state: generation 10831 (cycle)
This commit is contained in:
@@ -908,7 +908,7 @@
|
||||
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 6,
|
||||
"evidenceCount": 5,
|
||||
"expiresAt": "2026-10-20T18:51:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-20T18:51:21+00:00",
|
||||
@@ -2146,7 +2146,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T19:19:40.807962+00:00",
|
||||
"generatedAt": "2026-09-20T19:33:34.912187+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 105,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-20T19:07:40.748006+00:00",
|
||||
"communityAttemptedAt": "2026-09-20T19:33:34.924035+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-20T19:07:40.748006+00:00",
|
||||
"communityUpdatedAt": "2026-09-20T19:33:34.924035+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-20T17:22:53.568270+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -425,121 +425,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-20T19:22:05.928238+00:00",
|
||||
"generatedAt": "2026-09-20T19:33:34.924035+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 936.476821192053,
|
||||
"backlogHours": 924.0784313725491,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.7429814807472412,
|
||||
"queueFactor": 0.9978296271700628,
|
||||
"queueWeight": 0.9978296271700628,
|
||||
"qualityFactor": 0.8720057078999777,
|
||||
"queueFactor": 0.999491884510734,
|
||||
"queueWeight": 0.999491884510734,
|
||||
"recentSuccess": 43,
|
||||
"recentSuccessRate": 0.2847682119205298,
|
||||
"recentTerminal": 151,
|
||||
"recentWilsonLowerBound": 0.218822241459768,
|
||||
"recentSuccessRate": 0.28104575163398693,
|
||||
"recentTerminal": 153,
|
||||
"recentWilsonLowerBound": 0.21585451117980445,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.741368933928281,
|
||||
"selectionWeight": 0.8715626282930653,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 25.166666666666668,
|
||||
"waiting": 23568
|
||||
"throughputPerHour": 25.5,
|
||||
"waiting": 23564
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1310.2153846153844,
|
||||
"backlogHours": 1320.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.3924904469989587,
|
||||
"queueFactor": 0.9488106381389626,
|
||||
"queueWeight": 0.9488106381389626,
|
||||
"recentSuccess": 48,
|
||||
"recentSuccessRate": 0.36923076923076925,
|
||||
"recentTerminal": 130,
|
||||
"recentWilsonLowerBound": 0.29113735563740545,
|
||||
"qualityFactor": 1.8083922067820868,
|
||||
"queueFactor": 0.9474351815026946,
|
||||
"queueWeight": 0.9474351815026946,
|
||||
"recentSuccess": 49,
|
||||
"recentSuccessRate": 0.3798449612403101,
|
||||
"recentTerminal": 129,
|
||||
"recentWilsonLowerBound": 0.30071077692282255,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.3212097496194912,
|
||||
"selectionWeight": 1.7133343986606449,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 21.666666666666668,
|
||||
"waiting": 28388
|
||||
"throughputPerHour": 21.5,
|
||||
"waiting": 28380
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 197.72185430463574,
|
||||
"backlogHours": 197.96026490066225,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.24242729411672975,
|
||||
"queueFactor": 1.2600063922188034,
|
||||
"queueWeight": 1.2600063922188034,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.18543046357615894,
|
||||
"qualityFactor": 0.32165746706792336,
|
||||
"queueFactor": 1.259357095038396,
|
||||
"queueWeight": 1.259357095038396,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.19205298013245034,
|
||||
"recentTerminal": 151,
|
||||
"recentWilsonLowerBound": 0.1315231360298444,
|
||||
"recentWilsonLowerBound": 0.1371784261383071,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.3054599402353874,
|
||||
"selectionWeight": 0.4050816133240685,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 25.166666666666668,
|
||||
"waiting": 4976
|
||||
"waiting": 4982
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1769.6470588235295,
|
||||
"backlogHours": 1768.9411764705883,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 1.0242579808841232,
|
||||
"queueFactor": 0.9069805019302394,
|
||||
"queueWeight": 0.9069805019302394,
|
||||
"qualityFactor": 1.2387892492962942,
|
||||
"queueFactor": 0.9067312600185927,
|
||||
"queueWeight": 0.9067312600185927,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.37254901960784315,
|
||||
"recentTerminal": 51,
|
||||
"recentWilsonLowerBound": 0.25320329720990103,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.9289820176083357,
|
||||
"selectionWeight": 1.1232489369119154,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.5,
|
||||
"waiting": 15042
|
||||
"waiting": 15036
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 461.900826446281,
|
||||
"backlogHours": 490.10526315789474,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.21012579369154263,
|
||||
"queueFactor": 1.1094267640717776,
|
||||
"queueWeight": 1.1094267640717776,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.18181818181818182,
|
||||
"recentTerminal": 121,
|
||||
"recentWilsonLowerBound": 0.12324630475994339,
|
||||
"qualityFactor": 0.2564701604785473,
|
||||
"queueFactor": 1.0992391617214785,
|
||||
"queueWeight": 1.0992391617214785,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.18421052631578946,
|
||||
"recentTerminal": 114,
