state: generation 21744 (intent)
This commit is contained in:
@@ -2214,6 +2214,25 @@
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"metax_c-500|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"latestFailureAt": "2026-10-06T08:52:26.243503+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5",
|
||||
"sourceModelIds": [
|
||||
"ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5319978"
|
||||
],
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"metax_c-500|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": {
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectures": [],
|
||||
@@ -2798,9 +2817,9 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-07T06:19:26.568779+00:00",
|
||||
"generatedAt": "2026-10-07T06:27:34.454414+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 141,
|
||||
"activeBlockCount": 142,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 9,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 7,
|
||||
@@ -2819,7 +2838,7 @@
|
||||
"Kunlunxin_p-800|vllm": 10,
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch": 9,
|
||||
"MetaX_c-500|vllm": 1,
|
||||
"MetaX_c-500|vllm_tokenizer_patch": 1,
|
||||
"MetaX_c-500|vllm_tokenizer_patch": 2,
|
||||
"Mthreads_s4000|vllm": 6,
|
||||
"Sunrise_pt-200-x1|vllm": 3,
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
|
||||
|
||||
@@ -434,121 +434,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-07T06:26:30.151018+00:00",
|
||||
"generatedAt": "2026-10-07T06:31:48.136906+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1038.4905660377358,
|
||||
"backlogHours": 1012.8957055214723,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.6717824312000182,
|
||||
"queueFactor": 1.0077969069567145,
|
||||
"queueWeight": 1.0077969069567145,
|
||||
"recentSuccess": 57,
|
||||
"recentSuccessRate": 0.3584905660377358,
|
||||
"recentTerminal": 159,
|
||||
"recentWilsonLowerBound": 0.2880963469218176,
|
||||
"qualityFactor": 1.5912166631046574,
|
||||
"queueFactor": 1.0120103152113202,
|
||||
"queueWeight": 1.0120103152113202,
|
||||
"recentSuccess": 58,
|
||||
"recentSuccessRate": 0.3558282208588957,
|
||||
"recentTerminal": 163,
|
||||
"recentWilsonLowerBound": 0.28642382027658386,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.6848171632679547,
|
||||
"selectionWeight": 1.6103276767980494,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 26.5,
|
||||
"waiting": 27520
|
||||
"throughputPerHour": 27.166666666666668,
|
||||
"waiting": 27517
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1252.5833333333333,
|
||||
"backlogHours": 1186.7763157894738,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9798563471154698,
|
||||
"queueWeight": 0.9798563471154698,
|
||||
"recentSuccess": 61,
|
||||
"recentSuccessRate": 0.4236111111111111,
|
||||
"recentTerminal": 144,
|
||||
"recentWilsonLowerBound": 0.34591885082690016,
|
||||
"queueFactor": 0.9882442999601041,
|
||||
"queueWeight": 0.9882442999601041,
|
||||
"recentSuccess": 65,
|
||||
"recentSuccessRate": 0.4276315789473684,
|
||||
"recentTerminal": 152,
|
||||
"recentWilsonLowerBound": 0.35171898448628874,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.4496408677886743,
|
||||
"selectionWeight": 2.4706107499002603,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.0,
|
||||
"waiting": 30062
|
||||
"throughputPerHour": 25.333333333333332,
|
||||
"waiting": 30065
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 135.18556701030926,
|
||||
"backlogHours": 133.65306122448982,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.35066825384663114,
|
||||
"qualityFactor": 0.37847356731448706,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 37,
|
||||
"recentSuccessRate": 0.19072164948453607,
|
||||
"recentTerminal": 194,
|
||||
"recentWilsonLowerBound": 0.1416534504648952,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.1989795918367347,
|
||||
"recentTerminal": 196,
|
||||
"recentWilsonLowerBound": 0.149111784396013,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.4558687300006205,
|
||||
"selectionWeight": 0.4920156375088332,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 32.333333333333336,
|
||||
"waiting": 4371
|
||||
"throughputPerHour": 32.666666666666664,
|
||||
"waiting": 4366
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1408.7671232876712,
|
||||
"backlogHours": 1408.6849315068494,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.23382941629282772,
|
||||
"queueFactor": 0.962736690329389,
|
||||
"queueWeight": 0.962736690329389,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.1917808219178082,
|
||||
"qualityFactor": 0.18286808654257464,
|
||||
"queueFactor": 0.9631580711323764,
|
||||
"queueWeight": 0.9631580711323764,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.1780821917808219,
|
||||
"recentTerminal": 73,
|
||||
"recentWilsonLowerBound": 0.11782254045474991,
|
||||
"recentWilsonLowerBound": 0.10713272068797697,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.22511615834340987,
|
||||
"selectionWeight": 0.17613087350601467,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.166666666666666,
|
||||
"waiting": 17140
|
||||
"waiting": 17139
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 397.6363636363637,
|
||||
"backlogHours": 406.37142857142857,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.6054854211243794,
|
||||
"queueFactor": 1.163886123813303,
|
||||
"queueWeight": 1.163886123813303,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.24475524475524477,
|
||||
"recentTerminal": 143,
|
||||
"recentWilsonLowerBound": 0.18157189677413066,
|
||||
"qualityFactor": 0.5251562930624213,
|
||||
"queueFactor": 1.1605962789577513,
|
||||
"queueWeight": 1.1605962789577513,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.2357142857142857,
|
||||
"recentTerminal": 140,
|
||||
"recentWilsonLowerBound": 0.17305032975689183,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.7047160798179193,
|
||||
"selectionWeight": 0.6094944395994925,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.833333333333332,
|
||||
"waiting": 9477
|
||||
"throughputPerHour": 23.333333333333332,
|
||||
"waiting": 9482
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 41.5374449339207,
|
||||
"backlogHours": 41.33041575492341,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -557,197 +557,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.02643171806167401,
|
||||
"recentTerminal": 454,
|
||||
"recentWilsonLowerBound": 0.015183347737471053,
|
||||
"running": 5,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.030634573304157548,
|
||||
"recentTerminal": 457,
|
||||
"recentWilsonLowerBound": 0.01833435998100694,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 75.66666666666667,
|
||||
"waiting": 3143
|
||||
"throughputPerHour": 76.16666666666667,
|
||||
"waiting": 3148
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 156.3688524590164,
|
||||
"backlogHours": 155.14634146341464,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.07523239818656347,
|
||||
"qualityFactor": 0.08725485980883657,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.10245901639344263,
|
||||
"recentTerminal": 244,
|
||||
"recentWilsonLowerBound": 0.07036672922485303,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.09780211764253251,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.10975609756097561,
|
||||
"recentTerminal": 246,
|
||||
"recentWilsonLowerBound": 0.07653405552200385,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.11343131775148754,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 40.666666666666664,
|
||||
"waiting": 6359
|
||||
"throughputPerHour": 41.0,
|
||||
"waiting": 6361
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 1792.9615384615386,
|
||||
"backlogHours": 1864.56,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.7419461614860645,
|
