state: generation 11385 (cycle)
This commit is contained in:
@@ -2652,7 +2652,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T10:01:40.238300+00:00",
|
||||
"generatedAt": "2026-09-21T10:05:14.085772+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 133,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -434,121 +434,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-21T10:04:10.177617+00:00",
|
||||
"generatedAt": "2026-09-21T10:05:23.787223+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 957.4459459459459,
|
||||
"backlogHours": 964.1632653061224,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.025666568543973,
|
||||
"queueFactor": 0.9910022665434337,
|
||||
"queueWeight": 0.9910022665434337,
|
||||
"recentSuccess": 43,
|
||||
"recentSuccessRate": 0.2905405405405405,
|
||||
"recentTerminal": 148,
|
||||
"recentWilsonLowerBound": 0.22343062480550951,
|
||||
"qualityFactor": 1.0255872330871003,
|
||||
"queueFactor": 0.9917622177216276,
|
||||
"queueWeight": 0.9917622177216276,
|
||||
"recentSuccess": 44,
|
||||
"recentSuccessRate": 0.29931972789115646,
|
||||
"recentTerminal": 147,
|
||||
"recentWilsonLowerBound": 0.23116798348527112,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.0164378941449033,
|
||||
"selectionWeight": 1.0171386687534505,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.666666666666668,
|
||||
"waiting": 23617
|
||||
"throughputPerHour": 24.5,
|
||||
"waiting": 23622
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1348.3809523809523,
|
||||
"backlogHours": 1327.3125,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.3958982963647815,
|
||||
"queueFactor": 0.9413906837949334,
|
||||
"queueWeight": 0.9413906837949334,
|
||||
"recentSuccess": 42,
|
||||
"recentSuccessRate": 0.3333333333333333,
|
||||
"recentTerminal": 126,
|
||||
"recentWilsonLowerBound": 0.2570292256450892,
|
||||
"qualityFactor": 1.1000772511413817,
|
||||
"queueFactor": 0.945331585464432,
|
||||
"queueWeight": 0.945331585464432,
|
||||
"recentSuccess": 40,
|
||||
"recentSuccessRate": 0.3125,
|
||||
"recentTerminal": 128,
|
||||
"recentWilsonLowerBound": 0.23865407613652956,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.3140856517230242,
|
||||
"selectionWeight": 1.0399377719548364,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 21.0,
|
||||
"throughputPerHour": 21.333333333333332,
|
||||
"waiting": 28316
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 177.06896551724137,
|
||||
"backlogHours": 185.06586826347305,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.2322354188631864,
|
||||
"queueFactor": 1.2764988266904402,
|
||||
"queueWeight": 1.2764988266904402,
|
||||
"qualityFactor": 0.2363224153649593,
|
||||
"queueFactor": 1.2703728310316402,
|
||||
"queueWeight": 1.2703728310316402,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.16091954022988506,
|
||||
"recentTerminal": 174,
|
||||
"recentWilsonLowerBound": 0.11374322651966227,
|
||||
"recentSuccessRate": 0.16766467065868262,
|
||||
"recentTerminal": 167,
|
||||
"recentWilsonLowerBound": 0.11862320234962478,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.29644823969482037,
|
||||
"selectionWeight": 0.3002175758434185,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 29.0,
|
||||
"waiting": 5135
|
||||
"throughputPerHour": 27.833333333333332,
|
||||
"waiting": 5151
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1475.2131147540983,
|
||||
"backlogHours": 1430.095238095238,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.7649849450853935,
|
||||
"queueFactor": 0.9287815352262515,
|
||||
"queueWeight": 0.9287815352262515,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.29508196721311475,
|
||||
"recentTerminal": 61,
|
||||
"recentWilsonLowerBound": 0.19554865403985322,
|
||||
"qualityFactor": 0.8821324804294756,
|
||||
"queueFactor": 0.9348144186887947,
|
||||
"queueWeight": 0.9348144186887947,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.31746031746031744,
|
||||
"recentTerminal": 63,
|
||||
"recentWilsonLowerBound": 0.21586527168091207,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.7105038917213815,
|
||||
"selectionWeight": 0.8246301618991847,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 10.166666666666666,
|
||||
"waiting": 14998
|
||||
"throughputPerHour": 10.5,
|
||||
"waiting": 15016
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 457.6859504132231,
|
||||
"backlogHours": 454.91803278688525,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.2141250978866827,
|
||||
"queueFactor": 1.1070230158743228,
|
||||
"queueWeight": 1.1070230158743228,
|
||||
"qualityFactor": 0.1950037950183471,
|
||||
"queueFactor": 1.1100439485577436,
|
||||
"queueWeight": 1.1100439485577436,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.1652892561983471,
|
||||
"recentTerminal": 121,
|
||||
"recentWilsonLowerBound": 0.10962203759241998,
|
||||
"recentSuccessRate": 0.16393442622950818,
|
||||
"recentTerminal": 122,
|
||||
"recentWilsonLowerBound": 0.10870072431592571,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.2370414116369001,
|
||||
"selectionWeight": 0.21646278260591087,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.166666666666668,
|
||||
"waiting": 9230
|
||||
"throughputPerHour": 20.333333333333332,
|
||||
"waiting": 9250
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 39.10569105691057,
|
||||