|
||||
"recentWilsonLowerBound": 0.12375939628073249,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.2331191793432221,
|
||||
"selectionWeight": 0.2819220442110114,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.166666666666668,
|
||||
"waiting": 9315
|
||||
"throughputPerHour": 19.0,
|
||||
"waiting": 9312
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 41.02209944751381,
|
||||
"backlogHours": 41.119113573407205,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -548,197 +548,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.058011049723756904,
|
||||
"recentTerminal": 362,
|
||||
"recentWilsonLowerBound": 0.03825223873227009,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.06371191135734072,
|
||||
"recentTerminal": 361,
|
||||
"recentWilsonLowerBound": 0.04282606853752132,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 60.333333333333336,
|
||||
"waiting": 2475
|
||||
"throughputPerHour": 60.166666666666664,
|
||||
"waiting": 2474
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 93.74050632911393,
|
||||
"backlogHours": 100.43389830508475,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.08282877091684923,
|
||||
"qualityFactor": 0.11679517071717828,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.11075949367088607,
|
||||
"recentTerminal": 316,
|
||||
"recentWilsonLowerBound": 0.08072387859383849,
|
||||
"recentSuccessRate": 0.11864406779661017,
|
||||
"recentTerminal": 295,
|
||||
"recentWilsonLowerBound": 0.08655656627752173,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.107677402191904,
|
||||
"selectionWeight": 0.15183372193233177,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 52.666666666666664,
|
||||
"waiting": 4937
|
||||
"throughputPerHour": 49.166666666666664,
|
||||
"waiting": 4938
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2937.090909090909,
|
||||
"backlogHours": 3126.5806451612902,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8406076562292617,
|
||||
"queueWeight": 0.8406076562292617,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.5454545454545454,
|
||||
"recentTerminal": 33,
|
||||
"recentWilsonLowerBound": 0.3798565794374957,
|
||||
"queueFactor": 0.8324825750946072,
|
||||
"queueWeight": 0.8324825750946072,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.5161290322580645,
|
||||
"recentTerminal": 31,
|
||||
"recentWilsonLowerBound": 0.3484011828697317,
|
||||
"running": 2,
|
||||
"selectionWeight": 2.101519140573154,
|
||||
"selectionWeight": 2.081206437736518,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.5,
|
||||
"throughputPerHour": 5.166666666666667,
|
||||
"waiting": 16154
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 590.5321100917431,
|
||||
"backlogHours": 585.1090909090909,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.33650325365012146,
|
||||
"queueFactor": 1.0692873327091696,
|
||||
"queueWeight": 1.0692873327091696,
|
||||
"qualityFactor": 0.3986199154808131,
|
||||
"queueFactor": 1.0704097846258247,
|
||||
"queueWeight": 1.0704097846258247,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.22018348623853212,
|
||||
"recentTerminal": 109,
|
||||
"recentWilsonLowerBound": 0.1526627048081528,
|
||||
"recentSuccessRate": 0.21818181818181817,
|
||||
"recentTerminal": 110,
|
||||
"recentWilsonLowerBound": 0.15122852088416214,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.35981866654349554,
|
||||
"selectionWeight": 0.4266866578773816,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.166666666666668,
|
||||
"waiting": 10728
|
||||
"throughputPerHour": 18.333333333333332,
|
||||
"waiting": 10727
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 469.22535211267603,
|
||||
"backlogHours": 479.3093525179856,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.20617927616303047,
|
||||
"queueFactor": 1.10681166909922,
|
||||
"queueWeight": 1.10681166909922,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.176056338028169,
|
||||
"recentTerminal": 142,
|
||||
"recentWilsonLowerBound": 0.1221886925217712,
|
||||
"qualityFactor": 0.20940249634895772,
|
||||
"queueFactor": 1.1029179672601153,
|
||||
"queueWeight": 1.1029179672601153,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.16546762589928057,
|
||||
"recentTerminal": 139,
|
||||
"recentWilsonLowerBound": 0.11286341507330147,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.22820162878367278,
|
||||
"selectionWeight": 0.23095377561238614,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.666666666666668,
|
||||
"waiting": 11105
|
||||
"throughputPerHour": 23.166666666666668,
|
||||
"waiting": 11104
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1754.1081081081081,
|
||||
"backlogHours": 1778.4657534246576,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.8182921080735044,
|
||||
"queueFactor": 0.9081811764341233,
|
||||
"queueWeight": 0.9081811764341233,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.32432432432432434,
|
||||
"recentTerminal": 74,
|
||||
"recentWilsonLowerBound": 0.22863921647459504,
|
||||
"qualityFactor": 0.9095898145821663,
|
||||
"queueFactor": 0.906001196453494,
|
||||
"queueWeight": 0.906001196453494,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.3150684931506849,
|
||||
"recentTerminal": 73,
|
||||
"recentWilsonLowerBound": 0.22003473675403795,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.743157489376954,
