state: generation 24270 (cycle)
This commit is contained in:
@@ -2748,7 +2748,7 @@
|
|||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-10-13T10:49:23.863111+00:00",
|
"generatedAt": "2026-10-13T11:06:54.597830+00:00",
|
||||||
"summary": {
|
"summary": {
|
||||||
"activeBlockCount": 137,
|
"activeBlockCount": 137,
|
||||||
"byGpuFramework": {
|
"byGpuFramework": {
|
||||||
|
|||||||
@@ -414,99 +414,99 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"frameworkUpdatedAt": null,
|
"frameworkUpdatedAt": null,
|
||||||
"generatedAt": "2026-10-13T11:02:31.386633+00:00",
|
"generatedAt": "2026-10-13T11:08:23.274856+00:00",
|
||||||
"gpuStats": {
|
"gpuStats": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1241.6934306569344,
|
"backlogHours": 1269.44776119403,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Ascend_910-b3",
|
"gpu": "Ascend_910-b3",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 8,
|
"maxConcurrentTasks": 8,
|
||||||
"qualityFactor": 1.6375186375297646,
|
"qualityFactor": 1.4106630049453348,
|
||||||
"queueFactor": 0.9797353756067583,
|
"queueFactor": 0.9752671121954923,
|
||||||
"queueWeight": 0.9797353756067583,
|
"queueWeight": 0.9752671121954923,
|
||||||
"recentSuccess": 41,
|
"recentSuccess": 38,
|
||||||
"recentSuccessRate": 0.29927007299270075,
|
"recentSuccessRate": 0.2835820895522388,
|
||||||
"recentTerminal": 137,
|
"recentTerminal": 134,
|
||||||
"recentWilsonLowerBound": 0.22891666332550556,
|
"recentWilsonLowerBound": 0.2141253553890085,
|
||||||
"running": 7,
|
"running": 6,
|
||||||
"selectionWeight": 1.604334937403291,
|
"selectionWeight": 1.3757732351140521,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 22.833333333333332,
|
"throughputPerHour": 22.333333333333332,
|
||||||
"waiting": 28352
|
"waiting": 28351
|
||||||
},
|
},
|
||||||
"Biren_166m": {
|
"Biren_166m": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 174.2918918918919,
|
"backlogHours": 174.16216216216216,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Biren_166m",
|
"gpu": "Biren_166m",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 8,
|
"maxConcurrentTasks": 8,
|
||||||
"qualityFactor": 0.40005961526620026,
|
"qualityFactor": 0.47000026220442115,
|
||||||
"queueFactor": 1.3,
|
"queueFactor": 1.3,
|
||||||
"queueWeight": 1.3,
|
"queueWeight": 1.3,
|
||||||
"recentSuccess": 31,
|
"recentSuccess": 33,
|
||||||
"recentSuccessRate": 0.16756756756756758,
|
"recentSuccessRate": 0.1783783783783784,
|
||||||
"recentTerminal": 185,
|
"recentTerminal": 185,
|
||||||
"recentWilsonLowerBound": 0.12063341342339436,
|
"recentWilsonLowerBound": 0.1299278067352906,
|
||||||
"running": 8,
|
"running": 7,
|
||||||
"selectionWeight": 0.5200774998460603,
|
"selectionWeight": 0.6110003408657475,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 30.833333333333332,
|
"throughputPerHour": 30.833333333333332,
|
||||||
"waiting": 5374
|
"waiting": 5370
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x4": {
|
"Cambricon_mlu-370-x4": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1175.858823529412,
|
"backlogHours": 1189.5714285714287,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Cambricon_mlu-370-x4",
|
"gpu": "Cambricon_mlu-370-x4",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 7,
|
"maxConcurrentTasks": 7,
|
||||||
"qualityFactor": 0.7222644440021432,
|
"qualityFactor": 0.6433628845126895,
|
||||||
