state: generation 25962 (intent)
This commit is contained in:
@@ -336,25 +336,6 @@
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"cambricon_mlu-370-x8|vllm-customized|text-generation|model_type:gemma4": {
|
||||
"architectureSignature": "model_type:gemma4",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-20T12:30:15.535777+00:00",
|
||||
"framework": "vllm-customized",
|
||||
"latestFailureAt": "2026-09-20T12:30:15.535777+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "gemma4",
|
||||
"sourceModelIds": [
|
||||
"mlx-community/gemma-4-e2b-it-OptiQ-4bit"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4978792"
|
||||
],
|
||||
"targetGpu": "Cambricon_mlu-370-x8",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"cambricon_mlu-370-x8|vllm-customized|text-generation|model_type:gemma4_unified": {
|
||||
"architectureSignature": "model_type:gemma4_unified",
|
||||
"architectures": [],
|
||||
@@ -1229,9 +1210,9 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-10-20T12:12:45.063285+00:00",
|
||||
"generatedAt": "2026-10-20T12:39:15.738361+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 60,
|
||||
"activeBlockCount": 59,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 2,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 5,
|
||||
@@ -1239,7 +1220,7 @@
|
||||
"Cambricon_mlu-370-x4|vllm": 2,
|
||||
"Cambricon_mlu-370-x4|vllm-customized": 2,
|
||||
"Cambricon_mlu-370-x4|vllm-mlu": 1,
|
||||
"Cambricon_mlu-370-x8|vllm-customized": 3,
|
||||
"Cambricon_mlu-370-x8|vllm-customized": 2,
|
||||
"Cambricon_mlu-370-x8|vllm-mlu": 3,
|
||||
"Iluvatar_bi-150|transformers": 1,
|
||||
"Iluvatar_bi-150|vllm": 1,
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-10-20T12:13:50.866062+00:00",
|
||||
"communityAttemptedAt": "2026-10-20T12:41:39.351234+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-10-20T12:13:50.866062+00:00",
|
||||
"communityUpdatedAt": "2026-10-20T12:41:39.351234+00:00",
|
||||
"frameworkAttemptedAt": "2026-10-20T08:15:56.753569+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -452,121 +452,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-10-20T12:13:50.866062+00:00",
|
||||
"generatedAt": "2026-10-20T12:41:39.351234+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1922.0224719101122,
|
||||
"backlogHours": 1781.5,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.1864929926803334,
|
||||
"queueFactor": 0.9618890743763584,
|
||||
"queueWeight": 0.9618890743763584,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.29213483146067415,
|
||||
"recentTerminal": 89,
|
||||
"recentWilsonLowerBound": 0.2078347417163135,
|
||||
"qualityFactor": 1.0856521041802525,
|
||||
"queueFactor": 0.9702721248645664,
|
||||
"queueWeight": 0.9702721248645664,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.28125,
|
||||
"recentTerminal": 96,
|
||||
"recentWilsonLowerBound": 0.20107282637501533,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.1412746464833212,
|
||||
"selectionWeight": 1.053377973986661,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.833333333333334,
|
||||
"waiting": 28510
|
||||
"throughputPerHour": 16.0,
|
||||
"waiting": 28504
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1328.0675675675675,
|
||||
"backlogHours": 1310.36,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 1.0167302274032661,
|
||||
"queueWeight": 1.0167302274032661,
|
||||
"recentSuccess": 54,
|
||||
"recentSuccessRate": 0.36486486486486486,
|
||||
"recentTerminal": 148,
|
||||
"recentWilsonLowerBound": 0.2916373002819259,
|
||||
"queueFactor": 1.0160213511887268,
|
||||
"queueWeight": 1.0160213511887268,
|
||||
"recentSuccess": 55,
|
||||
"recentSuccessRate": 0.36666666666666664,
|
||||
"recentTerminal": 150,
|
||||
"recentWilsonLowerBound": 0.293773196710732,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.541825568508165,
|
||||
"selectionWeight": 2.540053377971817,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.666666666666668,
|
||||
"throughputPerHour": 25.0,
|
||||
"waiting": 32759
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 128.28699551569508,
|
||||
"backlogHours": 104.9010989010989,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.1072973529876815,
|
||||
"qualityFactor": 0.05975114096439499,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.1031390134529148,
|
||||
"recentTerminal": 223,
|
||||
"recentWilsonLowerBound": 0.0697139815570414,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.08058608058608059,
|
||||
"recentTerminal": 273,
|
||||
"recentWilsonLowerBound": 0.053817568894455145,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.13948655888398595,
|
||||
"selectionWeight": 0.07767648325371349,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 37.166666666666664,
|
||||
"waiting": 4768
|
||||
"throughputPerHour": 45.5,
|
||||
"waiting": 4773
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1682.0307692307692,
|
||||
"backlogHours": 1708.59375,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.35946955272049663,
|
||||
"queueFactor": 0.9813268248627862,
|
||||
"queueWeight": 0.9813268248627862,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.2,
|
||||
"recentTerminal": 65,
|
||||
"recentWilsonLowerBound": 0.12077845770945214,
|
||||
"qualityFactor": 0.45206724160695255,
|
||||
"queueFactor": 0.9763726524704905,
|
||||
"queueWeight": 0.9763726524704905,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.21875,
|
||||
"recentTerminal": 64,
|
||||
"recentWilsonLowerBound": 0.13502197461349752,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.3527571148060509,
|
||||