|
||||
"selectionWeight": 0.8240894602933544,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.333333333333334,
|
||||
"waiting": 21634
|
||||
"throughputPerHour": 12.166666666666666,
|
||||
"waiting": 21638
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 4270.363636363637,
|
||||
"backlogHours": 4270.909090909091,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.39185252724199937,
|
||||
"queueFactor": 0.794714653370167,
|
||||
"queueWeight": 0.794714653370167,
|
||||
"qualityFactor": 0.4739262052300172,
|
||||
"queueFactor": 0.7944334976839765,
|
||||
"queueWeight": 0.7944334976839765,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.3181818181818182,
|
||||
"recentTerminal": 22,
|
||||
"recentWilsonLowerBound": 0.16360387354692477,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.31141094535934943,
|
||||
"selectionWeight": 0.37650285286497664,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 3.6666666666666665,
|
||||
"waiting": 15658
|
||||
"waiting": 15660
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1802.375,
|
||||
"backlogHours": 1880.7391304347825,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9044908469745102,
|
||||
"queueWeight": 0.9044908469745102,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.10416666666666667,
|
||||
"recentTerminal": 48,
|
||||
"recentWilsonLowerBound": 0.04532105090117825,
|
||||
"queueFactor": 0.8984342778022876,
|
||||
"queueWeight": 0.8984342778022876,
|
||||
"recentSuccess": 4,
|
||||
"recentSuccessRate": 0.08695652173913043,
|
||||
"recentTerminal": 46,
|
||||
"recentWilsonLowerBound": 0.03433531187670748,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.04522454234872551,
|
||||
"selectionWeight": 0.04492171389011438,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 8.0,
|
||||
"throughputPerHour": 7.666666666666667,
|
||||
"waiting": 14419
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 909.5428571428571,
|
||||
"backlogHours": 917.8269230769231,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.5023348470668136,
|
||||
"queueFactor": 1.002207098453722,
|
||||
"queueWeight": 1.002207098453722,
|
||||
"qualityFactor": 0.620989901650416,
|
||||
"queueFactor": 1.0005101026222207,
|
||||
"queueWeight": 1.0005101026222207,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.2571428571428571,
|
||||
"recentTerminal": 105,
|
||||
"recentWilsonLowerBound": 0.18315791773630993,
|
||||
"recentSuccessRate": 0.25961538461538464,
|
||||
"recentTerminal": 104,
|
||||
"recentWilsonLowerBound": 0.1849887491976701,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.5034435495310254,
|
||||
"selectionWeight": 0.6213066702276204,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.5,
|
||||
"waiting": 15917
|
||||
"throughputPerHour": 17.333333333333332,
|
||||
"waiting": 15909
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-20T19:18:26.620003+00:00",
|
||||
"queueAttemptedAt": "2026-09-20T19:33:34.924035+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-20T19:18:26.620003+00:00",
|
||||
"queueUpdatedAt": "2026-09-20T19:33:34.924035+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Kunlunxin_p-800",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T19:19:40.746701+00:00",
|
||||
"lastSyncTime": "2026-09-20T19:19:40.458840+00:00",
|
||||
"generatedAt": "2026-09-20T19:33:34.854966+00:00",
|
||||
"lastSyncTime": "2026-09-20T19:33:34.552450+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -912,7 +912,7 @@
|
||||
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 6,
|
||||
"evidenceCount": 5,
|
||||
"expiresAt": "2026-10-20T18:51:21+00:00",
|
||||
"framework": "vllm",
|
||||
"latestFailureAt": "2026-09-20T18:51:21+00:00",
|
||||
@@ -4533,18 +4533,18 @@
|
||||
"unresolvedFailureCount": 72
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation": {
|
||||
"attributableFailureCount": 23,
|
||||
"attributableFailureCount": 24,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 23,
|
||||
"decisionTotal": 24,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"model_load": 3,
|
||||
"runtime_memory": 6,
|
||||
"runtime_memory": 7,
|
||||
"参数/模板问题": 8
|
||||
},
|
||||
"failureCount": 43,
|
||||
"failureCount": 44,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -4554,14 +4554,14 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 43,
|
||||
"total": 44,
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 649,
|
||||
"attributableFailureCount": 650,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 649,
|
||||
"decisionTotal": 650,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 153,
|
||||
"architecture_compatibility": 30,
|
||||
@@ -4572,10 +4572,10 @@
|
||||
"model_load": 56,
|
||||
"platform_infrastructure": 3,
|
||||
"repository_structure": 109,
|
||||
"runtime_memory": 52,
|
||||
"runtime_memory": 53,
|
||||
"tokenizer_compatibility": 79
|
||||
},
|
||||
"failureCount": 805,
|
||||
"failureCount": 806,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -4585,7 +4585,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 805,
|
||||
"total": 806,
|
||||
"unresolvedFailureCount": 153
|
||||
},
|
||||
"hygon_k100-ai|vllm|unknown": {
|
||||
@@ -4709,10 +4709,10 @@
|
||||
"unresolvedFailureCount": 6406
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3490,
