state: generation 25827 (intent)
This commit is contained in:
@@ -2354,7 +2354,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-19T13:29:43.661959+00:00",
|
||||
"generatedAt": "2026-10-19T14:04:19.479624+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 117,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-10-19T13:31:19.581074+00:00",
|
||||
"communityAttemptedAt": "2026-10-19T14:05:54.950440+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-10-19T13:31:19.581074+00:00",
|
||||
"communityUpdatedAt": "2026-10-19T14:05:54.950440+00:00",
|
||||
"frameworkAttemptedAt": "2026-10-19T10:53:37.915642+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -414,298 +414,298 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-19T13:31:19.581074+00:00",
|
||||
"generatedAt": "2026-10-19T14:05:54.950440+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1421.9555555555555,
|
||||
"backlogHours": 1422.088888888889,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9025046768917661,
|
||||
"queueWeight": 0.9025046768917661,
|
||||
"recentSuccess": 53,
|
||||
"recentSuccessRate": 0.3925925925925926,
|
||||
"queueFactor": 0.8978687220499478,
|
||||
"queueWeight": 0.8978687220499478,
|
||||
"recentSuccess": 49,
|
||||
"recentSuccessRate": 0.362962962962963,
|
||||
"recentTerminal": 135,
|
||||
"recentWilsonLowerBound": 0.3142817963315327,
|
||||
"recentWilsonLowerBound": 0.28667958803945254,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.256261692229415,
|
||||
"selectionWeight": 2.2446718051248697,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.5,
|
||||
"waiting": 31994
|
||||
"waiting": 31997
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 132.57142857142858,
|
||||
"backlogHours": 132.25714285714287,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.20996471945997275,
|
||||
"queueFactor": 1.2882936734791912,
|
||||
"queueWeight": 1.2882936734791912,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.14285714285714285,
|
||||
"qualityFactor": 0.35620325684203347,
|
||||
"queueFactor": 1.282150434444406,
|
||||
"queueWeight": 1.282150434444406,
|
||||
"recentSuccess": 34,
|
||||
"recentSuccessRate": 0.1619047619047619,
|
||||
"recentTerminal": 210,
|
||||
"recentWilsonLowerBound": 0.10193471154371501,
|
||||
"recentWilsonLowerBound": 0.11823369477704991,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.27049621973411614,
|
||||
"selectionWeight": 0.4567061605105255,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 35.0,
|
||||
"waiting": 4640
|
||||
"waiting": 4629
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1385.3076923076924,
|
||||
"backlogHours": 1317.8048780487804,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.3609319396546032,
|
||||
"queueFactor": 0.9060463760490683,
|
||||
"queueWeight": 0.9060463760490683,
|
||||
"qualityFactor": 0.394337442752552,
|
||||
"queueFactor": 0.908184713673282,
|
||||
"queueWeight": 0.908184713673282,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.20512820512820512,
|
||||
"recentTerminal": 78,
|
||||
"recentWilsonLowerBound": 0.13039684796163398,
|
||||
"recentSuccessRate": 0.1951219512195122,
|
||||
"recentTerminal": 82,
|
||||
"recentWilsonLowerBound": 0.12382792433083327,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.32702107592441426,
|
||||
"selectionWeight": 0.3581312375368807,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.0,
|
||||
"waiting": 18009
|
||||
"throughputPerHour": 13.666666666666666,
|
||||
"waiting": 18010
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 425.4857142857143,
|
||||
"backlogHours": 410.93793103448274,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.6726932322940828,
|
||||
"queueFactor": 1.0815575093995078,
|
||||
"queueWeight": 1.0815575093995078,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.2357142857142857,
|
||||
"recentTerminal": 140,
|
||||
"recentWilsonLowerBound": 0.17305032975689183,
|
||||
"qualityFactor": 0.6453411525121064,
|
||||
"queueFactor": 1.0816466755544307,
|
||||
"queueWeight": 1.0816466755544307,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.21379310344827587,
|
||||
"recentTerminal": 145,
|
||||
"recentWilsonLowerBound": 0.15490148025035644,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.7275564169098928,
|
||||
"selectionWeight": 0.6980311122131848,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.333333333333332,
|
||||
"waiting": 9928
|
||||
"throughputPerHour": 24.166666666666668,
|
||||
"waiting": 9931
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 76.62162162162161,
|
||||
"backlogHours": 76.5608108108108,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 24,
|
||||
"qualityFactor": 0.05,
|
||||
"qualityFactor": 0.05928766688634274,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.06756756756756757,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.0777027027027027,
|
||||
"recentTerminal": 296,
|
||||
"recentWilsonLowerBound": 0.044161675124001584,
|
||||
"recentWilsonLowerBound": 0.05233249937444344,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"selectionWeight": 0.07707396695224557,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 49.333333333333336,
|
||||
"waiting": 3780
|
||||
"waiting": 3777
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 200.325,
|
||||
"backlogHours": 178.13333333333333,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.15569270615475347,
|
||||
"queueFactor": 1.2109385129041577,
|
||||
"queueWeight": 1.2109385129041577,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.125,
|
||||
"recentTerminal": 240,
|
||||