"backlogHours": 37.336787564766844,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -557,197 +557,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.06504065040650407,
|
||||
"recentTerminal": 369,
|
||||
"recentWilsonLowerBound": 0.044092991505070275,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.05699481865284974,
|
||||
"recentTerminal": 386,
|
||||
"recentWilsonLowerBound": 0.03793620535056797,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 61.5,
|
||||
"waiting": 2405
|
||||
"throughputPerHour": 64.33333333333333,
|
||||
"waiting": 2402
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 106.80866425992781,
|
||||
"backlogHours": 100.23050847457628,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.1936779334589081,
|
||||
"qualityFactor": 0.13633432948524812,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.1407942238267148,
|
||||
"recentTerminal": 277,
|
||||
"recentWilsonLowerBound": 0.10473344792429565,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.25178131349658056,
|
||||
"recentSuccess": 37,
|
||||
"recentSuccessRate": 0.12542372881355932,
|
||||
"recentTerminal": 295,
|
||||
"recentWilsonLowerBound": 0.09238019524417321,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.17723462833082257,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 46.166666666666664,
|
||||
"waiting": 4931
|
||||
"throughputPerHour": 49.166666666666664,
|
||||
"waiting": 4928
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 3841.4399999999996,
|
||||
"backlogHours": 4364.727272727273,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8045771219807961,
|
||||
"queueWeight": 0.8045771219807961,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.52,
|
||||
"recentTerminal": 25,
|
||||
"recentWilsonLowerBound": 0.3349821795314731,
|
||||
"queueFactor": 0.7907452278423037,
|
||||
"queueWeight": 0.7907452278423037,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.5454545454545454,
|
||||
"recentTerminal": 22,
|
||||
"recentWilsonLowerBound": 0.3465947328904156,
|
||||
"running": 2,
|
||||
"selectionWeight": 2.01144280495199,
|
||||
"selectionWeight": 1.9768630696057592,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 4.166666666666667,
|
||||
"waiting": 16006
|
||||
"throughputPerHour": 3.6666666666666665,
|
||||
"waiting": 16004
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 594.5607476635514,
|
||||
"backlogHours": 579.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.4127304604676082,
|
||||
"queueFactor": 1.0644183485182297,
|
||||
"queueWeight": 1.0644183485182297,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.21495327102803738,
|
||||
"recentTerminal": 107,
|
||||
"recentWilsonLowerBound": 0.14772120660505175,
|
||||
"qualityFactor": 0.4498586899253121,
|
||||
"queueFactor": 1.0706027680107695,
|
||||
"queueWeight": 1.0706027680107695,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.22727272727272727,
|
||||
"recentTerminal": 110,
|
||||
"recentWilsonLowerBound": 0.15894521607203976,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.43931787511410003,
|
||||
"selectionWeight": 0.4816199586477376,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.833333333333332,
|
||||
"waiting": 10603
|
||||
"throughputPerHour": 18.333333333333332,
|
||||
"waiting": 10615
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 684.375,
|
||||
"backlogHours": 684.125,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.5284246032567707,
|
||||
"queueFactor": 1.0421918364275486,
|
||||
"queueWeight": 1.0421918364275486,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.23958333333333334,
|
||||
"qualityFactor": 0.5499209007051823,
|
||||
"queueFactor": 1.0441426297529484,
|
||||
"queueWeight": 1.0441426297529484,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.25,
|
||||
"recentTerminal": 96,
|
||||
"recentWilsonLowerBound": 0.16528105536529172,
|
||||
"recentWilsonLowerBound": 0.17413849417796742,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.5507198076816726,
|
||||
"selectionWeight": 0.574195855418419,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 16.0,
|
||||
"waiting": 10950
|
||||
"waiting": 10946
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2007.0461538461536,
|
||||
"backlogHours": 1976.5454545454545,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.223347318928749,
|
||||
"queueFactor": 0.886866363402042,
|
||||
"queueWeight": 0.886866363402042,
|
||||
"qualityFactor": 1.9896056161874065,
|
||||
"queueFactor": 0.8905209183965654,
|
||||
"queueWeight": 0.8905209183965654,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.4307692307692308,
|
||||
"recentTerminal": 65,
|
||||
"recentWilsonLowerBound": 0.31759267537345776,
|
||||
"recentSuccessRate": 0.42424242424242425,
|
||||
"recentTerminal": 66,
|
||||
"recentWilsonLowerBound": 0.31242322955377905,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.9718119513180197,
|
||||
"selectionWeight": 1.7717854205741737,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 10.833333333333334,
|
||||
"waiting": 21743
|
||||
"throughputPerHour": 11.0,
|
||||
"waiting": 21742
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 5234.333333333333,
|
||||
"backlogHours": 5234.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.262887733112932,
|
||||
"queueFactor": 0.7680908314669678,
|
||||
"queueWeight": 0.7680908314669678,
|
||||
"qualityFactor": 1.1716669634159769,
|
||||
"queueFactor": 0.7694937357765416,
|
||||
