10-15T14:37:21+00:00", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-32B-FP8", "repoId": "IFM/K2-Horizon-32B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.455867+00:00", "framework": "vllm_tokenizer_patch", "intentId": "186a9d4ceb134c7182496d9039a13ef9", "lastModified": "2026-10-15T18:35:13+00:00", "modelAddress": "https://modelscope.cn/models/rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit", "repoId": "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "228b6bc2745650abd95687d8da71c138b5e7b7e9cbd7ff60115887f5ff13ac2c", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.455915+00:00", "framework": "llamacpp", "intentId": "24290d5484604cbab9ee27f5f1007b86", "lastModified": "2026-10-15T11:37:55+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B-GGUF", "repoId": "DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "f15ba589f8fc347b06d694c47e50f0ec39eb094f4731fb654c6ecbc9c8faac9b", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.455981+00:00", "framework": "llamacpp", "intentId": "c5e24844ad564cb9aba04989751cb330", "lastModified": "2026-10-15T23:18:06+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/microsoft-UserRepGen-4B-GGUF", "repoId": "prithivMLmods/microsoft-UserRepGen-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "077eea1fd1f15fd13a8367dad60b0d1b310724d7cc6ea546505d0f84d78d5aca", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.456067+00:00", "framework": "llamacpp", "intentId": "da11efd95c3b490c95c765de4acf4b9d", "lastModified": "2026-10-18T14:13:55+00:00", "modelAddress": "https://modelscope.cn/models/castorini/gaggle-nanochat-pretrained-climbmix-20260924", "repoId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "e9c4f4f15802a39a57c6e07956c53755f75fc438be43d1164a8a2eda32456b1e", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.456173+00:00", "framework": "llamacpp", "intentId": "db3e675826c941cfbb7533c1f8d51938", "lastModified": "2026-10-18T14:39:44+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "repoId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "0b3aba8e880b5f6fa7b9aa817b9c4c2fbbfb0030e00a71272a9bebf44f0f76b5", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.456285+00:00", "framework": "llamacpp", "intentId": "5cc024ffecff4e4a911c5cafd3defd86", "lastModified": "2026-10-16T15:51:15+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "02e187e3671a31235c75c7c9ad7c52e86e0476bdc3118ddf379ddb46a07261d1", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.456382+00:00", "framework": "llamacpp", "intentId": "98fe46e0ddc84f36aa7ca75150b8d036", "lastModified": "2026-10-16T15:51:32+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "repoId": "OpenBMB/MiniCPM-V-4.7-35B-A3B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "61898f295f143f06988745beef05f856402c5162f007122829060f3694145199", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.456483+00:00", "framework": "llamacpp", "intentId": "7115d21f22ef4f5385ae213f621d6aeb", "lastModified": "2026-10-15T14:56:28+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "repoId": "DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.456582+00:00", "framework": "vllm_tokenizer_patch", "intentId": "afdf7b26bf9047109e4de55c37147449", "lastModified": "2026-10-17T05:39:17+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.456676+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1e27d02375444e9d95bf669c065b8d16", "lastModified": "2026-10-16T15:54:35+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-3.7B-FP8", "repoId": "IFM/Jais-3-3.7B-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "d7fb911bff724d3aa869b269e8c03a0b", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-19T03:32:52.456766+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ede8264ab85b4fedaa128ac0d2989291", "lastModified": "2026-10-15T08:32:12+00:00", "modelAddress": "https://modelscope.cn/models/mrm8488/mistral-7b-ft-h4-no_robots_instructions", "repoId": "mrm8488/mistral-7b-ft-h4-no_robots_instructions", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
|
||||
{"batchId": "69aeca8f229c49d1ae27c241c2af02c0", "completedAt": "2026-10-19T03:21:22.675931+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T02:52:43.464642+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6633d9ae94144df1ab2bd28ce6f67c94", "repoId": "DavidAU/Mistral-Nemo-Instruct-2407-12B-Thinking-M-Claude-Opus-High-Reasoning", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "69aeca8f229c49d1ae27c241c2af02c0", "completedAt": "2026-10-19T03:21:22.675928+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T02:52:43.464600+00:00", "framework": "vllm_tokenizer_patch", "intentId": "93731e3b6b274c11a8dc8ec242bfa03a", "repoId": "DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "69aeca8f229c49d1ae27c241c2af02c0", "completedAt": "2026-10-19T03:21:22.675926+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T02:52:43.464558+00:00", "framework": "vllm_tokenizer_patch", "intentId": "14fb5ee495b54e1f95626a6f5afbc03e", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "f4fb420b3f1e8f38efed19aac890912f0d59732d9b0dfddc16af6e0ad2ea3faf",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "2a701ef535bde2b2c87ca2b46ffe609d72b6ff6fe776794b8f52e53e7e15782c",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "a087fc8b0ffdc2870ba76776b3b270e0242a4c1c59ed198f7a743b20b5184939",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "9141a62a0ade2869564b8a053bba2ea44df687398039d6e2e7c83dbff27f6768",
|
||||
".modelhub_state/official_capabilities.json": "3dd58c3fc5b0fe65aea62ae418f997453ba654ccd66a8b38f00abcd450c62228",
|
||||
".modelhub_state/outcome_checkpoint.json": "a880a8f21037233f942af781f6015f9a636a650ff48597afa564ff08ec92c40f",
|
||||
".modelhub_state/market_intelligence.json": "87bb223d36d4c9135043a4e1c859fc71e0358b43670689f25ad0b061a1e96ceb",
|
||||
".modelhub_state/official_capabilities.json": "036454550635dbe6d7de0e52d7c953a4e59858cd8fa0696f6c91078ec39cf189",
|
||||
".modelhub_state/outcome_checkpoint.json": "d87efdea58cd9dca88451383979254561d6d36ece46aeb49b80babaef20ec060",
|
||||
".modelhub_state/queue_cleanup_latest.json": "27074b03987fc2f279ccc84565fc56c4236022f976c6479d04423ecbfa20e4de",
|
||||
".modelhub_state/recent_outcomes.jsonl": "fa91981c7ed2f069f9d64d025e5739016eda9d52a36ec06064f667e592ce0db4",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "cb6d2b26dfa28c60ff2fc2ba66ac4fdcc7d1410ef84ad1eeb69ab4fd75fd442b",
|
||||
".modelhub_state/recovery_intents.jsonl": "52baf510db0700b42db1b7feb8db4756566fb8e61dcad93ed7b05918b89a700c",
|
||||
".modelhub_state/recovery_intents.jsonl": "5894b68bcdc5df6088b19f460929a165a44c8155a4b98b9e96d198fa49c0feaa",
|
||||
".modelhub_state/routing_intelligence.json": "0d6519dfd486aa9e7fac788d287587c2b9313893144f3da7a7d523388158e28d",
|
||||
".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b",
|
||||
".modelhub_state/worker_crashes.jsonl": "75c8a6c5605f99dfe3e7d27ff6e9c6d730e1ee3a5016c812ed5cc3137a98684c",
|
||||
"ledger/submissions.jsonl": "1af1295c8d23a0d3087643d07b49fc6d4878c03f59c81e1b08517285a8084730",
|
||||
"outcomes/submissions.jsonl": "ac59d991bbae8028664186fee6fe91f6571a1f8814170e0cfd7a210b875bba59"
|
||||
"outcomes/submissions.jsonl": "0c1a3ee40692c7d8e550d545814840faeeeb3c06d50fd01471f5b746b579c404"
|
||||
},
|
||||
"generation": 25759,
|
||||
"phase": "cycle",
|
||||
"generation": 25760,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-10-19T03:21:31.244246+00:00",
|
||||
"updatedAt": "2026-10-19T03:32:52.617638+00:00",
|
||||
"writerId": "eca444bc9fdf4bc89c9cfc2f8a9a6ac1"
|
||||
}
|
||||
|
||||