"recentWilsonLowerBound": 0.0889788148889117,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.18853429406106118,
|
||||
"qualityFactor": 0.1340670058353061,
|
||||
"queueFactor": 1.2261400411765961,
|
||||
"queueWeight": 1.2261400411765961,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.10740740740740741,
|
||||
"recentTerminal": 270,
|
||||
"recentWilsonLowerBound": 0.07583035525600543,
|
||||
"running": 1,
|
||||
"selectionWeight": 0.16438492405532518,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 40.0,
|
||||
"waiting": 8013
|
||||
"throughputPerHour": 45.0,
|
||||
"waiting": 8016
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2030.25,
|
||||
"backlogHours": 1988.4489795918369,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.2859600569197139,
|
||||
"queueFactor": 0.8555589457130458,
|
||||
"queueWeight": 0.8555589457130458,
|
||||
"qualityFactor": 0.3339511864159958,
|
||||
"queueFactor": 0.8538364416249191,
|
||||
"queueWeight": 0.8538364416249191,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.20833333333333334,
|
||||
"recentTerminal": 48,
|
||||
"recentWilsonLowerBound": 0.11730147795889814,
|
||||
"recentSuccessRate": 0.20408163265306123,
|
||||
"recentTerminal": 49,
|
||||
"recentWilsonLowerBound": 0.11481727042813812,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.24465568481427297,
|
||||
"selectionWeight": 0.2851396926858539,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.0,
|
||||
"waiting": 16242
|
||||
"throughputPerHour": 8.166666666666666,
|
||||
"waiting": 16239
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 490.1694915254237,
|
||||
"backlogHours": 502.9565217391304,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.9934940381528063,
|
||||
"queueFactor": 1.0588402038077906,
|
||||
"queueWeight": 1.0588402038077906,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.2796610169491525,
|
||||
"recentTerminal": 118,
|
||||
"recentWilsonLowerBound": 0.20660883500092977,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.0519514298395425,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.0938173115542988,
|
||||
"queueFactor": 1.049354641258258,
|
||||
"queueWeight": 1.049354641258258,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.26956521739130435,
|
||||
"recentTerminal": 115,
|
||||
"recentWilsonLowerBound": 0.1968870391761085,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.1478022725681334,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.666666666666668,
|
||||
"throughputPerHour": 19.166666666666668,
|
||||
"waiting": 9640
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 630.972972972973,
|
||||
"backlogHours": 693.4455445544555,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.7396324296596852,
|
||||
"queueFactor": 1.0194847903398223,
|
||||
"queueWeight": 1.0194847903398223,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.25225225225225223,
|
||||
"recentTerminal": 111,
|
||||
"recentWilsonLowerBound": 0.18067547191382155,
|
||||
"qualityFactor": 0.7434992876526879,
|
||||
"queueFactor": 1.0,
|
||||
"queueWeight": 1.0,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.2376237623762376,
|
||||
"recentTerminal": 101,
|
||||
"recentWilsonLowerBound": 0.1651985046175726,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.7540440124801375,
|
||||
"selectionWeight": 0.7434992876526879,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.5,
|
||||
"throughputPerHour": 16.833333333333332,
|
||||
"waiting": 11673
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2012.8461538461538,
|
||||
"backlogHours": 2012.4615384615386,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.30146580011512913,
|
||||
"queueFactor": 0.8566645137895267,
|
||||
"queueWeight": 0.8566645137895267,
|
||||
"qualityFactor": 0.3690349101454802,
|
||||
"queueFactor": 0.8523004465131054,
|
||||
"queueWeight": 0.8523004465131054,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.19230769230769232,
|
||||
"recentTerminal": 78,
|
||||
"recentWilsonLowerBound": 0.12015101048823743,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.25825505307979774,
|
||||
"selectionWeight": 0.3145286186959165,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.0,
|
||||
"waiting": 26167
|
||||
"waiting": 26162
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 717.6,
|
||||
"backlogHours": 686.7777777777778,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.0,
|
||||
"queueWeight": 1.0,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.04516129032258064,
|
||||
"recentTerminal": 155,
|
||||
"recentWilsonLowerBound": 0.022045472650521432,
|
||||
"queueFactor": 1.0014503419875787,
|
||||
"queueWeight": 1.0014503419875787,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.04938271604938271,
|
||||
"recentTerminal": 162,
|
||||
"recentWilsonLowerBound": 0.025232188799837046,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.05,
|
||||
"selectionWeight": 0.05007251709937893,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 25.833333333333332,
|
||||
"waiting": 18538
|
||||
"throughputPerHour": 27.0,
|
||||
"waiting": 18543
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1376.6153846153845,
|
||||
"backlogHours": 1344.6,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9069022339550461,
|
||||
"queueWeight": 0.9069022339550461,
|
||||
"queueFactor": 0.9054466959243264,
|
||||
"queueWeight": 0.9054466959243264,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.08974358974358974,
|
||||
"recentTerminal": 78,
|
||||
"recentWilsonLowerBound": 0.044152447186411065,
|
||||
"recentSuccessRate": 0.0875,
|
||||
"recentTerminal": 80,
|