"queueWeight": 0.7694937357765416,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.4444444444444444,
|
||||
"recentTerminal": 18,
|
||||
"recentWilsonLowerBound": 0.24559231101389123,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.970012488976146,
|
||||
"selectionWeight": 0.9015903887649165,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 3.0,
|
||||
"waiting": 15703
|
||||
"waiting": 15702
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1573.418181818182,
|
||||
"backlogHours": 1699.4117647058824,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.06339684947274064,
|
||||
"queueFactor": 0.9198460818773394,
|
||||
"queueWeight": 0.9198460818773394,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.12727272727272726,
|
||||
"recentTerminal": 55,
|
||||
"recentWilsonLowerBound": 0.06304130417480196,
|
||||
"qualityFactor": 0.10402027436196304,
|
||||
"queueFactor": 0.9109307305557416,
|
||||
"queueWeight": 0.9109307305557416,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.1568627450980392,
|
||||
"recentTerminal": 51,
|
||||
"recentWilsonLowerBound": 0.08169125888021325,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.05831534359086795,
|
||||
"selectionWeight": 0.09475526451715166,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.166666666666666,
|
||||
"waiting": 14423
|
||||
"throughputPerHour": 8.5,
|
||||
"waiting": 14445
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 845.4690265486727,
|
||||
"backlogHours": 860.7027027027027,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.8083612858986949,
|
||||
"queueFactor": 1.0096646057989307,
|
||||
"queueWeight": 1.0096646057989307,
|
||||
"qualityFactor": 0.7812802606287282,
|
||||
"queueFactor": 1.0087932588693656,
|
||||
"queueWeight": 1.0087932588693656,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.2743362831858407,
|
||||
"recentTerminal": 113,
|
||||
"recentWilsonLowerBound": 0.2005129306491566,
|
||||
"recentSuccessRate": 0.27927927927927926,
|
||||
"recentTerminal": 111,
|
||||
"recentWilsonLowerBound": 0.20427535700815577,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.8161737790700225,
|
||||
"selectionWeight": 0.788150260209962,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.833333333333332,
|
||||
"throughputPerHour": 18.5,
|
||||
"waiting": 15923
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-21T09:54:22.177158+00:00",
|
||||
"queueAttemptedAt": "2026-09-21T10:05:23.787223+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-21T09:54:22.177158+00:00",
|
||||
"queueUpdatedAt": "2026-09-21T10:05:23.787223+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Kunlunxin_p-800",
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
{
|
||||
"catalogUpdatedAt": "2026-09-21T10:04:10.177617+00:00",
|
||||
"catalogUpdatedAt": "2026-09-21T10:05:23.787223+00:00",
|
||||
"configuredTaskTypes": [
|
||||
"text-generation"
|
||||
],
|
||||
@@ -56,7 +56,7 @@
|
||||
"time-series-forecasting"
|
||||
],
|
||||
"errors": [],
|
||||
"generatedAt": "2026-09-21T10:04:10.177617+00:00",
|
||||
"generatedAt": "2026-09-21T10:05:23.787223+00:00",
|
||||
"gpuCatalog": {
|
||||
"Ascend_910-b3": {
|
||||
"canVerify": true,
|
||||
@@ -6520,6 +6520,6 @@
|
||||
"updateTime": "2025-12-22 08:59:53"
|
||||
}
|
||||
],
|
||||
"taskTreeUpdatedAt": "2026-09-21T10:04:10.177617+00:00",
|
||||
"taskTreeUpdatedAt": "2026-09-21T10:05:23.787223+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-21T10:01:40.168106+00:00",
|
||||
"lastSyncTime": "2026-09-21T10:01:37.498157+00:00",
|
||||
"generatedAt": "2026-09-21T10:05:14.010504+00:00",
|
||||
"lastSyncTime": "2026-09-21T10:05:11.455599+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2961,11 +2961,11 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 21,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 30,
|
||||
"ambiguous_runtime": 31,
|
||||
"framework_architecture_unsupported": 21,
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 52,
|
||||
"failureCount": 53,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
@@ -2975,8 +2975,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 52,
|
||||
"unresolvedFailureCount": 30
|
||||
"total": 53,
|
||||
"unresolvedFailureCount": 31
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 201,
|
||||
@@ -5446,7 +5446,7 @@
|
||||
"decisionSuccessRate": 0.0317,
|
||||
"decisionTotal": 63,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 52,
|
||||
"ambiguous_runtime": 53,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 56,
|
||||
"memory_capacity": 1,
|
||||
@@ -5455,18 +5455,18 @@
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 19
|
||||
},
|
||||
"failureCount": 133,
|
||||
"failureRate": 0.9852,
|
||||
"failureCount": 134,
|
||||
"failureRate": 0.9853,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0148,
|
||||
"total": 135,
|
||||
"unresolvedFailureCount": 71
|
||||
"successRate": 0.0147,
|
||||
"total": 136,
|
||||
"unresolvedFailureCount": 72
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-21T10:01:40.113915+00:00",
|
||||
"generatedAt": "2026-09-21T10:05:13.998246+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 91,
|
||||
@@ -5500,7 +5500,7 @@
|
||||
"decisionSuccessRate": 0.164,
|
||||
"decisionTotal": 378,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 162,
|
||||
"ambiguous_runtime": 163,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 175,
|
||||
"memory_capacity": 18,