|
||||
"decisionFailureRate": 0.977,
|
||||
"decisionSuccessRate": 0.023,
|
||||
"decisionTotal": 3572,
|
||||
"attributableFailureCount": 3491,
|
||||
"decisionFailureRate": 0.9771,
|
||||
"decisionSuccessRate": 0.0229,
|
||||
"decisionTotal": 3573,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1440,
|
||||
"architecture_compatibility": 112,
|
||||
@@ -4724,18 +4724,18 @@
|
||||
"model_load": 200,
|
||||
"platform_infrastructure": 864,
|
||||
"repository_structure": 470,
|
||||
"runtime_memory": 61,
|
||||
"runtime_memory": 62,
|
||||
"tokenizer_compatibility": 409,
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 5834,
|
||||
"failureCount": 5835,
|
||||
"failureRate": 0.9861,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 864,
|
||||
"successCount": 82,
|
||||
"successRate": 0.0139,
|
||||
"total": 5916,
|
||||
"total": 5917,
|
||||
"unresolvedFailureCount": 1480
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -4779,25 +4779,25 @@
|
||||
"unresolvedFailureCount": 48
|
||||
},
|
||||
"vllm-patch-tokenizer": {
|
||||
"attributableFailureCount": 23,
|
||||
"attributableFailureCount": 24,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 23,
|
||||
"decisionTotal": 24,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"framework_architecture_unsupported": 14,
|
||||
"model_load": 3,
|
||||
"runtime_memory": 6,
|
||||
"runtime_memory": 7,
|
||||
"参数/模板问题": 8
|
||||
},
|
||||
"failureCount": 43,
|
||||
"failureCount": 44,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 43,
|
||||
"total": 44,
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"vllm_0_17_0_corex_4_4_0": {
|
||||
@@ -4870,7 +4870,7 @@
|
||||
"unresolvedFailureCount": 32
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T19:19:40.737918+00:00",
|
||||
"generatedAt": "2026-09-20T19:33:34.846545+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 78,
|
||||
@@ -5252,10 +5252,10 @@
|
||||
"unresolvedFailureCount": 1303
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"attributableFailureCount": 687,
|
||||
"decisionFailureRate": 0.9582,
|
||||
"decisionSuccessRate": 0.0418,
|
||||
"decisionTotal": 717,
|
||||
"attributableFailureCount": 689,
|
||||
"decisionFailureRate": 0.9583,
|
||||
"decisionSuccessRate": 0.0417,
|
||||
"decisionTotal": 719,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 298,
|
||||
"architecture_compatibility": 32,
|
||||
@@ -5266,20 +5266,20 @@
|
||||
"model_load": 59,
|
||||
"platform_infrastructure": 4,
|
||||
"repository_structure": 116,
|
||||
"runtime_memory": 58,
|
||||
"runtime_memory": 60,
|
||||
"tokenizer_compatibility": 79,
|
||||
"参数/模板问题": 376,
|
||||
"日志缺失": 66,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 1458,
|
||||
"failureRate": 0.9798,
|
||||
"failureCount": 1460,
|
||||
"failureRate": 0.9799,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 30,
|
||||
"successRate": 0.0202,
|
||||
"total": 1488,
|
||||
"successRate": 0.0201,
|
||||
"total": 1490,
|
||||
"unresolvedFailureCount": 767
|
||||
}
|
||||
},
|
||||
@@ -11870,6 +11870,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gpt_oss|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"runtime_memory": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none": {
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -13022,13 +13045,14 @@
|
||||
"decisionTotal": 10,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"framework_architecture_unsupported": 10
|
||||
"framework_architecture_unsupported": 9,
|
||||
"runtime_memory": 1
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-20T18:53:01.472996+00:00",
|
||||
"lastTerminalAt": "2026-09-20T19:33:34.552400+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -25099,6 +25123,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|gpt_oss|compressed-tensors|35": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"runtime_memory": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-patch-tokenizer",
|
||||
"loadSizeLog2Bucket": 35,
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm-patch-tokenizer|text-generation|lfm2|none|29": {
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -25535,13 +25583,13 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15937,
|
||||
"totalRecords": 16071,
|
||||
"terminalRecords": 15939,
|
||||
"totalRecords": 16073,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5786,
|
||||
"attributableFailureCount": 5788,
|
||||
"decisionFailureRate": 0.8614,
|
||||
"decisionSuccessRate": 0.1386,
|
||||
"decisionTotal": 6717,
|
||||
"decisionTotal": 6719,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3796,
|
||||
"architecture_compatibility": 212,
|
||||
@@ -25553,20 +25601,20 @@
|
||||
"model_load": 483,
|
||||
"platform_infrastructure": 922,
|
||||
"repository_structure": 734,
|
||||
"runtime_memory": 79,
|
||||
"runtime_memory": 81,
|
||||
"tokenizer_compatibility": 655,
|
||||
"参数/模板问题": 3110,
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 15006,
|
||||
"failureCount": 15008,
|
||||
"failureRate": 0.9416,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 931,
|
||||
"successRate": 0.0584,
|
||||
"total": 15937,
|
||||
"total": 15939,
|
||||
"unresolvedFailureCount": 8298
|
||||
},
|
||||
"warnings": [
|
||||
@@ -25612,12 +25660,12 @@
|
||||