||||
"recentWilsonLowerBound": 0.043031454647439876,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.04534511169775231,
|
||||
"selectionWeight": 0.04527233479621632,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 13.0,
|
||||
"waiting": 17896
|
||||
"throughputPerHour": 13.333333333333334,
|
||||
"waiting": 17928
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1319.8909090909092,
|
||||
"backlogHours": 1437.6831683168318,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.445994236818528,
|
||||
"queueFactor": 0.9126445377645452,
|
||||
"queueWeight": 0.9126445377645452,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.20909090909090908,
|
||||
"recentTerminal": 110,
|
||||
"recentWilsonLowerBound": 0.1435626967427802,
|
||||
"qualityFactor": 0.5879078185698873,
|
||||
"queueFactor": 0.8964010902583698,
|
||||
"queueWeight": 0.8964010902583698,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.21782178217821782,
|
||||
"recentTerminal": 101,
|
||||
"recentWilsonLowerBound": 0.14847574440775013,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.4070342041068966,
|
||||
"selectionWeight": 0.5270012095374668,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.333333333333332,
|
||||
"waiting": 24198
|
||||
"throughputPerHour": 16.833333333333332,
|
||||
"waiting": 24201
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-10-19T13:31:19.581074+00:00",
|
||||
"queueAttemptedAt": "2026-10-19T14:05:54.950440+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-10-19T13:31:19.581074+00:00",
|
||||
"queueUpdatedAt": "2026-10-19T14:05:54.950440+00:00",
|
||||
"supportedGpus": [
|
||||
"Cambricon_mlu-370-x4",
|
||||
"Vastai_va16",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-19T13:29:43.569582+00:00",
|
||||
"lastSyncTime": "2026-10-19T13:29:43.268878+00:00",
|
||||
"generatedAt": "2026-10-19T14:04:19.379277+00:00",
|
||||
"lastSyncTime": "2026-10-19T14:04:19.066017+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -4532,40 +4532,41 @@
|
||||
"unresolvedFailureCount": 296
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 137,
|
||||
"attributableFailureCount": 138,
|
||||
"decisionFailureRate": 0.9928,
|
||||
"decisionSuccessRate": 0.0072,
|
||||
"decisionTotal": 138,
|
||||
"decisionTotal": 139,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3,
|
||||
"backend_operator": 11,
|
||||
"framework_architecture_unsupported": 29,
|
||||
"platform_infrastructure": 33,
|
||||
"memory_capacity": 1,
|
||||
"platform_infrastructure": 34,
|
||||
"tokenizer_compatibility": 97,
|
||||
"参数/模板问题": 10
|
||||
},
|
||||
"failureCount": 183,
|
||||
"failureCount": 185,
|
||||
"failureRate": 0.9946,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 33,
|
||||
"platformFailureCount": 34,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0054,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 184,
|
||||
"total": 186,
|
||||
"unresolvedFailureCount": 13
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 632,
|
||||
"attributableFailureCount": 633,
|
||||
"decisionFailureRate": 0.9829,
|
||||
"decisionSuccessRate": 0.0171,
|
||||
"decisionTotal": 643,
|
||||
"decisionTotal": 644,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 109,
|
||||
"architecture_compatibility": 43,
|
||||
"backend_operator": 31,
|
||||
"backend_operator": 32,
|
||||
"context_length": 34,
|
||||
"framework_architecture_unsupported": 153,
|
||||
"memory_capacity": 113,
|
||||
@@ -4575,7 +4576,7 @@
|
||||
"tokenizer_compatibility": 182,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 974,
|
||||
"failureCount": 975,
|
||||
"failureRate": 0.9888,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -4585,7 +4586,7 @@
|
||||
"successRate": 0.0112,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 985,
|
||||
"total": 986,
|
||||
"unresolvedFailureCount": 118
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|unknown": {
|
||||
@@ -5088,15 +5089,15 @@
|
||||
"unresolvedFailureCount": 6552
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 3703,
|
||||
"attributableFailureCount": 3704,
|
||||
"decisionFailureRate": 0.9709,
|
||||
"decisionSuccessRate": 0.0291,
|
||||
"decisionTotal": 3814,
|
||||
"decisionTotal": 3815,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1606,
|
||||
"architecture_compatibility": 112,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 96,
|
||||
"backend_operator": 97,
|
||||
"context_length": 161,
|
||||
"framework_architecture_unsupported": 1417,
|
||||
"memory_capacity": 725,
|
||||
@@ -5107,14 +5108,14 @@
|
||||
"tokenizer_compatibility": 425,
|
||||
"参数/模板问题": 89
|
||||
},
|
||||
"failureCount": 6286,
|
||||
"failureRate": 0.9826,
|
||||
"failureCount": 6287,
|
||||
"failureRate": 0.9827,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 888,
|
||||
"successCount": 111,
|
||||
"successRate": 0.0174,
|
||||
"total": 6397,
|
||||
"successRate": 0.0173,
|
||||
"total": 6398,
|
||||
"unresolvedFailureCount": 1695
|
||||
},
|
||||
"vllm-customized": {
|
||||
@@ -5212,28 +5213,28 @@
|
||||
"unresolvedFailureCount": 57
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 186,
|
||||
"decisionFailureRate": 0.9688,
|
||||
"decisionSuccessRate": 0.0312,
|
||||
"decisionTotal": 192,
|
||||
"attributableFailureCount": 187,
|
||||
"decisionFailureRate": 0.9689,
|
||||
"decisionSuccessRate": 0.0311,
|
||||
"decisionTotal": 193,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 422,
|
||||
"backend_operator": 11,
|
||||
"framework_architecture_unsupported": 55,
|
||||
"memory_capacity": 10,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 13,
|
||||