|
||||
@@ -5512,15 +5512,15 @@
|
||||
"日志缺失": 14,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 931,
|
||||
"failureCount": 932,
|
||||
"failureRate": 0.9376,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 62,
|
||||
"successRate": 0.0624,
|
||||
"total": 993,
|
||||
"unresolvedFailureCount": 613
|
||||
"total": 994,
|
||||
"unresolvedFailureCount": 614
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 182,
|
||||
@@ -7008,9 +7008,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 2
|
||||
"ambiguous_runtime": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "phi3",
|
||||
@@ -7022,8 +7022,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 2
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -15427,12 +15427,12 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 7,
|
||||
"ambiguous_runtime": 6,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"参数/模板问题": 4
|
||||
},
|
||||
"failureCount": 13,
|
||||
"failureCount": 12,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -15444,8 +15444,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 13,
|
||||
"unresolvedFailureCount": 11
|
||||
"total": 12,
|
||||
"unresolvedFailureCount": 10
|
||||
},
|
||||
"Ascend_910-b3|vllm|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
@@ -15506,9 +15506,10 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastPlatformFailureAt": "2026-09-20T03:41:42.246689+00:00",
|
||||
@@ -15520,8 +15521,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
@@ -16305,31 +16306,6 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
|
||||
"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": "2026-09-21T04:15:31.153931+00:00",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b3",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mpt|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
@@ -16431,6 +16407,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors": {
|
||||
"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": "2026-09-21T10:05:11.455599+00:00",
|
||||
"modelType": "phi3",
|
||||
"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
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen2|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -21365,6 +21366,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|31": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 31,
|
||||
"modelType": "phi3",
|
||||
"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
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|phi3|compressed-tensors|32": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -33470,15 +33495,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 16208,
|
||||
"totalRecords": 16391,
|
||||
"terminalRecords": 16209,
|
||||
"totalRecords": 16392,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5864,
|
||||
"decisionFailureRate": 0.8615,
|
||||
"decisionSuccessRate": 0.1385,
|
||||
"decisionTotal": 6807,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3910,
|
||||
"ambiguous_runtime": 3911,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
@@ -33494,31 +33519,31 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 674
|
||||
},
|
||||
"failureCount": 15265,
|
||||
"failureCount": 15266,
|
||||
"failureRate": 0.9418,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 924,
|
||||
"successCount": 943,
|
||||
"successRate": 0.0582,
|
||||
"total": 16208,
|
||||
"unresolvedFailureCount": 8477
|
||||
"total": 16209,
|
||||
"unresolvedFailureCount": 8478
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -33558,6 +33583,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16391,
|
||||
"summarizedRecords": 16392,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -266,6 +266,7 @@
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T01:08:25.664296+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T03:25:32.245630+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969647", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T02:15:17.867315+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T03:25:31.995522+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969637", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T08:25:31.485651+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430847031, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430847031}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:31.991647+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969636", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T10:05:11.455599+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2263018168, "estimatedRequiredGiB": 2.532, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 2265562651, "modelscopeLicense": "llama2", "modelscopeParams": 3821079552, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2265562651}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:24.247231+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969623", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:42:10.765050+00:00", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:24.240446+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969618", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:42:10.765072+00:00", "modelId": "OpenBMB/BitCPM-CANN-8B", "modelProfile": {"architectures": ["MiniCPMForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16370604914, "estimatedRequiredGiB": 18.305, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpm", "modelscopeFileSize": 