"selectionWeight": 0.44138609178279836,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 10.833333333333334,
|
||||
"waiting": 18222
|
||||
"throughputPerHour": 10.666666666666666,
|
||||
"waiting": 18225
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 516.3620689655173,
|
||||
"backlogHours": 516.4137931034483,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.7158090033782087,
|
||||
"queueFactor": 1.1715089508331464,
|
||||
"queueWeight": 1.1715089508331464,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.23275862068965517,
|
||||
"qualityFactor": 0.7759661869387919,
|
||||
"queueFactor": 1.168319844882866,
|
||||
"queueWeight": 1.168319844882866,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.2413793103448276,
|
||||
"recentTerminal": 116,
|
||||
"recentWilsonLowerBound": 0.16518094816137183,
|
||||
"recentWilsonLowerBound": 0.17260719345282605,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.8385766545445255,
|
||||
"selectionWeight": 0.9065766951586784,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.333333333333332,
|
||||
"waiting": 9983
|
||||
"waiting": 9984
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 80.40425531914893,
|
||||
"backlogHours": 74.85049833887044,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -575,20 +575,20 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.01773049645390071,
|
||||
"recentTerminal": 282,
|
||||
"recentWilsonLowerBound": 0.007596476356414029,
|
||||
"running": 24,
|
||||
"recentSuccess": 4,
|
||||
"recentSuccessRate": 0.013289036544850499,
|
||||
"recentTerminal": 301,
|
||||
"recentWilsonLowerBound": 0.005179572748049918,
|
||||
"running": 25,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 47.0,
|
||||
"waiting": 3779
|
||||
"throughputPerHour": 50.166666666666664,
|
||||
"waiting": 3755
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 239.11764705882354,
|
||||
"backlogHours": 234.14423076923077,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
@@ -598,174 +598,174 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.04411764705882353,
|
||||
"recentTerminal": 204,
|
||||
"recentWilsonLowerBound": 0.023381114061204137,
|
||||
"running": 0,
|
||||
"recentSuccessRate": 0.04326923076923077,
|
||||
"recentTerminal": 208,
|
||||
"recentWilsonLowerBound": 0.022928210873058096,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 34.0,
|
||||
"waiting": 8130
|
||||
"throughputPerHour": 34.666666666666664,
|
||||
"waiting": 8117
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2258.6511627906975,
|
||||
"backlogHours": 2066.0425531914893,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.22401411848644864,
|
||||
"queueFactor": 0.9388828080926838,
|
||||
"queueWeight": 0.9388828080926838,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.18604651162790697,
|
||||
"recentTerminal": 43,
|
||||
"recentWilsonLowerBound": 0.09741635580105981,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.21032300461696407,
|
||||
"qualityFactor": 0.25541033041570227,
|
||||
"queueFactor": 0.9489439019432856,
|
||||
"queueWeight": 0.9489439019432856,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.19148936170212766,
|
||||
"recentTerminal": 47,
|
||||
"recentWilsonLowerBound": 0.10415815605310119,
|
||||
"running": 3,
|
||||
"selectionWeight": 0.24237007554130036,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.166666666666667,
|
||||
"waiting": 16187
|
||||
"throughputPerHour": 7.833333333333333,
|
||||
"waiting": 16184
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 552.2285714285714,
|
||||
"backlogHours": 585.7575757575758,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.7312358670319414,
|
||||
"queueFactor": 1.159767488475284,
|
||||
"queueWeight": 1.159767488475284,
|
||||
"qualityFactor": 0.8230618870065182,
|
||||
"queueFactor": 1.1464463646588101,
|
||||
"queueWeight": 1.1464463646588101,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.23809523809523808,
|
||||
"recentTerminal": 105,
|
||||
"recentWilsonLowerBound": 0.16678968751856937,
|
||||
"recentSuccessRate": 0.25252525252525254,
|
||||
"recentTerminal": 99,
|
||||
"recentWilsonLowerBound": 0.17729258424187705,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.8480635849906815,
|
||||
"selectionWeight": 0.9435963082478431,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.5,
|
||||
"waiting": 9664
|
||||
"throughputPerHour": 16.5,
|
||||
"waiting": 9665
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 1052.6865671641792,
|
||||
"backlogHours": 1068.909090909091,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.8356353065881124,
|
||||
"queueFactor": 1.0527952063323414,
|
||||
"queueWeight": 1.0527952063323414,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.26865671641791045,
|
||||
"recentTerminal": 67,
|
||||
"recentWilsonLowerBound": 0.17722065178970134,
|
||||
"qualityFactor": 0.9888772613680206,
|
||||
"queueFactor": 1.047539270763868,
|
||||
"queueWeight": 1.047539270763868,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.2878787878787879,
|
||||
"recentTerminal": 66,
|
||||
"recentWilsonLowerBound": 0.19271802784703906,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.8797528450180211,
|
||||
"selectionWeight": 1.035887765248427,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.166666666666666,
|
||||
"waiting": 11755
|
||||
"throughputPerHour": 11.0,
|
||||
"waiting": 11758
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 3426.260869565217,
|
||||
"backlogHours": 3581.727272727273,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.3715563230728305,
|
||||
"queueFactor": 0.8819941346422006,