"platform_infrastructure": 33,
|
||||
"platform_infrastructure": 34,
|
||||
"tokenizer_compatibility": 97,
|
||||
"参数/模板问题": 28
|
||||
},
|
||||
"failureCount": 669,
|
||||
"failureCount": 671,
|
||||
"failureRate": 0.9911,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 33,
|
||||
"platformFailureCount": 34,
|
||||
"successCount": 6,
|
||||
"successRate": 0.0089,
|
||||
"total": 675,
|
||||
"total": 677,
|
||||
"unresolvedFailureCount": 450
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -5265,7 +5266,7 @@
|
||||
"unresolvedFailureCount": 338
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-19T13:29:43.553061+00:00",
|
||||
"generatedAt": "2026-10-19T14:04:19.361959+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 132,
|
||||
@@ -5602,32 +5603,32 @@
|
||||
"unresolvedFailureCount": 332
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 788,
|
||||
"decisionFailureRate": 0.8824,
|
||||
"decisionSuccessRate": 0.1176,
|
||||
"decisionTotal": 893,
|
||||
"attributableFailureCount": 790,
|
||||
"decisionFailureRate": 0.8827,
|
||||
"decisionSuccessRate": 0.1173,
|
||||
"decisionTotal": 895,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 165,
|
||||
"architecture_compatibility": 44,
|
||||
"backend_operator": 42,
|
||||
"backend_operator": 43,
|
||||
"context_length": 39,
|
||||
"framework_architecture_unsupported": 184,
|
||||
"memory_capacity": 113,
|
||||
"platform_infrastructure": 257,
|
||||
"memory_capacity": 114,
|
||||
"platform_infrastructure": 258,
|
||||
"repository_structure": 83,
|
||||
"runtime_memory": 1,
|
||||
"tokenizer_compatibility": 282,
|
||||
"参数/模板问题": 232,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 1474,
|
||||
"failureRate": 0.9335,
|
||||
"failureCount": 1477,
|
||||
"failureRate": 0.9336,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 257,
|
||||
"platformFailureCount": 258,
|
||||
"successCount": 105,
|
||||
"successRate": 0.0665,
|
||||
"total": 1579,
|
||||
"successRate": 0.0664,
|
||||
"total": 1582,
|
||||
"unresolvedFailureCount": 429
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -22871,6 +22872,29 @@
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|bailing_hybrid|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"memory_capacity": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "bailing_hybrid",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|bailing_moe|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -23339,22 +23363,22 @@
|
||||
"decisionTotal": 8,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 8,
|
||||
"platform_infrastructure": 1,
|
||||
"platform_infrastructure": 2,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 10,
|
||||
"failureCount": 11,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "qwen3_5_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"platformFailureCount": 2,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 10,
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
|
||||
@@ -23705,14 +23729,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq": {
|
||||
"attributableFailureCount": 2,
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 2
|
||||
"backend_operator": 3
|
||||
},
|
||||
"failureCount": 2,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "llama",
|
||||
@@ -23724,7 +23748,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|bitsandbytes": {
|
||||
@@ -54616,6 +54640,30 @@
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|bailing_hybrid|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"memory_capacity": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "bailing_hybrid",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|bailing_moe|none|34": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -55342,22 +55390,23 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 4
|
||||
"framework_architecture_unsupported": 4,
|
||||
"platform_infrastructure": 1
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "qwen3_5_moe",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"platformFailureCount": 1,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": {
|
||||
@@ -55868,14 +55917,14 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 2,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
"backend_operator": 2
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 2,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 32,
|
||||
@@ -55888,7 +55937,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq|33": {
|
||||
@@ -59996,23 +60045,23 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17900,
|
||||
"totalRecords": 18429,
|
||||
"terminalRecords": 17903,
|
||||
"totalRecords": 18432,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6335,
|
||||
"decisionFailureRate": 0.8654,
|
||||
"decisionSuccessRate": 0.1346,
|
||||
"decisionTotal": 7320,
|
||||
"attributableFailureCount": 6337,
|
||||
"decisionFailureRate": 0.8655,
|
||||
"decisionSuccessRate": 0.1345,
|
||||
"decisionTotal": 7322,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4643,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 133,
|
||||
"backend_operator": 134,
|
||||
"context_length": 327,
|
||||
"framework_architecture_unsupported": 2342,
|
||||
"memory_capacity": 1206,
|
||||
"memory_capacity": 1207,
|
||||
"model_load": 573,
|
||||
"platform_infrastructure": 969,
|
||||
"platform_infrastructure": 970,
|
||||
"repository_structure": 742,
|
||||
"runtime_memory": 101,
|
||||
"tokenizer_compatibility": 696,
|
||||
@@ -60020,19 +60069,18 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16915,
|
||||
"failureCount": 16918,
|
||||