"queueFactor": 0.9877741799759399,
|
"queueFactor": 0.9848208296591828,
|
||||||
"queueWeight": 0.9877741799759399,
|
"queueWeight": 0.9848208296591828,
|
||||||
"recentSuccess": 20,
|
"recentSuccess": 19,
|
||||||
"recentSuccessRate": 0.23529411764705882,
|
"recentSuccessRate": 0.2261904761904762,
|
||||||
"recentTerminal": 85,
|
"recentTerminal": 84,
|
||||||
"recentWilsonLowerBound": 0.1577942000874349,
|
"recentWilsonLowerBound": 0.14985904898307537,
|
||||||
"running": 7,
|
"running": 7,
|
||||||
"selectionWeight": 0.7134341688999951,
|
"selectionWeight": 0.633597169697712,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 14.166666666666666,
|
"throughputPerHour": 14.0,
|
||||||
"waiting": 16658
|
"waiting": 16654
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x8": {
|
"Cambricon_mlu-370-x8": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 409.3282442748092,
|
"backlogHours": 397.2888888888889,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Cambricon_mlu-370-x8",
|
"gpu": "Cambricon_mlu-370-x8",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 7,
|
"maxConcurrentTasks": 7,
|
||||||
"qualityFactor": 0.8009169116850051,
|
"qualityFactor": 0.7464059921108056,
|
||||||
"queueFactor": 1.157178058096492,
|
"queueFactor": 1.160913446381819,
|
||||||
"queueWeight": 1.157178058096492,
|
"queueWeight": 1.160913446381819,
|
||||||
"recentSuccess": 30,
|
"recentSuccess": 30,
|
||||||
"recentSuccessRate": 0.22900763358778625,
|
"recentSuccessRate": 0.2222222222222222,
|
||||||
"recentTerminal": 131,
|
"recentTerminal": 135,
|
||||||
"recentWilsonLowerBound": 0.16538500851400117,
|
"recentWilsonLowerBound": 0.1603281725224173,
|
||||||
"running": 7,
|
"running": 6,
|
||||||
"selectionWeight": 0.9268034765602939,
|
"selectionWeight": 0.866512752701396,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 21.833333333333332,
|
"throughputPerHour": 22.5,
|
||||||
"waiting": 8937
|
"waiting": 8939
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-100": {
|
"Iluvatar_bi-100": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 45.63503649635037,
|
"backlogHours": 46.73684210526316,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Iluvatar_bi-100",
|
"gpu": "Iluvatar_bi-100",
|
||||||
@@ -515,197 +515,197 @@
|
|||||||
"qualityFactor": 0.05,
|
"qualityFactor": 0.05,
|
||||||
"queueFactor": 1.3,
|
"queueFactor": 1.3,
|
||||||
"queueWeight": 1.3,
|
"queueWeight": 1.3,
|
||||||
"recentSuccess": 9,
|
"recentSuccess": 10,
|
||||||
"recentSuccessRate": 0.021897810218978103,
|
"recentSuccessRate": 0.02506265664160401,
|
||||||
"recentTerminal": 411,
|
"recentTerminal": 399,
|
||||||
"recentWilsonLowerBound": 0.011562299880801982,
|
"recentWilsonLowerBound": 0.013669256410865761,
|
||||||
"running": 5,
|
"running": 9,
|
||||||
"selectionWeight": 0.065,
|
"selectionWeight": 0.065,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": false,
|
"submissionEligible": false,
|
||||||
"throughputPerHour": 68.5,
|
"throughputPerHour": 66.5,
|
||||||
"waiting": 3126
|
"waiting": 3108
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150": {
|
"Iluvatar_bi-150": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 164.0307692307692,
|
"backlogHours": 168.47430830039528,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Iluvatar_bi-150",
|
"gpu": "Iluvatar_bi-150",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 50,
|
"maxConcurrentTasks": 50,