|
||||
"queueWeight": 0.8819941346422006,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.21739130434782608,
|
||||
"recentTerminal": 46,
|
||||
"recentWilsonLowerBound": 0.1226077461858075,
|
||||
"qualityFactor": 0.534799327200542,
|
||||
"queueFactor": 0.8737708490082854,
|
||||
"queueWeight": 0.8737708490082854,
|
||||
"recentSuccess": 11,
|
||||
"recentSuccessRate": 0.25,
|
||||
"recentTerminal": 44,
|
||||
"recentWilsonLowerBound": 0.14574066080685744,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.32771049763945903,
|
||||
"selectionWeight": 0.4672920621770774,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.666666666666667,
|
||||
"waiting": 26268
|
||||
"throughputPerHour": 7.333333333333333,
|
||||
"waiting": 26266
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 4128.0,
|
||||
"backlogHours": 3715.4,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.07476874043894509,
|
||||
"queueFactor": 0.8576849859694332,
|
||||
"queueWeight": 0.8576849859694332,
|
||||
"recentSuccess": 4,
|
||||
"recentSuccessRate": 0.14814814814814814,
|
||||
"recentTerminal": 27,
|
||||
"recentWilsonLowerBound": 0.0591583185964489,
|
||||
"qualityFactor": 0.11813546654174567,
|
||||
"queueFactor": 0.8689816228417321,
|
||||
"queueWeight": 0.8689816228417321,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.16666666666666666,
|
||||
"recentTerminal": 30,
|
||||
"recentWilsonLowerBound": 0.07336434240351682,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.06412802609432881,
|
||||
"selectionWeight": 0.1026575494306113,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 4.5,
|
||||
"waiting": 18576
|
||||
"throughputPerHour": 5.0,
|
||||
"waiting": 18577
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1875.966101694915,
|
||||
"backlogHours": 2012.8363636363638,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.21078220285665877,
|
||||
"queueFactor": 0.9653949284858432,
|
||||
"queueWeight": 0.9653949284858432,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.1694915254237288,
|
||||
"recentTerminal": 59,
|
||||
"recentWilsonLowerBound": 0.0947573785633763,
|
||||
"qualityFactor": 0.12617111806194253,
|
||||
"queueFactor": 0.9526648864250695,
|
||||
"queueWeight": 0.9526648864250695,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.14545454545454545,
|
||||
"recentTerminal": 55,
|
||||
"recentWilsonLowerBound": 0.07559199016771778,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.2034880696528926,
|
||||
"selectionWeight": 0.12019879385860452,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.833333333333334,
|
||||
"waiting": 18447
|
||||
"throughputPerHour": 9.166666666666666,
|
||||
"waiting": 18451
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1638.7333333333333,
|
||||
"backlogHours": 1603.304347826087,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.36362827237900774,
|
||||
"queueFactor": 0.9851730383801596,
|
||||
"queueWeight": 0.9851730383801596,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.18888888888888888,
|
||||
"recentTerminal": 90,
|
||||
"recentWilsonLowerBound": 0.1214115980938824,
|
||||
"qualityFactor": 0.3984889196627591,
|
||||
"queueFactor": 0.9857324033872993,
|
||||
"queueWeight": 0.9857324033872993,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.1956521739130435,
|
||||
"recentTerminal": 92,
|
||||
"recentWilsonLowerBound": 0.12749741209297205,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.3582367699405553,
|
||||
"selectionWeight": 0.39280344050238,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.0,
|
||||
"waiting": 24581
|
||||
"throughputPerHour": 15.333333333333334,
|
||||
"waiting": 24584
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-10-20T12:13:50.866062+00:00",
|
||||
"queueAttemptedAt": "2026-10-20T12:41:39.351234+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-10-20T12:13:50.866062+00:00",
|
||||
"queueUpdatedAt": "2026-10-20T12:41:39.351234+00:00",
|
||||
"supportedGpus": [
|
||||
"Cambricon_mlu-370-x4",
|
||||
"Vastai_va16",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -4,6 +4,7 @@
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "llamacpp", "lastSyncTime": "2026-10-18T17:28:58.572069+00:00", "modelId": "ornith-ai/Ornith-1.0-9B-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-18T17:13:43+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4332412", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-10-16T08:44:58.249327+00:00", "modelId": "DavidAU/DarkSapling-V2-Ultra-Quality-7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "a7159961e1848fd33948f09e6020f02399009945e81bc356b0f9fcd8e43bdd29", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8080881376, "estimatedRequiredGiB": 55.473, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 49636846090, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:creative", "custom_tag:story", "custom_tag:roleplay", "custom_tag:rp", "custom_tag:32 bit upscale", "custom_tag:remastered", "custom_tag:writing", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 49636846090}, "outcome": "failed", "status": "success", "submitTime": "2026-10-15T20:46:16.830124+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5569369", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-16T17:41:11.941285+00:00", "modelId": "inclusionAI/Ring-mini-2.0", "modelProfile": {"architectures": ["BailingMoeV2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 32513135016, "estimatedRequiredGiB": 36.346, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_moe", "modelscopeFileSize": 32522223867, "modelscopeLicense": "mit", "modelscopeParams": 