"failureRate": 0.945,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 969,
|
||||
"platformFailureCount": 970,
|
||||
"successCount": 985,
|
||||
"successRate": 0.055,
|
||||
"total": 17900,
|
||||
"total": 17903,
|
||||
"unresolvedFailureCount": 9611
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x4 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。",
|
||||
@@ -60041,6 +60089,7 @@
|
||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -60091,6 +60140,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 18429,
|
||||
"summarizedRecords": 18432,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -3645,6 +3645,18 @@
|
||||
{"batchId": "dc8943324fd24878926b05411e7010b6", "completedAt": "2026-10-19T05:42:22.143459+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T05:16:59.066933+00:00", "framework": "vllm_tokenizer_patch", "intentId": "554b81fb9c1a4d1dab8ccec278f37473", "lastModified": "2026-10-15T14:05:57+00:00", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Diplodocus-preview-JANG_6M", "reason": null, "reconciledAt": "2026-10-19T13:58:33.787649+00:00", "repoId": "OsaurusAI/Diplodocus-preview-JANG_6M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5645005", "taskType": "text-generation"}
|
||||
{"batchId": "7d8714bb31484a34b25b1e9218a6bd5f", "completedAt": "2026-10-19T05:49:46.882158+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T05:48:25.746255+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0512ce8e35fc4e3993253c3b1048dc20", "lastModified": "2026-10-19T05:33:13+00:00", "modelAddress": "https://modelscope.cn/models/hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "reason": null, "reconciledAt": "2026-10-19T13:58:33.789107+00:00", "repoId": "hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5645467", "taskType": "text-generation"}
|
||||
{"batchId": "2f477057c7ec43eca67dacd9b9eb46d5", "completedAt": "2026-10-19T12:20:36.162545+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T11:58:25.852127+00:00", "framework": "vllm_tokenizer_patch", "intentId": "63ce37f826f14ede8c320b620a768f1d", "lastModified": "2026-10-16T15:13:58+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-7B-MLX-4bit", "reason": null, "reconciledAt": "2026-10-19T13:58:33.788272+00:00", "repoId": "IFM/Jais-3-7B-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5651876", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389432+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c7ce2b72e90c44faafcfb6f7eeea6479", "lastModified": "2026-10-19T08:34:36+00:00", "modelAddress": "https://modelscope.cn/models/XingChen-AGI/Xing4.0-29B-Intent-FP8", "repoId": "XingChen-AGI/Xing4.0-29B-Intent-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389539+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9a6d72e873a94990a39b913a4bb9b478", "lastModified": "2026-10-19T07:00:41+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-8B-W8A8", "repoId": "iluvatar-corex/Qwen3-8B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389587+00:00", "framework": "vllm_tokenizer_patch", "intentId": "77f6e57367f8469ba0109305a00595a2", "lastModified": "2026-10-19T07:29:23+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-14B-W8A8", "repoId": "iluvatar-corex/Qwen3-14B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389630+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d41faebbcb6f4105804b3a29dafd581c", "lastModified": "2026-10-17T05:39:17+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389672+00:00", "framework": "vllm_tokenizer_patch", "intentId": "75a39a835b4940dfac040e5684e21074", "lastModified": "2026-10-15T14:37:21+00:00", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-32B-FP8", "repoId": "IFM/K2-Horizon-32B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389715+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5574d22be07e4e88bb17463b8336f425", "lastModified": "2026-10-15T13:48:47+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/Qwen3-Great-Bowels-Of-Horror-FREAKSTORM-6B", "repoId": "DavidAU/Qwen3-Great-Bowels-Of-Horror-FREAKSTORM-6B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389757+00:00", "framework": "vllm_tokenizer_patch", "intentId": "41a72faf5b6f43c9860671e2ae9cbc76", "lastModified": "2026-10-15T14:01:42+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "repoId": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389800+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0c6b680cd86a4d4b896baf39256cd1a1", "lastModified": "2026-10-15T18:36:05+00:00", "modelAddress": "https://modelscope.cn/models/groxaxo/humanizer-12B-MLX-oQ5-G64", "repoId": "groxaxo/humanizer-12B-MLX-oQ5-G64", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389842+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3d9bcc230a824744b4d94d940359ebcf", "lastModified": "2026-10-19T07:32:17+00:00", "modelAddress": "https://modelscope.cn/models/StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "repoId": "StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389884+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6807bff875104fe79d51acc252a53f03", "lastModified": "2026-10-15T18:35:13+00:00", "modelAddress": "https://modelscope.cn/models/rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit", "repoId": "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389926+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cb45c40d7b344793b7b9ce623209313d", "lastModified": "2026-10-17T05:35:31+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "36bd5948fd6541f0b6b66918ca790c7f", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T14:10:16.389969+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b5439a281070