||||
"queueFactor": 0.9285338879324957,
|
||||
"queueWeight": 0.9285338879324957,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.3076923076923077,
|
||||
"recentTerminal": 52,
|
||||
"recentWilsonLowerBound": 0.19914562391353519,
|
||||
"qualityFactor": 0.9298693847135451,
|
||||
"queueFactor": 0.923492120353867,
|
||||
"queueWeight": 0.923492120353867,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.34,
|
||||
"recentTerminal": 50,
|
||||
"recentWilsonLowerBound": 0.2243676963506106,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.6889221539612468,
|
||||
"selectionWeight": 0.8587270497412574,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.666666666666666,
|
||||
"waiting": 15539
|
||||
"throughputPerHour": 8.333333333333334,
|
||||
"waiting": 15538
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 359.53846153846155,
|
||||
"backlogHours": 373.92,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.09806040399899325,
|
||||
"queueFactor": 1.1816030439626988,
|
||||
"queueWeight": 1.1816030439626988,
|
||||
"qualityFactor": 0.1032258423881529,
|
||||
"queueFactor": 1.1751758130446714,
|
||||
"queueWeight": 1.1751758130446714,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.12179487179487179,
|
||||
"recentTerminal": 156,
|
||||
"recentWilsonLowerBound": 0.07937439771255031,
|
||||
"recentSuccessRate": 0.12666666666666668,
|
||||
"recentTerminal": 150,
|
||||
"recentWilsonLowerBound": 0.082610643407449,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.11586847185742243,
|
||||
"selectionWeight": 0.12130851325571869,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 26.0,
|
||||
"throughputPerHour": 25.0,
|
||||
"waiting": 9348
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 607.5963302752293,
|
||||
"backlogHours": 606.880733944954,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.1782328307858316,
|
||||
"queueFactor": 1.0921722384069021,
|
||||
"queueWeight": 1.0921722384069021,
|
||||
"recentSuccess": 45,
|
||||
"recentSuccessRate": 0.41284403669724773,
|
||||
"qualityFactor": 1.8647341565439437,
|
||||
"queueFactor": 1.0928338688153905,
|
||||
"queueWeight": 1.0928338688153905,
|
||||
"recentSuccess": 43,
|
||||
"recentSuccessRate": 0.3944954128440367,
|
||||
"recentTerminal": 109,
|
||||
"recentWilsonLowerBound": 0.32491980199339493,
|
||||
"recentWilsonLowerBound": 0.30783761244479607,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.3790054265707647,
|
||||
"selectionWeight": 2.037844642608122,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.166666666666668,
|
||||
"waiting": 11038
|
||||
"waiting": 11025
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1791.123287671233,
|
||||
"backlogHours": 1867.9714285714288,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 1.8994591759442159,
|
||||
"queueFactor": 0.9286767704011881,
|
||||
"queueWeight": 0.9286767704011881,
|
||||
"qualityFactor": 2.021623079291102,
|
||||
"queueFactor": 0.9232389412604294,
|
||||
"queueWeight": 0.9232389412604294,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.410958904109589,
|
||||
"recentTerminal": 73,
|
||||
"recentWilsonLowerBound": 0.30531095731905994,
|
||||
"recentSuccessRate": 0.42857142857142855,
|
||||
"recentTerminal": 70,
|
||||
"recentWilsonLowerBound": 0.31935124886212546,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.7639836130247766,
|
||||
"selectionWeight": 1.8664411513523662,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.166666666666666,
|
||||
"waiting": 21792
|
||||
"throughputPerHour": 11.666666666666666,
|
||||
"waiting": 21793
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 2178.3829787234044,
|
||||
"backlogHours": 2090.571428571429,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.17828792315065778,
|
||||
"queueFactor": 0.9018063088871912,
|
||||
"queueWeight": 0.9018063088871912,
|
||||
"qualityFactor": 0.15632747425650573,
|
||||
"queueFactor": 0.9077785093113998,
|
||||
"queueWeight": 0.9077785093113998,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.19148936170212766,
|
||||
"recentTerminal": 47,
|
||||
"recentWilsonLowerBound": 0.10415815605310119,
|
||||
"recentSuccessRate": 0.1836734693877551,
|
||||
"recentTerminal": 49,
|
||||
"recentWilsonLowerBound": 0.09976228838458356,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.16078117389565788,
|
||||
"selectionWeight": 0.141910721544987,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.833333333333333,
|
||||
"waiting": 17064
|
||||
"throughputPerHour": 8.166666666666666,
|
||||
"waiting": 17073
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1250.6341463414635,
|
||||
"backlogHours": 1221.357142857143,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9800852701010395,
|
||||
"queueWeight": 0.9800852701010395,
|
||||
"queueFactor": 0.9839958055412086,
|
||||
"queueWeight": 0.9839958055412086,
|
||||
"recentSuccess": 4,
|
||||
"recentSuccessRate": 0.04878048780487805,
|
||||
"recentTerminal": 82,
|
||||
"recentWilsonLowerBound": 0.019130755973884292,
|
||||
"recentSuccessRate": 0.047619047619047616,
|
||||
"recentTerminal": 84,
|
||||
"recentWilsonLowerBound": 0.01867144465444291,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.04900426350505198,
|
||||
"selectionWeight": 0.04919979027706043,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 13.666666666666666,
|
||||
"waiting": 17092
|
||||
"throughputPerHour": 14.0,
|
||||
"waiting": 17099
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1148.8648648648648,
|
||||
"backlogHours": 1180.7222222222222,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.5989284438907971,
|
||||
"queueFactor": 0.9926429496047678,
|
||||
"queueWeight": 0.9926429496047678,
|
||||
"qualityFactor": 0.6147135325421119,
|
||||
"queueFactor": 0.9890027247578006,
|
||||
"queueWeight": 0.9890027247578006,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.25225225225225223,
|
||||
"recentTerminal": 111,
|
||||
"recentWilsonLowerBound": 0.18067547191382155,
|
||||
"recentSuccessRate": 0.25925925925925924,
|
||||
"recentTerminal": 108,
|
||||
"recentWilsonLowerBound": 0.1858900560683251,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.5945220971459546,
|
||||
"selectionWeight": 0.6079533586296416,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.5,
|
||||
"waiting": 21254
|
||||
"throughputPerHour": 18.0,
|
||||
"waiting": 21253
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-10-07T06:20:59.173987+00:00",
|
||||
"queueAttemptedAt": "2026-10-07T06:31:48.136906+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-10-07T06:20:59.173987+00:00",
|
||||
"queueUpdatedAt": "2026-10-07T06:31:48.136906+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Cambricon_mlu-370-x4",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-10-07T06:08:41.731783+00:00",
|
||||
"lastSyncTime": "2026-10-07T06:08:41.663388+00:00",
|
||||
"generatedAt": "2026-10-07T06:31:48.041351+00:00",
|
||||
"lastSyncTime": "2026-10-07T06:31:47.977081+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2218,6 +2218,25 @@
|
||||
"targetGpu": "Kunlunxin_p-800",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"metax_c-500|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"latestFailureAt": "2026-10-06T08:52:26.243503+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "qwen3_5",
|
||||
"sourceModelIds": [
|
||||
"ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"5319978"
|
||||
],
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"metax_c-500|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": {
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectures": [],
|
||||
@@ -2803,7 +2822,7 @@
|
||||
}
|
||||
},
|
||||
"architectureCompatibilitySummary": {
|
||||
"activeBlockCount": 141,
|
||||
"activeBlockCount": 142,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 9,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 7,