16255643392, "modelscopeTags": ["license:mit", "model_type:bailing_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 32522223867}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T21:53:35.357776+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520150", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-20T12:39:15.571332+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "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": "failed", "status": "failed", "submitTime": "2026-10-13T21:52:38.758920+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520133", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-13T22:17:18.970452+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T13:12:18.147765+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5513114", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-13T22:17:18.970462+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T12:52:58.552750+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5512698", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-13T22:17:18.970469+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T12:30:24.554632+00:00", "targetGpu": "MetaX_c-500", "taskId": "5512351", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -131,6 +132,7 @@
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.556998+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T11:46:58.959385+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353406", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557134+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T11:46:58.949218+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353400", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557107+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T11:46:58.932770+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353396", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-20T12:39:15.571353+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "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": 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": "failed", "status": "failed", "submitTime": "2026-10-07T11:46:58.931650+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353403", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T02:21:33.753289+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T06:35:26.381282+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5349734", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T02:21:33.753315+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T06:35:26.357823+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5349733", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T02:21:33.753379+00:00", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T06:35:26.352295+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5349732", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -236,6 +238,7 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-09T17:44:29.077619+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T03:04:40.754950+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 467369015}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:21.657678+00:00", "targetGpu": "Biren_166m", "taskId": "5320467", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851090+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:13:59.677111+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320455", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851246+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:13:59.676142+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320466", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-20T12:39:15.571321+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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, "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}, "repositoryOnDiskBytes": 7120897697}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:13:59.673954+00:00", "targetGpu": "Biren_166m", "taskId": "5320462", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-10-09T13:05:40.965751+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.673292+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320022", "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": "2026-10-07T00:15:56.875101+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}
|
||||
@@ -295,6 +298,3 @@
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T13:13:59.503959+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:49.572421+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260112", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851110+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:49.560660+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260110", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851022+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:49.555638+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260108", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851196+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:49.469061+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260106", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T03:19:51.851140+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-03T16:15:49.446747+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260107", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-09T21:13:02.549189+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": "failed", "status": "success", "submitTime": "2026-10-03T16:15:49.353284+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260101", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