481090d75135d42a682c", "lastModified": "2026-10-15T15:33:45+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "repoId": "DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "02feb7660d24463dbab1d6fb6087608f", "completedAt": "2026-10-19T13:58:25.436151+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T13:35:27.329820+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7ce427bdefea46db9c1eb21d1b63f6a5", "repoId": "DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "02feb7660d24463dbab1d6fb6087608f", "completedAt": "2026-10-19T13:58:25.436148+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T13:35:27.329778+00:00", "framework": "vllm_tokenizer_patch", "intentId": "84750c2595dc471e9b06a659c3d1b450", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "02feb7660d24463dbab1d6fb6087608f", "completedAt": "2026-10-19T13:58:25.436145+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T13:35:27.329737+00:00", "framework": "vllm_tokenizer_patch", "intentId": "53814780c1c94a7091eb33f7175383e9", "repoId": "rapid-mlx/NVIDIA-Nemotron-3.5-Bolt-74B-A9B-MLX-3bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "651df4da42bcd688cd9277b6812bbf0aa41f15249c2cf1d6bda229985e2e69c4",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "0b95ecf3bdb062421b4813856fbc0d61b03b1a32f0931b0e39e50a417e000cb7",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "8f1169717d7ec2fb6411c484bc678b70fa4635b00a69a3ba666cd04cdb0bb6ae",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "e566a8248824e16ff5b0b3c144f9ba41b844a4b279a2d7fc97c6477c04bb8321",
|
||||
".modelhub_state/official_capabilities.json": "d1eb088a45b41dfd738105e6ce8cd8a608722ea92d8443a8634aa9c80e2a1d03",
|
||||
".modelhub_state/outcome_checkpoint.json": "940b1dce16e6c1b472b421bfe3bffd9528023d5a36f882b885bb0232b1f2c4ba",
|
||||
".modelhub_state/market_intelligence.json": "aa77f90fe62d71ed9bc569dcd2e00bbac175a59a84c5b29d274f411b79800886",
|
||||
".modelhub_state/official_capabilities.json": "d218a00a81d6cecc3addd1873583c6fef557a796da5f89895669ef21f182191b",
|
||||
".modelhub_state/outcome_checkpoint.json": "2ea5336a6942ca1e9a269cef779ac12a30cfc6d9d259cd98b47bfc8eaf2fda9c",
|
||||
".modelhub_state/queue_cleanup_latest.json": "27074b03987fc2f279ccc84565fc56c4236022f976c6479d04423ecbfa20e4de",
|
||||
".modelhub_state/recent_outcomes.jsonl": "fa91981c7ed2f069f9d64d025e5739016eda9d52a36ec06064f667e592ce0db4",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "f7bd16dc60e86b22dea4e021fced201f64845e0f153877183a2d2027cccd1ebe",
|
||||
".modelhub_state/recovery_intents.jsonl": "e82d96ec5e632382321c702bb8545a5c662ff5e8224d4445c25d0baa53c4a11f",
|
||||
".modelhub_state/recovery_intents.jsonl": "de3df66d25e6de86cdcdab709451d78c35725c23105883976d7329e8d2dce3b2",
|
||||
".modelhub_state/routing_intelligence.json": "32b6fdd67a46f0f0c6b322b24c7fc31aeeb76ad6ed50146e29088273d3a449c4",
|
||||
".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b",
|
||||
".modelhub_state/worker_crashes.jsonl": "75c8a6c5605f99dfe3e7d27ff6e9c6d730e1ee3a5016c812ed5cc3137a98684c",
|
||||
"ledger/submissions.jsonl": "f9f6c9fa1bdf4c14a79dbe51d9d5d82dd18a5417fd2d628955e55aa5f9690b0b",
|
||||
"outcomes/submissions.jsonl": "6c7818c213d278f18aacafcd3c087156a2da3fd53f4555663388221fb6f63539"
|
||||
"outcomes/submissions.jsonl": "8437abae3a3bd33d76e83302a7b811ecbaf6ff96f48221aa0073abe92d687758"
|
||||
},
|
||||
"generation": 25826,
|
||||
"phase": "cycle",
|
||||
"generation": 25827,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-10-19T13:58:34.032987+00:00",
|
||||
"updatedAt": "2026-10-19T14:10:16.604014+00:00",
|
||||
"writerId": "eca444bc9fdf4bc89c9cfc2f8a9a6ac1"
|
||||
}
|
||||
|
||||
@@ -95,7 +95,6 @@
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T22:02:17.790796+00:00", "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "ec890c5fa72ce5b6a2dc821183a5c5a4672e35039ad1cfdbb4ec3edd6dfa8870", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T13:59:45.181269+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4935796", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T08:29:40.588024+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "6f6eecfdce8cb92ba7646b68356f539b9e3b22165c56b20ad43debc6f5797b02", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:19:16.727802+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4942012", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T08:40:17.761417+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "27037ea4923276909ffec48c4aaf432c445fc1dc3338331f7fc62f1a8b8c7449", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:38:36.958172+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4942203", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-19T08:54:50.387371+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "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": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:52:10.650329+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4942335", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T09:05:14.592097+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "542d431820ab22236d94f13de518d5b298cdcf7ff50b3161b528640bca46f3cb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:56:39.197981+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4942377", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T09:47:25.992989+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "28c8d3558c2c4f5aa7066e89457573be5bb7c439ae2f59b7240a1c80c37520c2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T01:39:17.100253+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4943097", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063090+00:00", "modelId": "rengensheng/Ternary-Bonsai-2-27B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "87e2d06ee2cbb5d6c759a240df54c78746d706859f9a364e78515c8f28fcc1fd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629246976, "estimatedRequiredGiB": 