|
||||||
"qualityFactor": 0.14295734602238894,
|
"qualityFactor": 0.1377938352233525,
|
||||||
"queueFactor": 1.3,
|
"queueFactor": 1.3,
|
||||||
"queueWeight": 1.3,
|
"queueWeight": 1.3,
|
||||||
"recentSuccess": 28,
|
"recentSuccess": 27,
|
||||||
"recentSuccessRate": 0.1076923076923077,
|
"recentSuccessRate": 0.1067193675889328,
|
||||||
"recentTerminal": 260,
|
"recentTerminal": 253,
|
||||||
"recentWilsonLowerBound": 0.07556539624250147,
|
"recentWilsonLowerBound": 0.07438566298944568,
|
||||||
"running": 15,
|
"running": 17,
|
||||||
"selectionWeight": 0.18584454982910562,
|
"selectionWeight": 0.17913198579035827,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 43.333333333333336,
|
"throughputPerHour": 42.166666666666664,
|
||||||
"waiting": 7108
|
"waiting": 7104
|
||||||
},
|
},
|
||||||
"Iluvatar_mrv-100": {
|
"Iluvatar_mrv-100": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1938.857142857143,
|
"backlogHours": 1900.1999999999998,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Iluvatar_mrv-100",
|
"gpu": "Iluvatar_mrv-100",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 2,
|
"maxConcurrentTasks": 2,
|
||||||
"qualityFactor": 0.35884907903007424,
|
"qualityFactor": 0.341938387892243,
|
||||||
"queueFactor": 0.9163873287721701,
|
"queueFactor": 0.9180068192451335,
|
||||||
"queueWeight": 0.9163873287721701,
|
"queueWeight": 0.9180068192451335,
|
||||||
"recentSuccess": 10,
|
"recentSuccess": 10,
|
||||||
"recentSuccessRate": 0.20408163265306123,
|
"recentSuccessRate": 0.2,
|
||||||
"recentTerminal": 49,
|
"recentTerminal": 50,
|
||||||
"recentWilsonLowerBound": 0.11481727042813812,
|
"recentWilsonLowerBound": 0.11243629945973886,
|
||||||
"running": 2,
|
"running": 2,
|
||||||
"selectionWeight": 0.3288447489647231,
|
"selectionWeight": 0.31390177184676665,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 8.166666666666666,
|
"throughputPerHour": 8.333333333333334,
|
||||||
"waiting": 15834
|
"waiting": 15835
|
||||||
},
|
},
|
||||||
"Kunlunxin_p-800": {
|
"Kunlunxin_p-800": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 299.0470588235294,
|
"backlogHours": 295.56976744186045,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Kunlunxin_p-800",
|
"gpu": "Kunlunxin_p-800",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 8,
|
"maxConcurrentTasks": 8,
|
||||||
"qualityFactor": 0.44411932650235214,
|
"qualityFactor": 0.43162894969026144,
|
||||||
"queueFactor": 1.212969879922749,
|
"queueFactor": 1.213575507437635,
|
||||||
"queueWeight": 1.212969879922749,
|
"queueWeight": 1.213575507437635,
|
||||||
"recentSuccess": 30,
|
"recentSuccess": 30,
|
||||||
"recentSuccessRate": 0.17647058823529413,
|
"recentSuccessRate": 0.1744186046511628,
|
||||||
"recentTerminal": 170,
|
"recentTerminal": 172,
|
||||||
"recentWilsonLowerBound": 0.1265006037723213,
|
"recentWilsonLowerBound": 0.12499412236734236,
|
||||||
"running": 8,
|
"running": 8,
|
||||||
"selectionWeight": 0.5387033661389302,
|
"selectionWeight": 0.5238143216451325,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 28.333333333333332,
|
"throughputPerHour": 28.666666666666668,
|
||||||
"waiting": 8473
|
"waiting": 8473
|
||||||
},
|
},
|
||||||
"MetaX_c-500": {
|
"MetaX_c-500": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 747.6279069767442,
|
"backlogHours": 722.3595505617977,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "MetaX_c-500",