|
||||
@@ -2822,7 +2841,7 @@
|
||||
"Kunlunxin_p-800|vllm": 10,
|
||||
"Kunlunxin_p-800|vllm_tokenizer_patch": 9,
|
||||
"MetaX_c-500|vllm": 1,
|
||||
"MetaX_c-500|vllm_tokenizer_patch": 1,
|
||||
"MetaX_c-500|vllm_tokenizer_patch": 2,
|
||||
"Mthreads_s4000|vllm": 6,
|
||||
"Sunrise_pt-200-x1|vllm": 3,
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
|
||||
@@ -4659,14 +4678,15 @@
|
||||
"unresolvedFailureCount": 66
|
||||
},
|
||||
"MetaX_c-500|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"attributableFailureCount": 3,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
"framework_architecture_unsupported": 2,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
@@ -4676,7 +4696,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|feature_emb": {
|
||||
@@ -5671,35 +5691,35 @@
|
||||
"unresolvedFailureCount": 376
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 151,
|
||||
"decisionFailureRate": 0.9379,
|
||||
"decisionSuccessRate": 0.0621,
|
||||
"decisionTotal": 161,
|
||||
"attributableFailureCount": 153,
|
||||
"decisionFailureRate": 0.9387,
|
||||
"decisionSuccessRate": 0.0613,
|
||||
"decisionTotal": 163,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 208,
|
||||
"backend_operator": 15,
|
||||
"context_length": 9,
|
||||
"framework_architecture_unsupported": 94,
|
||||
"framework_architecture_unsupported": 95,
|
||||
"memory_capacity": 2,
|
||||
"model_load": 23,
|
||||
"model_load": 24,
|
||||
"platform_infrastructure": 3,
|
||||
"repository_structure": 3,
|
||||
"runtime_memory": 3,
|
||||
"tokenizer_compatibility": 2,
|
||||
"参数/模板问题": 29
|
||||
},
|
||||
"failureCount": 391,
|
||||
"failureRate": 0.9751,
|
||||
"failureCount": 393,
|
||||
"failureRate": 0.9752,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 3,
|
||||
"successCount": 10,
|
||||
"successRate": 0.0249,
|
||||
"total": 401,
|
||||
"successRate": 0.0248,
|
||||
"total": 403,
|
||||
"unresolvedFailureCount": 237
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-07T06:08:41.714429+00:00",
|
||||
"generatedAt": "2026-10-07T06:31:48.024636+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 119,
|
||||
@@ -5974,18 +5994,18 @@
|
||||
"unresolvedFailureCount": 170
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 669,
|
||||
"decisionFailureRate": 0.8199,
|
||||
"decisionSuccessRate": 0.1801,
|
||||
"decisionTotal": 816,
|
||||
"attributableFailureCount": 671,
|
||||
"decisionFailureRate": 0.8203,
|
||||
"decisionSuccessRate": 0.1797,
|
||||
"decisionTotal": 818,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 306,
|
||||
"architecture_compatibility": 21,
|
||||
"backend_operator": 43,
|
||||
"context_length": 59,
|
||||
"framework_architecture_unsupported": 201,
|
||||
"framework_architecture_unsupported": 202,
|
||||
"memory_capacity": 85,
|
||||
"model_load": 65,
|
||||
"model_load": 66,
|
||||
"platform_infrastructure": 5,
|
||||
"repository_structure": 114,
|
||||
"runtime_memory": 2,
|
||||
@@ -5994,14 +6014,14 @@
|
||||
"日志缺失": 15,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 1441,
|
||||
"failureRate": 0.9074,
|
||||
"failureCount": 1443,
|
||||
"failureRate": 0.9075,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 5,
|
||||
"successCount": 147,
|
||||
"successRate": 0.0926,
|
||||
"total": 1588,
|
||||
"successRate": 0.0925,
|
||||
"total": 1590,
|
||||
"unresolvedFailureCount": 767
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -6140,7 +6160,7 @@
|
||||
"hygon_k100-ai": 64.0
|
||||
},
|
||||
"pendingRecords": 0,
|
||||
"policyCancelledRecords": 243,
|
||||
"policyCancelledRecords": 257,
|
||||
"profileCombinationStats": {
|
||||
"Ascend_910-b3|llamacpp|text-generation|smollm3|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -20582,6 +20602,29 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm_tokenizer_patch|text-generation|gpt_oss|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -20605,6 +20648,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|aquila3|none": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -25121,9 +25187,9 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"参数/模板问题": 5
|
||||
"参数/模板问题": 3
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -25135,8 +25201,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 5
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -25688,20 +25754,21 @@
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"MetaX_c-500|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
"framework_architecture_unsupported": 2,
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureCount": 3,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-10-07T06:05:03.160740+00:00",
|
||||
"lastTerminalAt": "2026-10-07T06:27:34.062566+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -25709,7 +25776,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"total": 3,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation": {
|
||||
@@ -28919,6 +28986,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm_tokenizer_patch|text-generation|gpt_oss|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastTerminalAt": "2026-10-07T06:27:34.062566+00:00",
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
@@ -28944,6 +29036,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastTerminalAt": "2026-10-07T06:27:34.062607+00:00",
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Mthreads_s4000|vllm|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 0,
|
||||
"consecutiveFailures": 0,
|
||||
@@ -51416,6 +51533,30 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm_tokenizer_patch|text-generation|gpt_oss|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"model_load": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "gpt_oss",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -51440,6 +51581,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|aquila3|none|12": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
@@ -58115,22 +58280,22 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 17358,
|
||||
"totalRecords": 17601,
|
||||
"terminalRecords": 17360,
|
||||
"totalRecords": 17617,
|
||||
"totals": {
|
||||
"attributableFailureCount": 6241,
|
||||
"decisionFailureRate": 0.8645,
|
||||
"decisionSuccessRate": 0.1355,
|
||||
"decisionTotal": 7219,
|
||||
"attributableFailureCount": 6243,
|
||||
"decisionFailureRate": 0.8646,
|
||||
"decisionSuccessRate": 0.1354,
|
||||
"decisionTotal": 7221,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4559,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 3,
|
||||
"backend_operator": 129,
|
||||
"context_length": 327,
|
||||
"framework_architecture_unsupported": 2264,
|
||||
"framework_architecture_unsupported": 2265,
|
||||
"memory_capacity": 1206,
|
||||
"model_load": 568,
|
||||
"model_load": 569,
|
||||
"platform_infrastructure": 952,
|
||||
"repository_structure": 742,
|
||||
"runtime_memory": 101,
|
||||
@@ -58139,14 +58304,14 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 676
|
||||
},
|
||||
"failureCount": 16380,
|
||||
"failureCount": 16382,
|
||||
"failureRate": 0.9437,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 952,
|
||||
"successCount": 978,
|
||||
"successRate": 0.0563,
|
||||
"total": 17358,
|
||||
"total": 17360,
|
||||
"unresolvedFailureCount": 9187
|
||||
},
|
||||
"warnings": [
|
||||
@@ -58187,6 +58352,7 @@
|
||||
"组合 hygon_k100-ai|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-100|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 hygon_k100-ai|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 MetaX_c-500|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x4|vllm-mlu|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|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -58207,6 +58373,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 17601,
|
||||