@@ -102,17 +102,9 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063090+00:00", "modelId": "rengensheng/Ternary-Bonsai-2-27B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "87e2d06ee2cbb5d6c759a240df54c78746d706859f9a364e78515c8f28fcc1fd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629246976, "estimatedRequiredGiB": 8.757, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7835440764, "modelscopeLicense": "apache-2.0", "modelscopeParams": 460730096, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7835440764}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.174402+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947147", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063052+00:00", "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "a0e7803b6725f735d0804da4c3b2af6ac5c0db91adef3494b64f29a43c4cded8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.177348+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947146", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063105+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "ed217196ebf72901791ffd67a7627878fd8f0fd29fa1291cafd8f6b32c01507f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.175900+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947142", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647466+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "2026-09-20T02:52:51.140009+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969028", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647505+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60671749474, "estimatedRequiredGiB": 67.825, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60688949222, "modelscopeLicense": "other", "modelscopeParams": 15303312058, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:jangtq-prestack", "custom_tag:minimax", "custom_tag:minimax-m2", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:2bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60688949222}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.187054+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969030", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:10:38.766358+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-20T03:09:17.840209+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969321", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600049+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T03:25:32.237107+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969645", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671271+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T03:41:49.554113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671248+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-09-20T03:53:59.224352+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970246", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901858+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-20T04:10:03.058495+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970512", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901659+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72670025872, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679340864, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int88", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679340864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.788367+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:34:29.856383+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "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": "2026-09-20T04:26:45.109939+00:00", "targetGpu": "Vastai_va16", "taskId": "4970729", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:46:14.462938+00:00", "modelId": "empero-ai/Qwen3.8-35B-A3B-Distill", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903778536, "estimatedRequiredGiB": 80.392, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71933964484, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.6", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:moe", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-15T22:59:41.110897+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 71933964484}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:42:19.067096+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970926", "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", "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": "2026-09-21T00:08:58.191942+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.487823+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981859", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.191900+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "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", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.445927+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981853", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -131,7 +123,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T01:35:45.556088+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809686744, "modelscopeLicense": "other", "modelscopeParams": 219544320, "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": 809686744}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:20:07.435588+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984361", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T01:35:45.556160+00:00", "modelId": "RedHatAI/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720441937, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720441937}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:20:14.310450+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984367", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T02:15:17.867333+00:00", "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658256, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:59:59.555224+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985000", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-21T02:42:24.494032+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-20T18:39:53.164098+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985692", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:02:20.757732+00:00", "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658310, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:17.970020+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985910", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T03:02:20.757780+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:32.459840+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985911", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:45:50.542869+00:00", "modelId": "RedHatAI/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": 9093325064, "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": 9093325064}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:30:14.636274+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986332", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -140,7 +131,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T08:25:31.485626+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3-8B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556376, "estimatedRequiredGiB": 17.964, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16073634582, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16073634582}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:22:06.134784+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4990307", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295624+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "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": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:19:31.687350+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991029", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998391+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "status": "waiting", "submitTime": "2026-09-21T02:04:12.536952+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991720", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:33:30.477748+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": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-21T02:09:08.713395+00:00", "targetGpu": "Biren_166m", "taskId": "4991852", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T12:58:50.741624+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "pending", "status": "waiting", "submitTime": "2026-09-21T04:44:11.759434+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4994057", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T14:32:55.759836+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:25:35.855289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995260", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T15:02:24.876320+00:00", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161034, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:55:59.084023+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4995631", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -156,7 +146,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T19:05:56.949088+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.622, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345693224, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "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": 2345693224}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T10:52:20.710547+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4999410", "taskType": "text-generation", "verifyResult": null}