8.757, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7835440764, "modelscopeLicense": "apache-2.0", "modelscopeParams": 460730096, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7835440764}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.174402+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947147", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -105,7 +104,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:21:49.901659+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72670025872, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679340864, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int88", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679340864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:14:34.788367+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970568", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T12:46:14.462938+00:00", "modelId": "empero-ai/Qwen3.8-35B-A3B-Distill", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903778536, "estimatedRequiredGiB": 80.392, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71933964484, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.6", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:moe", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-15T22:59:41.110897+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 71933964484}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:42:19.067096+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4970926", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.191942+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.487823+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981859", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.191900+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.445927+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981853", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192060+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "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": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.441456+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981851", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192031+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16313701503, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.502255+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981861", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191915+00:00", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.453969+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981852", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -122,7 +120,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T01:35:45.556160+00:00", "modelId": "RedHatAI/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720441937, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720441937}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:20:14.310450+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984367", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T02:15:17.867333+00:00", "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658256, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:59:59.555224+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985000", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:02:20.757732+00:00", "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658310, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:17.970020+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985910", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T03:02:20.757780+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:32.459840+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985911", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:45:50.542869+00:00", "modelId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325064, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325064}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:30:14.636274+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986332", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T03:45:50.542801+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "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": "pending", "status": "waiting", "submitTime": "2026-09-20T19:31:34.206245+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986333", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T08:17:25.672470+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236688, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236688}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:03:59.684853+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4990026", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -1094,7 +1091,7 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T03:26:50.355272+00:00", "modelId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-BF16", "modelProfile": {"architectures": ["DoryForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7950515472, "estimatedRequiredGiB": 8.907, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "dory", "modelscopeFileSize": 