"summarizedRecords": 17617,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -14,13 +14,13 @@
|
||||
100
|
||||
],
|
||||
"accounts": 12,
|
||||
"activeScanned": 1154,
|
||||
"activeScanned": 1149,
|
||||
"ageCleanupMode": "admission_only",
|
||||
"agePolicySkipped": {
|
||||
"cleanupDisabled": true,
|
||||
"reason": "admission_only"
|
||||
},
|
||||
"architectureBlockCount": 141,
|
||||
"architectureBlockCount": 142,
|
||||
"architectureFrameworkCatalog": {
|
||||
"ascend_910-b3|text-generation": [
|
||||
"llamacpp",
|
||||
@@ -58,132 +58,300 @@
|
||||
]
|
||||
},
|
||||
"architectureFrameworkCatalogErrors": {},
|
||||
"architectureIncompatibleCount": 6,
|
||||
"architectureIncompatibleCount": 14,
|
||||
"architectureIncompatibleTasks": [
|
||||
{
|
||||
"accountIndex": 1,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed",
|
||||
"modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319972,
|
||||
"taskId": 5319949,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 1,
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Balance",
|
||||
"modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319981,
|
||||
"taskId": 5319931,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 5,
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
|
||||
"modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319984,
|
||||
"taskId": 5319942,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 10,
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "primitive-ai/Nex-N2.5-mini-FP8",
|
||||
"modelId": "togethercomputer/Tev1-4B-experimental",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319936,
|
||||
"taskId": 5319950,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319980,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "ukisai/Swift-1.5-5bit-MLX",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319947,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319979,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 4,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5305971,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 4,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319945,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 4,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "groxaxo/Hemmingway-1-oQ5-MLX",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5343307,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 7,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5347242,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 11,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "juspay/xor-nvfp4",
|
||||
"modelId": "ukisai/Swift-1.5-4bit-MLX",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319941,
|
||||
"taskId": 5319937,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 11,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319953,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 12,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
|
||||
"modelId": "togethercomputer/Tev1-0.8B-experimental",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319990,
|
||||
"taskId": 5319956,
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
],
|
||||
@@ -214,23 +382,23 @@
|
||||
"frameworkCatalogUnknown": 0,
|
||||
"frameworkContextUnknown": 44,
|
||||
"modelArchitectureUnknown": 159,
|
||||
"noMatchingBlock": 973,
|
||||
"noMatchingBlock": 960,
|
||||
"partiallyBlockedFrameworkSet": 16,
|
||||
"runningMatchedProtected": 0,
|
||||
"submissionContextMismatch": 0,
|
||||
"submissionContextUnknown": 0
|
||||
},
|
||||
"cancelledCount": 6,
|
||||
"cancelledCount": 14,
|
||||
"cancelledTasks": [
|
||||
{
|
||||
"accountIndex": 1,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
@@ -240,21 +408,21 @@
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed",
|
||||
"modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319972,
|
||||
"taskId": 5319949,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 1,
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
@@ -264,21 +432,21 @@
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Balance",
|
||||
"modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319981,
|
||||
"taskId": 5319931,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 5,
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
@@ -288,21 +456,21 @@
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
|
||||
"modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319984,
|
||||
"taskId": 5319942,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 10,
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
@@ -312,21 +480,189 @@
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "primitive-ai/Nex-N2.5-mini-FP8",
|
||||
"modelId": "togethercomputer/Tev1-4B-experimental",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319936,
|
||||
"taskId": 5319950,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319980,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "ukisai/Swift-1.5-5bit-MLX",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319947,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319979,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 4,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5305971,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 4,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319945,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 4,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "groxaxo/Hemmingway-1-oQ5-MLX",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5343307,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 7,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5347242,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 11,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
@@ -336,21 +672,45 @@
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "juspay/xor-nvfp4",
|
||||
"modelId": "ukisai/Swift-1.5-4bit-MLX",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319941,
|
||||
"taskId": 5319937,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 11,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319953,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 12,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:25.882518+00:00",
|
||||
"architectureBlockExpiresAt": "2026-11-05T08:52:26.243503+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5_moe",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5_moe"
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
@@ -360,16 +720,16 @@
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "MetaX_c-500",
|
||||
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
|
||||
"modelId": "togethercomputer/Tev1-0.8B-experimental",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 5319990,
|
||||
"taskId": 5319956,
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
],
|
||||
"certainOomCount": 0,
|
||||
"certainOomTasks": [],
|
||||
"cleanupCandidateCount": 6,
|
||||
"cleanupCandidateCount": 14,
|
||||
"dryRun": false,
|
||||
"listingErrors": {},
|
||||
"modelAgeErrors": {},
|
||||
@@ -394,7 +754,7 @@
|
||||
],
|
||||
"oldOverflowCount": 0,
|
||||
"oldOverflowTasks": [],
|
||||
"policyCancelledRecorded": 6,
|
||||
"policyCancelledRecorded": 14,
|
||||
"policyNoLongerAppliesCount": 0,
|
||||
"policyNoLongerAppliesTasks": [],
|
||||
"recentModelDays": 7,
|
||||
@@ -407,5 +767,5 @@
|
||||
"repositorySizeUnknown": 0
|
||||
},
|
||||
"stopErrors": [],
|
||||
"uniqueModels": 311
|
||||
"uniqueModels": 310
|
||||
}
|
||||
|
||||
@@ -3,6 +3,8 @@
|
||||