"组合 Cambricon_mlu-370-x4|unknown|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 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 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。",
|
||||
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16071,
|
||||
"summarizedRecords": 16073,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-20T19:33:34.552400+00:00", "modelId": "nv-community/Llama-3_3-Nemotron-Super-49B-v1_5-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T19:25:22+00:00", "targetGpu": "hygon_k100-ai", "taskId": "3986841", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-20T18:53:01.472996+00:00", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:51:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4523697", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-20T18:53:01.473044+00:00", "modelId": "fla-hub/rwkv7-191M-world", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:49:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079911", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-20T18:53:01.473084+00:00", "modelId": "vllm-ascend/Qwen3-32B-w8a8sc-310-vllm-tp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T18:47:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079186", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-15T00:31:34.841419+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:31:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4597481", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-15T00:22:04.249561+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:19:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592892", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-15T00:22:04.249539+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:17:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4595877", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-15T00:03:42.210358+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:03:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592744", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.20.2",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "3341ed68c11b0e5d2d4070e7cea7d0cf4ca57192c4bcbed3e6d3ddf901323f5a",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "c894bb05dc3ab263dd6dc0268cb61ff3fdaf8dc89b2b428155453619bb706384",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "bb82475491adfe039cd92ddfd28c6b4fd15eb046bbd74e25c6ff13083aae5f53",
|
||||
".modelhub_state/official_capabilities.json": "b55ee66422c10436cc0bccbc0d57a2156f6b911afd21142f6c0206953017f4bb",
|
||||
".modelhub_state/outcome_checkpoint.json": "6806a1fd4226fe5c168360adf1e0841819bba0aff1e22248e27f7fcfb905a4aa",
|
||||
".modelhub_state/market_intelligence.json": "173f54cf6979fbd88bd114a5a55b1b9b9d6b0a6b02aa3bc57dc75c32bc55cce9",
|
||||
".modelhub_state/official_capabilities.json": "d9c48c4bb1857844ff7f0883b221371384bd16576098ab53ba2bce0a17578a61",
|
||||
".modelhub_state/outcome_checkpoint.json": "641402cdc01fee0f7706e286dbf09c8e49222965806808f84e0f1309114a36c1",
|
||||
".modelhub_state/queue_cleanup_latest.json": "51060760318808c95c5f937aac9389cef4379d95a33f6213764b0f798b1c6bb9",
|
||||
".modelhub_state/recent_outcomes.jsonl": "f156fbb10d7bf9d896602a768c2e27bf24f4c457a873ba65e8579017ffae0fc3",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "5dde8bfb37315afaea8ca2a8928c278c35f131404bb514f047cecde6a5b0f586",
|
||||
".modelhub_state/recovery_intents.jsonl": "1e51906096a67bb8e86b1aab5ad71b9d78b24b13c83f7b3f14c5838d8a7b3510",
|
||||
".modelhub_state/recent_outcomes.jsonl": "bca9f8c48e8297165b151979e7aa5bfe8599e5d21a777f6afdb66eac2b2eb59f",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "e8ed56d64ad8253048f6242471930c08c722a6bfda78e1c5532c060ea21357df",
|
||||
".modelhub_state/recovery_intents.jsonl": "6782d777e059662c8632fe51a7843d19d7d466c00123285f8e2ac52d5a2d7aa2",
|
||||
".modelhub_state/routing_intelligence.json": "48892cb3c50a4d4e48176f31a46bd388b403776ec51c76eaf349c4f64e3b2c5d",
|
||||
".modelhub_state/submission_exclusions.jsonl": "221be895a524330815b3c5124450b33c94b5f1e68169030c73684bf675d06ec7",
|
||||
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
|
||||
"ledger/submissions.jsonl": "e0dc7f394d2148c7affc6e6a0d57d1b0254d05ff4a14711eeb1037e8f3cd0f24",
|
||||
"outcomes/submissions.jsonl": "794892fa4941c9f015458e413ef3a2e4215908c642f6126e8f1fd879bd06e3ed"
|
||||
"outcomes/submissions.jsonl": "59c727ede372a4dfea1078d4e5323fa56e2721428ae42dff5e8c144410c30339"
|
||||
},
|
||||
"generation": 10830,
|
||||
"generation": 10831,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-20T19:33:31.856440+00:00",
|
||||
"updatedAt": "2026-09-20T19:33:56.347447+00:00",
|
||||
"writerId": "fc715c06e24c4db2ae3e425e435db996"
|
||||
}
|
||||
|
||||