16378634956, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:minicpm", "library:pytorch", "library:transformer", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16378634956}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:25:24.238793+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969621", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T01:08:25.664243+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-20T03:24:23.636965+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969578", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754995+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.238662+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969344", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T05:07:16.468537+00:00", "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.153275+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969341", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754892+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.150831+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969343", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T04:15:31.153931+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6711252896, "estimatedRequiredGiB": 7.503, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6713123803, "modelscopeLicense": "mit", "modelscopeParams": 3355609600, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6713123803}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T03:09:18.145895+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969340", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.20.2",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "92aebe37291dca7ddf43be2b0a88aa8fd2fae42c2dcf992a460d91dd832ae1d9",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "1a8931a0c81a60e06cb37207e46b8c859917ed6ecc689b457d3734dd877e7484",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "7137f3d2a0839d9b4d5d56fd8a19241ff4936d3a1189f600d69449e4378e154c",
|
||||
".modelhub_state/official_capabilities.json": "5507d05e1ad30b2219fe78fc92452733c658b88aaead261c9930435da5717a1c",
|
||||
".modelhub_state/outcome_checkpoint.json": "e1ad7f46757ef970014f639f7a3b188d5f9b06dd33960fcfa9cebbce8254fb5c",
|
||||
".modelhub_state/market_intelligence.json": "39e359de948e0bd4f5a70c08eee6f71a98e5f3c180970c30ca391e298ae7328c",
|
||||
".modelhub_state/official_capabilities.json": "c3ae789af91b4c7001fa1b818a8563b076883b3f50d153c6218992ed722a8e2b",
|
||||
".modelhub_state/outcome_checkpoint.json": "6a85314b855a7379636957e38c2a203dcfaa1fd7b651132d52f51e972add48f2",
|
||||
".modelhub_state/queue_cleanup_latest.json": "f4afc5dbbf57b883780778e798518d72ad1770b7d52c2f9efa7ac7bca07813f7",
|
||||
".modelhub_state/recent_outcomes.jsonl": "8d57f7d5519984203fbd32c745b275356c1149ef8eaed29c15fb125cc3a904ba",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "a694b1a9e35152995cb302b646590f7cec5be62abbbdf3aad6a8bddcda44c61a",
|
||||
".modelhub_state/recovery_intents.jsonl": "ba5733af79e9590e1acbccc0cf39546eb714fd755b0b13acb52f49687c8b8f86",
|
||||
".modelhub_state/recent_outcomes.jsonl": "4048d7521696df671c525091f8381c845004f134c14b71c03c52b03a037590ac",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "2a8614934866717c284167d475c31036aacb7143c15ff60fb65793ad8b97159b",
|
||||
".modelhub_state/recovery_intents.jsonl": "7578ac402259ba273df2c6c37f7a7e02fc9b1fcb290de72bdc1b3999820ffbc0",
|
||||
".modelhub_state/routing_intelligence.json": "b74967b2f36e5e3e4ccf187ed4919ab22f86e688d61337513590a4e2d68e45cb",
|
||||
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
|
||||
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
|
||||
"ledger/submissions.jsonl": "12e5a0e74212526ca79a9b5eddf218e65037c277fe261ab92e906ba00cf292bf",
|
||||
"outcomes/submissions.jsonl": "81909c562ff7ce9afaf1535b6ccadcc7c9a9d06c655957e56e75a84d65488d9e"
|
||||
"outcomes/submissions.jsonl": "020ed5cf53e2d8cf979d3f03b423204594635b24d296a03721e57c11189e7c76"
|
||||
},
|
||||
"generation": 11384,
|
||||
"generation": 11385,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-21T10:04:10.585873+00:00",
|
||||
"updatedAt": "2026-09-21T10:05:25.845944+00:00",
|
||||
"writerId": "8b35139af6674067a339a670222d4b67"
|
||||
}
|
||||
|
||||
@@ -470,7 +470,6 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599823+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "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": 507443052, "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": 507443052}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:24:23.763508+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969572", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600428+00:00", "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T03:25:24.191660+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969616", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600358+00:00", "modelId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720442075, "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": 8720442075}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.243163+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969622", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599816+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2263018168, "estimatedRequiredGiB": 2.532, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 2265562651, "modelscopeLicense": "llama2", "modelscopeParams": 