|
||||
{"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_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": "2026-09-22T01:26:44.660341+00:00", "modelId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 761968600, "estimatedRequiredGiB": 0.854, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 763816934, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 763816934}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T17:25:56.838948+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004736", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T01:45:02.870751+00:00", "modelId": "nm-testing/tinyllama-oneshot-w4a16-channel-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 747618112, "estimatedRequiredGiB": 0.838, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 749466433, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-21T15:02:24.876390+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 749466433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T17:44:25.024486+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5004890", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T01:45:02.870729+00:00", "modelId": "nm-testing/tinyllama-oneshot-w4a16-group128-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 761968600, "estimatedRequiredGiB": 0.854, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 763816934, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 763816934}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T17:44:25.068055+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5004892", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -1103,7 +1092,7 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-18T20:30:33.153669+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7950515472, "estimatedRequiredGiB": 8.907, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 7969474643, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7969474643}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-18T12:17:52.663248+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5626803", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-18T23:11:19.047715+00:00", "modelId": "IFM/Jais-3-MoVA-36B-A4B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 48357794520, "estimatedRequiredGiB": 54.081, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 48390679219, "modelscopeLicense": "apache-2.0", "modelscopeParams": 37444792020, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:36b", "custom_tag:mova", "custom_tag:moe", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 48390679219}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-18T15:03:16.858653+00:00", "targetGpu": "MetaX_c-500", "taskId": "5628877", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T02:47:23.752421+00:00", "modelId": "rockmatrix/EdgeRock", "modelProfile": {"architectures": ["EdgeRockForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9823243736, "estimatedRequiredGiB": 20.793, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "edgerock", "modelscopeFileSize": 18605617057, "modelscopeLicense": "other", "modelscopeParams": 4578061568, "modelscopeTags": ["license:other", "model_type:edgerock", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:custom-code", "custom_tag:long-context", "custom_tag:image-text-to-text", "custom_tag:open-weights", "custom_tag:commercial-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18605617057}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-18T18:00:23.158975+00:00", "targetGpu": "MetaX_c-500", "taskId": "5631643", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "IFM/Jais-3-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.377, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11074974075, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:7B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11074974075}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-18T19:00:30.160858+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633211", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7950515472, "estimatedRequiredGiB": 8.907, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 7969474643, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7969474643}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-18T19:00:30.147828+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633182", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "IFM/Jais-3-32B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37350407624, "estimatedRequiredGiB": 41.766, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 37371953866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779304960, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:32B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 37371953866}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-18T19:00:30.149584+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633102", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "rapid-mlx/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-MLX-3bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42747017349, "estimatedRequiredGiB": 47.793, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 42764313592, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:nemotron", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 42764313592}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-18T19:00:30.157505+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633141", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T03:26:50.355302+00:00", "modelId": "IFM/Jais-3-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.377, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11074974075, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:7B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11074974075}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-18T19:00:30.160858+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633211", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T03:26:50.355272+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7950515472, "estimatedRequiredGiB": 8.907, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 7969474643, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7969474643}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-18T19:00:30.147828+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633182", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T03:26:50.355338+00:00", "modelId": "IFM/Jais-3-32B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37350407624, "estimatedRequiredGiB": 41.766, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 37371953866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779304960, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:32B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 37371953866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-18T19:00:30.149584+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633102", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T03:26:50.355360+00:00", "modelId": "rapid-mlx/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-MLX-3bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42747017349, "estimatedRequiredGiB": 47.793, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 42764313592, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:nemotron", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 42764313592}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-18T19:00:30.157505+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633141", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user