@@ -3,7 +3,6 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T12:43:05.302313+00:00", "modelId": "b77968543/Spark-X2.5-4B-Q8_0", "modelProfile": {"architectures": [], "configFingerprint": "054a7592edf89d789e18b12765c567c3c34b2ebb58661fdd49255aad03c66d40", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 4.889, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4375025003, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "library:", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4375025003}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:40:16.372199+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611339", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T15:14:29.722109+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "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:m1", "custom_tag:m2", "custom_tag:fp16", "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T22:53:17.234593+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T14:46:47.882785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4628625", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-04T23:34:40.935439+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:15"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:32:11.649244+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4629295", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T00:55:08.690909+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:50:16.092995+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4630839", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T02:32:00.692571+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T18:26:16.665549+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632117", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:05:43.096396+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998609696, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020499228, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020499228}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:03:47.678567+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632579", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -954,9 +953,9 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473061+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124714, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124714}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:49:41.634018+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4977490", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473015+00:00", "modelId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7003604832, "estimatedRequiredGiB": 7.829, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7005626643, "modelscopeLicense": "llama2", "modelscopeParams": 6738415616, "modelscopeTags": ["license:llama2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7005626643}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:50:01.755721+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977518", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T18:53:01.472942+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014789064, "estimatedRequiredGiB": 2.255, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018175215, "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", "repositoryOnDiskBytes": 2018175215}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T10:51:35.807777+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4977519", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788612744}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:19:51.535102+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4977812", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:19:51.641136+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977829", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124576, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124576}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:20:03.373586+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977833", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:33:34.552434+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612744, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788612744}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T11:19:51.535102+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4977812", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:33:34.552425+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T11:19:51.641136+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977829", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:33:34.552441+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124576, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124576}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T11:20:03.373586+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977833", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096479112, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096479112}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:39:31.087174+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4978074", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084040952, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093261938, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "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": 9093261938}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:39:31.092445+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4978075", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "transformers", "lastSyncTime": null, "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736540899, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756990943, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756990943}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T11:44:01.235722+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4978143", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user