@@ -3646,6 +3646,18 @@
|
||||
{"batchId": "7d8714bb31484a34b25b1e9218a6bd5f", "completedAt": "2026-10-19T05:49:46.882158+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T05:48:25.746255+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0512ce8e35fc4e3993253c3b1048dc20", "lastModified": "2026-10-19T05:33:13+00:00", "modelAddress": "https://modelscope.cn/models/hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "reason": null, "reconciledAt": "2026-10-20T12:34:56.185609+00:00", "repoId": "hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5645467", "taskType": "text-generation"}
|
||||
{"batchId": "2f477057c7ec43eca67dacd9b9eb46d5", "completedAt": "2026-10-19T12:20:36.162545+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-19T11:58:25.852127+00:00", "framework": "vllm_tokenizer_patch", "intentId": "63ce37f826f14ede8c320b620a768f1d", "lastModified": "2026-10-16T15:13:58+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-7B-MLX-4bit", "reason": null, "reconciledAt": "2026-10-20T12:34:56.184611+00:00", "repoId": "IFM/Jais-3-7B-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5651876", "taskType": "text-generation"}
|
||||
{"batchId": "dbc12fe57a8247638bf728bceccbca3f", "completedAt": "2026-10-20T04:39:17.415698+00:00", "configFingerprint": "e9c4f4f15802a39a57c6e07956c53755f75fc438be43d1164a8a2eda32456b1e", "configSource": "modelhub_live", "createdAt": "2026-10-20T04:13:53.649573+00:00", "framework": "llamacpp", "intentId": "a0c959ad23574499bd6e12b19d1bfafa", "lastModified": "2026-10-18T14:39:44+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "reason": null, "reconciledAt": "2026-10-20T12:34:56.185876+00:00", "repoId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5668972", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.987543+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a7d87127e8dd4435af6b8bfe5ea83fc3", "lastModified": "2026-10-19T16:26:03+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "repoId": "cpatonn-mirror/Qwen3-30B-A3B-Thinking-2507-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.987663+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4a66ee9139a8494fa9ebb883d407f8fd", "lastModified": "2026-10-19T17:09:46+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "repoId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.987745+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4ef0cb8b659e4915963c518be5db0cfe", "lastModified": "2026-10-19T18:03:45+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "repoId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.987820+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d1e1c74ea11a418c97d9a2772381901a", "lastModified": "2026-10-20T08:50:37+00:00", "modelAddress": "https://modelscope.cn/models/Haodong07/Qwen3-32B-TwinQuant-W4A4", "repoId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.987894+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4793c1b027924c398881c7718c3ad7b3", "lastModified": "2026-10-19T07:00:41+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-8B-W8A8", "repoId": "iluvatar-corex/Qwen3-8B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.987972+00:00", "framework": "vllm_tokenizer_patch", "intentId": "939a69da50164872b1630e30a6d83348", "lastModified": "2026-10-19T07:29:23+00:00", "modelAddress": "https://modelscope.cn/models/iluvatar-corex/Qwen3-14B-W8A8", "repoId": "iluvatar-corex/Qwen3-14B-W8A8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.988048+00:00", "framework": "vllm_tokenizer_patch", "intentId": "48026730a38740588d154e4876ae92b5", "lastModified": "2026-10-19T17:23:16+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "repoId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.988124+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8641cd00c94b4d3c9be797c11b87de4d", "lastModified": "2026-10-19T18:03:21+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "repoId": "cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.988213+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e0ba75ca87f14f769c0c5c2e742bc876", "lastModified": "2026-10-17T05:39:17+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.988289+00:00", "framework": "vllm_tokenizer_patch", "intentId": "84e46cd3cb1a4f99a3d967b061ee8122", "lastModified": "2026-10-19T18:55:19+00:00", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-2.1-FP8-dynamic", "repoId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.988362+00:00", "framework": "vllm_tokenizer_patch", "intentId": "80af426444fc4401bba1bee08b2537f4", "lastModified": "2026-10-19T07:32:17+00:00", "modelAddress": "https://modelscope.cn/models/StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "repoId": "StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "51501ccf8b114515ae500edea9e19951", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:42:10.988409+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6bbc015000f64e188eb6e746d6bddd35", "lastModified": "2026-10-17T05:35:31+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
|
||||
{"batchId": "d33dba52f5b840b4910a252c2d67c9f8", "completedAt": "2026-10-20T12:34:47.034366+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:16:36.889528+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9a3c1424729b44a696c4c4704f7b7ccb", "repoId": "nv-community/NVIDIA-Nemotron-Labs-Dory1.0-4B-MXFP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "d33dba52f5b840b4910a252c2d67c9f8", "completedAt": "2026-10-20T12:34:47.034363+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:16:36.889486+00:00", "framework": "vllm_tokenizer_patch", "intentId": "76c5d91e19904ae49e1f77ac98f8c0e2", "repoId": "StartLuxAI/gdn-1.3b-isp-hybrid-3to1-50b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "d33dba52f5b840b4910a252c2d67c9f8", "completedAt": "2026-10-20T12:34:47.034360+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-20T12:16:36.889444+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d73d61c601e74525a55f0766310d2b70", "repoId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -2,24 +2,24 @@