{"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_text"], "framework": "vllm", "lastSyncTime": "2026-10-07T00:15:56.875101+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.660895+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320023", "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_text"], "framework": "vllm", "lastSyncTime": "2026-10-07T00:04:30.851007+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.648162+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320021", "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-patch-tokenizer", "lastSyncTime": "2026-10-07T03:59:02.973639+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "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": 16320427112, "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:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.471074+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320018", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T06:27:34.062566+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:26.475735+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319987", "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_tokenizer_patch", "lastSyncTime": "2026-10-07T06:27:34.062607+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "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": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:26.243503+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319978", "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_moe"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T06:05:03.160740+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "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": 13269529500, "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": 13269529500}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:25.882518+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319960", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-10-05T02:01:26.868359+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-05T02:00:11+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332449", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-10-04T00:08:59.465250+00:00", "modelId": "logic65/Qwen3.6-Whittle-25B-A3B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-04T00:06:57+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4593060", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -296,5 +298,3 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-22T16:03:02.581809+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:55:59.063595+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994203", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164989+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:27+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4895729", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164919+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:26+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4899358", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164954+00:00", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:26+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969013", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164848+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:25+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969016", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
@@ -3087,6 +3087,11 @@
|
||||
{"batchId": "9ed0f87cfac4476bb0a5d7b69f2156ff", "completedAt": "2026-10-07T05:31:07.029835+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-07T05:25:16.871520+00:00", "framework": "vllm", "intentId": "b29401823a3e4d31bc20621aa309891e", "lastModified": "2026-09-15T15:06:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-9B-OptiQ-4bit", "reason": null, "reconciledAt": "2026-10-07T06:21:24.883877+00:00", "repoId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "5348833", "taskType": "text-generation"}
|
||||
{"batchId": "5a3af05bde6b4528bb47524ddacd472a", "completedAt": "2026-10-07T06:14:43.539682+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:12:05.846926+00:00", "framework": "vllm", "intentId": "03ee604c121841fc836e57e7f31e4608", "lastModified": "2026-09-23T05:44:29+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Hemmingway-1-OptiQ-4bit", "reason": null, "reconciledAt": "2026-10-07T06:21:24.881377+00:00", "repoId": "mlx-community/Hemmingway-1-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "5349428", "taskType": "text-generation"}
|
||||
{"batchId": "5a3af05bde6b4528bb47524ddacd472a", "completedAt": "2026-10-07T06:14:43.539700+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:12:05.847088+00:00", "framework": "vllm", "intentId": "d1687ac4f5bc4ccfba4a4dd54e8f14a3", "lastModified": "2026-09-22T14:23:22+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "reason": null, "reconciledAt": "2026-10-07T06:21:24.880481+00:00", "repoId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Iluvatar_mrv-100", "taskId": "5349427", "taskType": "text-generation"}
|
||||
{"batchId": "38b0dc9711f84fb482972853c3beb1ab", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:35:24.855439+00:00", "framework": "vllm-mlu", "intentId": "90e4f68a128e4097b000a81f05f1ee80", "lastModified": "2026-09-24T18:29:33+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/K2-Horizon-7B-AWQ-INT4", "repoId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "38b0dc9711f84fb482972853c3beb1ab", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:35:24.855582+00:00", "framework": "vllm-mlu", "intentId": "fa11f54e9346420cb1e4d7db86f50477", "lastModified": "2026-09-25T13:06:21+00:00", "modelAddress": "https://modelscope.cn/models/danish-foundation-models/DFM-Mimir-v1.5", "repoId": "danish-foundation-models/DFM-Mimir-v1.5", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "38b0dc9711f84fb482972853c3beb1ab", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:35:24.855655+00:00", "framework": "vllm-mlu", "intentId": "4f4c92bf442c427eb6965251ce90bb6f", "lastModified": "2026-09-24T18:35:22+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-3bit-MLX-TextOnly", "repoId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "38b0dc9711f84fb482972853c3beb1ab", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:35:24.855722+00:00", "framework": "vllm-mlu", "intentId": "708010e21c5c4926a340eb1f019a90b3", "lastModified": "2026-09-24T13:17:11+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.6-27B-MTPLX-Optimized", "repoId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "38b0dc9711f84fb482972853c3beb1ab", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:35:24.855800+00:00", "framework": "vllm-mlu", "intentId": "3e35d2108e6e4f55ad93b1f2685a047c", "lastModified": "2026-09-15T15:06:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-9B-OptiQ-4bit", "repoId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "5a3af05bde6b4528bb47524ddacd472a", "completedAt": "2026-10-07T06:14:43.539705+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-10-07T06:12:05.847146+00:00", "framework": "vllm", "intentId": "af78ba5491bc477db71d598faf14f76f", "repoId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "9ed0f87cfac4476bb0a5d7b69f2156ff", "completedAt": "2026-10-07T05:31:07.029844+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-10-07T05:25:16.871626+00:00", "framework": "vllm", "intentId": "272f1c84633d4b26a0094c622e876d7f", "repoId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "9ed0f87cfac4476bb0a5d7b69f2156ff", "completedAt": "2026-10-07T05:31:07.029840+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-10-07T05:25:16.871575+00:00", "framework": "vllm", "intentId": "16f4de0d509b4ad599717e6de899b1c3", "repoId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "2fea650bb20d17688d01e95f3025c3fbcdd24471d9e86db639ba81eb4dcc6ab6",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "e21c972b4960b4b0de20adff8b14f162fad6c35746a398c6e95058c33f767815",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "bfbeac0814ac00dad534be3341097ef4b105c4117145d0f1eea67163d24d472d",
|
||||
".modelhub_state/official_capabilities.json": "e68036e8daadebb48e2105c9e3ca5ad7466f15b07cc14bc265c2de97bb22ca3a",
|
||||