3821079552, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2265562651}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.247231+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969623", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599757+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857298896, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860673720, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860673720}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.195140+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969615", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.599998+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19342796520, "estimatedRequiredGiB": 21.64, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 19362750397, "modelscopeLicense": "other", "modelscopeParams": 18237772608, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19362750397}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.244532+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969625", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.599941+00:00", "modelId": "sapientinc/HRM-Text-1B", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2365606568, "estimatedRequiredGiB": 2.651, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 2371660433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1182795264, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:hrm", "custom_tag:hierarchical-reasoning", "custom_tag:prefix-lm", "custom_tag:pre-alignment", "custom_tag:non-chat", "custom_tag:non-instruction-tuned"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2371660433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.193729+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969617", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -993,7 +992,7 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T09:58:02.958221+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4018332584, "estimatedRequiredGiB": 4.494, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4020783717, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "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": "2026-09-21T00:42:10.765015+00:00", "modelType": "phi3", "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": 4020783717}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:54:23.239188+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4991516", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:58:02.958201+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504988}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:54:23.235347+00:00", "targetGpu": "Biren_166m", "taskId": "4991515", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:01:37.498148+00:00", "modelId": "aisingapore/SEA-LION-v1-7B", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15003361968, "estimatedRequiredGiB": 16.773, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 15008115847, "modelscopeLicense": "mit", "modelscopeParams": 7501651968, "modelscopeTags": ["license:mit", "model_type:mpt", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15008115847}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:57:56.851808+00:00", "targetGpu": "Biren_166m", "taskId": "4991645", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": null, "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19342796520, "estimatedRequiredGiB": 21.64, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 19362750397, "modelscopeLicense": "other", "modelscopeParams": 18237772608, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19362750397}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:02:02.598580+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991686", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-21T10:05:11.455577+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "bb5d6992290b1b4fa8f4c37e884585a27bef87a1ebfb58e5ca8f098924550f05", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19342796520, "estimatedRequiredGiB": 21.64, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 19362750397, "modelscopeLicense": "other", "modelscopeParams": 18237772608, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19362750397}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:02:02.598580+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4991686", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "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": "pending", "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_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8308282608, "estimatedRequiredGiB": 9.319, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 8338221450, "modelscopeLicense": "llama2", "modelscopeParams": 12247782400, "modelscopeTags": ["license:llama2", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8338221450}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:32.701292+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4991785", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195467, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "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", "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": 2018195467}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-21T02:07:32.882713+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4991786", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user