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/account_capacity.json": "513078806afb32dfda069cd5575642eaf8f72b4147688b3671e3b9380a633829",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "3844874a7bfae9683a821e19da96d8c9fcc4f80aaae562dd693c5b2c96571d74",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "781a6f229925cdb30e2c6c114c59817c8c9feb51da4f455ef85aa0ecd1e601fb",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "a7c87f0bb4aab3b1fe0ec1915567134185bad7c7f83f3bd8b6bfd50a9def51dc",
|
||||
".modelhub_state/official_capabilities.json": "5d350f437ad8eda4220c88f2476fc7b7618180f75a7d51113976d9feac8b8728",
|
||||
".modelhub_state/outcome_checkpoint.json": "b6f6eb878003221f8b41068f1f487615b4d6841290cb0744df0b78e641dd7e8d",
|
||||
".modelhub_state/market_intelligence.json": "f1306199614a0d7e28748f96e1d1ed05e541a7aeaba5a21b44e7b3d931466b28",
|
||||
".modelhub_state/official_capabilities.json": "a839f5803260440ef47bb7cf34f3dbfd74acd75b2cd6a274067f2039632f280a",
|
||||
".modelhub_state/outcome_checkpoint.json": "f086cee90552e0cb9a58b7a1bc922b5534b81bb3bcb8b456416fc656c45ca61a",
|
||||
".modelhub_state/queue_cleanup_latest.json": "24b8d3ed2ed8fc5782ecdd2bd7c653870341c4af075525d0b365df5ed0bcedb9",
|
||||
".modelhub_state/recent_outcomes.jsonl": "fa91981c7ed2f069f9d64d025e5739016eda9d52a36ec06064f667e592ce0db4",
|
||||
".modelhub_state/recent_outcomes.jsonl": "0cbbd7a29e804ad7e2133c6df58f56ef8ae942bfe00696cb87ca4c9f4ec221b8",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "7017aac026ff5a7a091f5195fd0b7ed8c81db04fd14892afff202e92dbd82028",
|
||||
".modelhub_state/recovery_intents.jsonl": "efac299b4a970eb9577f465b2bd544113da8accc7eef9c2bf59e47be06cce25a",
|
||||
".modelhub_state/recovery_intents.jsonl": "6777df40baedd904680ac20f1aa26282230ac081b4bb75aa2cd341e23810fb66",
|
||||
".modelhub_state/routing_intelligence.json": "3bb691c3219f09b342f5c2d4a486ab140e78b7a256ec9fa2e1a779045fbbb0c6",
|
||||
".modelhub_state/submission_exclusions.jsonl": "1ef249015e7dce06a9d85a72a9a31e2714443fe0ed14477ff3f48af7ef8f8b9c",
|
||||
".modelhub_state/worker_crashes.jsonl": "75c8a6c5605f99dfe3e7d27ff6e9c6d730e1ee3a5016c812ed5cc3137a98684c",
|
||||
"ledger/submissions.jsonl": "df38c060f3a90d4806233dc6ac41fd44bb9b673d0407b61194290c12919989a4",
|
||||
"outcomes/submissions.jsonl": "96f5f10a2ad04882fd4e6cabfe0d956713702efd0c89843babb90ff9490aaf2d"
|
||||
"outcomes/submissions.jsonl": "d6b7039d08838b18823ab11c7d793622e83f0ccb0afaddeecaece562e5b075ac"
|
||||
},
|
||||
"generation": 25961,
|
||||
"phase": "cycle",
|
||||
"generation": 25962,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-10-20T12:34:56.418518+00:00",
|
||||
"updatedAt": "2026-10-20T12:42:11.166471+00:00",
|
||||
"writerId": "eca444bc9fdf4bc89c9cfc2f8a9a6ac1"
|
||||
}
|
||||
|
||||
@@ -157,9 +157,7 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T10:15:00.768930+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2044205392, "estimatedRequiredGiB": 2.469, "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": 2209448692, "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": 2209448692}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T02:14:32.985862+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5010817", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T10:40:24.557236+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2038896936, "estimatedRequiredGiB": 2.283, "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": null, "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": 2042511760}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T02:38:35.435001+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5011087", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-22T13:46:14.276964+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:42:55.602315+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5013164", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T13:58:31.356521+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "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": null, "modelscopeLicense": "mit", "modelscopeParams": null, "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": "2026-09-22T05:55:01.182755+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5013341", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:58:31.356490+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:58:14.744160+00:00", "targetGpu": "MetaX_c-500", "taskId": "5013402", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T14:29:11.661447+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": null, "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": "2026-09-22T06:26:57.046313+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5013726", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T14:29:11.661394+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 30361724387, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T06:26:57.044876+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5013725", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-22T20:29:13.756800+00:00", "modelId": "z-lab/Muse-Glimmer-30B-DFlash2-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "b8a926f4d98c4c17ed728affade2dfee1910e905840c16a7c6d35cdf073f1b9a", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2959518912, "estimatedRequiredGiB": 