".modelhub_state/outcome_checkpoint.json": "a2807962e83f584d0e677c644bb479103df6a6d0ef2cb699223eeafa5cf4ab0a",
|
||||
".modelhub_state/queue_cleanup_latest.json": "19521156b8596ee274ab6cd41f0d5ad5894cb5c58ae766465897e8700c48419d",
|
||||
".modelhub_state/recent_outcomes.jsonl": "ad1004a41fcde5ce2022ef6fb11ad40a1c848e18d2f6d01809ade68c4afc5417",
|
||||
".modelhub_state/market_intelligence.json": "3eb2578546946e16a4528df104fe3c56c2814d5bfeeb48c0faf7e4a72967941c",
|
||||
".modelhub_state/official_capabilities.json": "05a97444022652cddf25ff976fe57bed6b3358f9670a2884c3e4496c4304aa5d",
|
||||
".modelhub_state/outcome_checkpoint.json": "4e41b662a0069fcfb4b2db81436049be125482ca32ea780ae7e764e6488c944d",
|
||||
".modelhub_state/queue_cleanup_latest.json": "4d15d1972b5d1d97d38cbfefd247476a8b152d98b4efda6c89903fd7b0c1a89c",
|
||||
".modelhub_state/recent_outcomes.jsonl": "2ac0c3ac4cd4bf891e22a04b634980f8a10f80c4e84c4743d8d28a0b013e7420",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "a0f8e3f2a71b070a14a105b98e6ef96d27e1ac0b1f80b0c710a55758c72d0e6e",
|
||||
".modelhub_state/recovery_intents.jsonl": "4d944cedd406afdc097b91b2e252bdaf537ca2fcff958a347629f77cfa75d879",
|
||||
".modelhub_state/recovery_intents.jsonl": "f670c12d24a9d777db738e295ad95a0b4bfde99996ad58fc581fc4b619716879",
|
||||
".modelhub_state/routing_intelligence.json": "8d49bf83a90bd3e565a013be15c83be7771c04f8b85401d1fb9a7e51e98b959f",
|
||||
".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5",
|
||||
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
|
||||
"ledger/submissions.jsonl": "b683dd54d12e8965f40c1f550858cab5613e54a66e5d30f9447c46ce96e1f144",
|
||||
"outcomes/submissions.jsonl": "ca00bc0df385da75b77f9135cc0d09da25849bd81d74fa4a96d9c704b5c2790f"
|
||||
"outcomes/submissions.jsonl": "5c6c83b2e9d85e85b8197ba6d0923d2d30054b620929db35e712e4c8e9ae6a8b"
|
||||
},
|
||||
"generation": 21743,
|
||||
"phase": "cycle",
|
||||
"generation": 21744,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-10-07T06:26:31.296417+00:00",
|
||||
"updatedAt": "2026-10-07T06:35:25.089654+00:00",
|
||||
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
|
||||
}
|
||||
|
||||
@@ -694,18 +694,15 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-05T13:56:01.763115+00:00", "modelId": "primitive-ai/Kolibri-1-NVFP4", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47707345296, "estimatedRequiredGiB": 53.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 42896496000, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 47737939154, "repositoryOnDiskBytes": 47737939154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-05T05:50:24.453804+00:00", "targetGpu": "MetaX_c-500", "taskId": "5295712", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-05T14:15:08.848397+00:00", "modelId": "primitive-ai/Kolibri-1-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 45807306768, "estimatedRequiredGiB": 51.228, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 44223812896, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 45837930112, "repositoryOnDiskBytes": 45837930112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-05T06:06:54.877440+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5295917", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-05T14:15:08.848422+00:00", "modelId": "primitive-ai/Kolibri-1-NVFP4", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47707345296, "estimatedRequiredGiB": 53.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 42896496000, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 47737939154, "repositoryOnDiskBytes": 47737939154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-05T06:06:54.870782+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5295916", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T01:01:25.972086+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "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": 16320426072, "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:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16320426072, "quantizationMethod": null, "recursiveRepositoryBytes": 16320426072, "repositoryOnDiskBytes": 16320426072}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-05T16:53:48.247093+00:00", "targetGpu": "MetaX_c-500", "taskId": "5305971", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T01:13:33.049671+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "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": 16320426072, "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:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 16320426072, "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "recursiveRepositoryBytes": 16320426072, "repositoryOnDiskBytes": 16320426072}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-05T17:11:20.150043+00:00", "targetGpu": "Biren_166m", "taskId": "5306227", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T02:18:00.653125+00:00", "modelId": "unsloth/gpt-oss-20b-bnb-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 40884615394, "estimatedRequiredGiB": 45.723, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 40912596558, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20934761652, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:openai", "custom_tag:unsloth"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 40912596558, "quantizationMethod": "bitsandbytes", "recursiveRepositoryBytes": 40912599808, "repositoryOnDiskBytes": 40912599808}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-05T18:17:07.068675+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5307270", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T02:40:20.542511+00:00", "modelId": "unsloth/gpt-oss-20b-bnb-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 40884615394, "estimatedRequiredGiB": 45.723, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 40912596558, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20934761652, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:openai", "custom_tag:unsloth"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 40912596558, "quantizationMethod": "bitsandbytes", "recursiveRepositoryBytes": 40912599808, "repositoryOnDiskBytes": 40912599808}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-05T18:34:25.654316+00:00", "targetGpu": "Biren_166m", "taskId": "5307498", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:32:26.862488+00:00", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 5045067151, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:05:30.743848+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319429", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:32:26.862464+00:00", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 5045067151, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:23:48.552550+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5319658", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348011+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "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": 