7969474643, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:dory", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-labs", "custom_tag:dory"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7969474643}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-18T19:00:30.147828+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633182", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T03:26:50.355338+00:00", "modelId": "IFM/Jais-3-32B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37350407624, "estimatedRequiredGiB": 41.766, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 37371953866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779304960, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jais-3", "custom_tag:32B", "custom_tag:dense", "custom_tag:fp8", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 37371953866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-18T19:00:30.149584+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633102", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T03:26:50.355360+00:00", "modelId": "rapid-mlx/NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-MLX-3bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 42747017349, "estimatedRequiredGiB": 47.793, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 42764313592, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:nemotron", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 42764313592}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-18T19:00:30.157505+00:00", "targetGpu": "MetaX_c-500", "taskId": "5633141", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mrm8488/mistral-7b-ft-h4-no_robots_instructions", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14483530784, "estimatedRequiredGiB": 16.189, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 14485412970, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:mistral", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14485412970}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-19T05:17:00.132818+00:00", "targetGpu": "MetaX_c-500", "taskId": "5645314", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T14:04:19.065952+00:00", "modelId": "mrm8488/mistral-7b-ft-h4-no_robots_instructions", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14483530784, "estimatedRequiredGiB": 16.189, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 14485412970, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:mistral", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14485412970}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-19T05:17:00.132818+00:00", "targetGpu": "MetaX_c-500", "taskId": "5645314", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T13:29:43.268862+00:00", "modelId": "OsaurusAI/Diplodocus-preview-JANG_6M", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6938269080, "estimatedRequiredGiB": 7.778, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6959482715, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1805389824, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:finance", "custom_tag:documents", "custom_tag:spreadsheets", "custom_tag:k2_horizon", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6959482715}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-19T05:17:00.139342+00:00", "targetGpu": "MetaX_c-500", "taskId": "5645005", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "modelProfile": {"architectures": ["MiniCPMV4_7ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23953202568, "estimatedRequiredGiB": 26.804, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpmv4_7", "modelscopeFileSize": 45773, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3242913051, "modelscopeTags": ["license:apache-2.0", "model_type:minicpmv4_7", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:minicpm", "custom_tag:minicpm-v-4-7", "custom_tag:moe", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:blackwell", "custom_tag:compressed-tensors", "custom_tag:vllm", "custom_tag:llama.cpp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23983932119}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-19T05:48:26.821232+00:00", "targetGpu": "MetaX_c-500", "taskId": "5645467", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T14:04:19.065999+00:00", "modelId": "hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "modelProfile": {"architectures": ["MiniCPMV4_7ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23953202568, "estimatedRequiredGiB": 26.804, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpmv4_7", "modelscopeFileSize": 45773, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3242913051, "modelscopeTags": ["license:apache-2.0", "model_type:minicpmv4_7", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:minicpm", "custom_tag:minicpm-v-4-7", "custom_tag:moe", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:blackwell", "custom_tag:compressed-tensors", "custom_tag:vllm", "custom_tag:llama.cpp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23983932119}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-19T05:48:26.821232+00:00", "targetGpu": "MetaX_c-500", "taskId": "5645467", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "IFM/Jais-3-7B-MLX-4bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7183832504, "estimatedRequiredGiB": 8.052, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 7204697873, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2021625856, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jais-3", "custom_tag:dense", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7204697873}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-19T11:58:27.074732+00:00", "targetGpu": "MetaX_c-500", "taskId": "5651876", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user