11.359, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10163561928, "modelscopeLicense": "apache-2.0", "modelscopeParams": 81, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:dflash2", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10163561928}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T12:28:01.206856+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5018933", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-22T20:33:11.953328+00:00", "modelId": "LiquidAI/LFM2.5-2.6B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "415f9524ad0e8e6c9c3d7532026f319100b3d292f6c5a09cdc37467f1144a744", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491776, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219881017, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219881017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T12:31:29.914227+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5019029", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -415,7 +413,6 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953125+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-10-06T09:13:59.670629+00:00", "targetGpu": "Biren_166m", "taskId": "5320460", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952117+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-10-06T09:13:59.674981+00:00", "targetGpu": "Biren_166m", "taskId": "5320465", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952898+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-10-06T09:13:59.669160+00:00", "targetGpu": "Biren_166m", "taskId": "5320458", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952350+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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, "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}, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.673954+00:00", "targetGpu": "Biren_166m", "taskId": "5320462", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952246+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-10-06T09:13:59.678748+00:00", "targetGpu": "Biren_166m", "taskId": "5320457", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952888+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-10-06T09:15:21.661697+00:00", "targetGpu": "Biren_166m", "taskId": "5320470", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952111+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "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": 2199119539, "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": 2199119539}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:21.748096+00:00", "targetGpu": "Biren_166m", "taskId": "5320472", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -604,7 +601,6 @@
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668239+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "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": 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": "2026-10-07T11:46:58.870068+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353399", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668233+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "05dc104fca8c61e0b7e14c3355cdda1d22c2b6dca6c7d2ae77046a8789aa91d4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "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": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T11:46:59.077598+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353404", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668400+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-10-07T11:46:58.861235+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353401", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668220+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "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": 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": "2026-10-07T11:46:58.931650+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353403", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668372+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "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": "waiting", "submitTime": "2026-10-07T11:46:58.869031+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353407", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668213+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-10-07T11:48:13.063658+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353415", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-07T20:23:14.668322+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "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": 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": "2026-10-07T11:48:13.053438+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5353413", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -938,7 +934,6 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T04:05:54.875280+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-8bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25484884997, "estimatedRequiredGiB": 28.502, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 25502895279, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25502895279}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T20:01:58.646474+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5518621", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T04:32:55.241111+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-6bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19493321709, "estimatedRequiredGiB": 