26090092835, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090092835}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.358297+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319932", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348006+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "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": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.259138+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319937", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347872+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.264946+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319930", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347867+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.252246+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319933", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347924+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.343842+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319928", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347814+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "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": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.245612+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319931", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347809+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.261247+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319939", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347930+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.256812+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319929", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348141+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.254703+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319935", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -713,20 +710,13 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348146+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.267901+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319934", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348135+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.547234+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319946", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347746+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.554613+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319948", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348049+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "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": 19310950017, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.544511+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319947", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347692+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "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": 13756989526, "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": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.576159+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319943", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347803+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "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": 20616225866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.543223+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319942", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347639+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "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:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.557635+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319940", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347918+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.551244+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319944", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347861+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "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": 19336478290, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.546082+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319945", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348096+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.659228+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319949", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348043+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "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": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.676818+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319951", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347798+00:00", "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "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": 9342812725, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.662173+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319950", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347686+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "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": 1769900320, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.762465+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319956", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348131+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.747314+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319958", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347856+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199622478, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199622478}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.745622+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319952", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347912+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.748983+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319954", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347995+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "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": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35256868927}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.758735+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319953", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347633+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.756975+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319955", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347738+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.752033+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319957", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348038+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.860251+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319963", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -743,14 +733,10 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348033+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.058806+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319974", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347843+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960168568, "estimatedRequiredGiB": 2.344, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2097293495, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2097293495}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.064607+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319970", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347786+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.056438+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319973", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347726+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "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": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.243503+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319978", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347901+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17593027563}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.156892+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319975", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347619+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "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": 