21.806, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 19511331991, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19511331991}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T20:24:48.464556+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5519001", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051622+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "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": "2026-10-13T21:52:38.762916+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520140", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051493+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "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": "2026-10-13T21:52:38.758920+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520133", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051699+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "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": "2026-10-13T21:52:38.769871+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520138", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051578+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "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": "2026-10-13T21:52:38.767702+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520136", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051853+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "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": "2026-10-13T21:52:38.765482+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520139", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -1092,4 +1087,4 @@
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T13:29:43.268862+00:00", "modelId": "OsaurusAI/Diplodocus-preview-JANG_6M", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6938269080, "estimatedRequiredGiB": 7.778, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6959482715, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1805389824, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:finance", "custom_tag:documents", "custom_tag:spreadsheets", "custom_tag:k2_horizon", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6959482715}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-19T05:17:00.139342+00:00", "targetGpu": "MetaX_c-500", "taskId": "5645005", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T14:04:19.065999+00:00", "modelId": "hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "modelProfile": {"architectures": ["MiniCPMV4_7ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23953202568, "estimatedRequiredGiB": 26.804, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minicpmv4_7", "modelscopeFileSize": 45773, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3242913051, "modelscopeTags": ["license:apache-2.0", "model_type:minicpmv4_7", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:minicpm", "custom_tag:minicpm-v-4-7", "custom_tag:moe", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:blackwell", "custom_tag:compressed-tensors", "custom_tag:vllm", "custom_tag:llama.cpp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23983932119}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-19T05:48:26.821232+00:00", "targetGpu": "MetaX_c-500", "taskId": "5645467", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-19T20:30:42.450583+00:00", "modelId": "IFM/Jais-3-7B-MLX-4bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7183832504, "estimatedRequiredGiB": 8.052, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 7204697873, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2021625856, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jais-3", "custom_tag:dense", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7204697873}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-19T11:58:27.074732+00:00", "targetGpu": "MetaX_c-500", "taskId": "5651876", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e9c4f4f15802a39a57c6e07956c53755f75fc438be43d1164a8a2eda32456b1e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3120573152, "estimatedRequiredGiB": 21.793, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 19499943398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2697198592, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:12 reasoning modes", "custom_tag:12 instruct modes", "custom_tag:Turbo-Brilliance", "custom_tag:NEO Imatrix", "custom_tag:Max Quants", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19499943398}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-20T04:13:55.532076+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5668972", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-20T12:39:15.571280+00:00", "modelId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e9c4f4f15802a39a57c6e07956c53755f75fc438be43d1164a8a2eda32456b1e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3120573152, "estimatedRequiredGiB": 21.793, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 19499943398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2697198592, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:12 reasoning modes", "custom_tag:12 instruct modes", "custom_tag:Turbo-Brilliance", "custom_tag:NEO Imatrix", "custom_tag:Max Quants", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19499943398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-20T04:13:55.532076+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5668972", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user