8145035684, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8145035684}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.261424+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319976", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347894+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.475735+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319987", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347958+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "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": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.251726+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319977", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347674+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.355129+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319982", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348027+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "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": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.388066+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319979", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347774+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "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": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "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:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981021}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.368621+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319980", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347984+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2152567281, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.348588+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319983", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347837+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.446600+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319986", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-06T16:58:45.347610+00:00", "modelId": "bartowski/junshim_When2Think-ThinkOnly-1.5B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "b8297dd5c3290e951d2802002a5e061d5d669c6886a4ec45f9008cda1aaf8cd3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1077324288, "estimatedRequiredGiB": 30.563, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 27347406407, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:reasoning", "custom_tag:mathematical", "custom_tag:hybrid-reasoning", "custom_tag:adaptive-reasoning", "custom_tag:efficient-reasoning", "custom_tag:reinforcement-learning", "custom_tag:rlvr", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 27347406407}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.577302+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5319989", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -1025,8 +1011,7 @@
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T02:27:52.060895+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T18:24:48.764764+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5339861", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T06:05:03.160729+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T21:54:55.149142+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5342603", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T06:05:03.160704+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T21:54:55.059764+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5342530", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "c7541f1f29b3fd5c7c77db0c143c2abddce8ce74fd696dee033dda5852b7e04f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T22:08:47.750829+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5342903", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "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": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T22:44:43.576920+00:00", "targetGpu": "MetaX_c-500", "taskId": "5343307", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T06:27:34.062598+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "c7541f1f29b3fd5c7c77db0c143c2abddce8ce74fd696dee033dda5852b7e04f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T22:08:47.750829+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5342903", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "unsloth/gpt-oss-120b-unsloth-bnb-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62087797505, "estimatedRequiredGiB": 69.427, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 62122535546, "modelscopeLicense": "apache-2.0", "modelscopeParams": 120454994706, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:openai", "custom_tag:unsloth"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "bitsandbytes", "repositoryOnDiskBytes": 62122535546}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T22:44:43.655618+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5343286", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Kolibri-1-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 45807306768, "estimatedRequiredGiB": 51.228, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": 45837930112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 44223812896, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 45837930112}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T22:44:43.557377+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5343294", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "primitive-ai/Kolibri-1-NVFP4", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47707345296, "estimatedRequiredGiB": 53.351, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": 47737939154, "modelscopeLicense": "apache-2.0", "modelscopeParams": 42896496000, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 47737939154}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T22:44:43.571765+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5343291", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -1052,7 +1037,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "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": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 4}, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 4, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T23:21:09.752397+00:00", "targetGpu": "Biren_166m", "taskId": "5343725", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T23:37:28.160203+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5343926", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T00:32:27.150657+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5344555", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "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": 7120900461, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1915564544, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:qwen3.5", "custom_tag:reasoning", "custom_tag:long-context", "custom_tag:function-calling", "custom_tag:tool-use", "custom_tag:agentic", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120900461}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T03:47:04.956076+00:00", "targetGpu": "MetaX_c-500", "taskId": "5347242", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T03:47:04.967444+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5347241", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T03:47:04.988602+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5347240", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120900461, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1915564544, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:qwen3.5", "custom_tag:reasoning", "custom_tag:long-context", "custom_tag:function-calling", "custom_tag:tool-use", "custom_tag:agentic", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120900461}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-07T05:25:18.483418+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5348833", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user