|
"gpu": "MetaX_c-500",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 4,
|
"maxConcurrentTasks": 4,
|
||||||
"qualityFactor": 2.5,
|
"qualityFactor": 2.5,
|
||||||
"queueFactor": 1.0572023539165551,
|
"queueFactor": 1.0613357457188284,
|
||||||
"queueWeight": 1.0572023539165551,
|
"queueWeight": 1.0613357457188284,
|
||||||
"recentSuccess": 32,
|
"recentSuccess": 33,
|
||||||
"recentSuccessRate": 0.37209302325581395,
|
"recentSuccessRate": 0.3707865168539326,
|
||||||
"recentTerminal": 86,
|
"recentTerminal": 89,
|
||||||
"recentWilsonLowerBound": 0.27746093282766765,
|
"recentWilsonLowerBound": 0.2777347664612416,
|
||||||
"running": 4,
|
"running": 3,
|
||||||
"selectionWeight": 2.6430058847913878,
|
"selectionWeight": 2.653339364297071,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 14.333333333333334,
|
"throughputPerHour": 14.833333333333334,
|
||||||
"waiting": 10716
|
"waiting": 10715
|
||||||
},
|
},
|
||||||
"Mthreads_s4000": {
|
"Mthreads_s4000": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 2232.705882352941,
|
"backlogHours": 2200.4347826086955,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Mthreads_s4000",
|
"gpu": "Mthreads_s4000",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 4,
|
"maxConcurrentTasks": 4,
|
||||||
"qualityFactor": 0.12549958341745843,
|
"qualityFactor": 0.0856719941009158,
|
||||||
"queueFactor": 0.8971937087025166,
|
"queueFactor": 0.8980272788133685,
|
||||||
"queueWeight": 0.8971937087025166,
|
"queueWeight": 0.8980272788133685,
|
||||||
"recentSuccess": 9,
|
"recentSuccess": 8,
|
||||||
"recentSuccessRate": 0.1323529411764706,
|
"recentSuccessRate": 0.11594202898550725,
|
||||||
"recentTerminal": 68,
|
"recentTerminal": 69,
|
||||||
"recentWilsonLowerBound": 0.07122163958543326,
|
"recentWilsonLowerBound": 0.059934265459584066,
|
||||||
"running": 4,
|
"running": 4,
|
||||||
"selectionWeight": 0.11259743668693038,
|
"selectionWeight": 0.07693578773296038,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 11.333333333333334,
|
"throughputPerHour": 11.5,
|
||||||
"waiting": 25304
|
"waiting": 25305
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1": {
|
"Sunrise_pt-200-x1": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 2142.6,
|
"backlogHours": 1847.2758620689656,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Sunrise_pt-200-x1",
|
"gpu": "Sunrise_pt-200-x1",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 2,
|
"maxConcurrentTasks": 2,
|
||||||
"qualityFactor": 0.05,
|
"qualityFactor": 0.05324223580195769,
|
||||||
"queueFactor": 0.9027547494697463,
|
"queueFactor": 0.9219047253894459,
|
||||||
"queueWeight": 0.9027547494697463,
|
"queueWeight": 0.9219047253894459,
|
||||||
"recentSuccess": 5,
|
"recentSuccess": 6,
|
||||||
"recentSuccessRate": 0.1,
|
"recentSuccessRate": 0.10344827586206896,
|
||||||
"recentTerminal": 50,
|
"recentTerminal": 58,
|
||||||
"recentWilsonLowerBound": 0.0434751239915711,
|
"recentWilsonLowerBound": 0.048280750158591554,
|
||||||
"running": 2,
|
"running": 2,
|
||||||
"selectionWeight": 0.045137737473487316,
|
"selectionWeight": 0.04908426877612393,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": false,
|
"submissionEligible": false,
|
||||||
"throughputPerHour": 8.333333333333334,
|
"throughputPerHour": 9.666666666666666,
|
||||||
"waiting": 17855
|
"waiting": 17857
|
||||||
},
|
},
|
||||||
"Vastai_va16": {
|
"Vastai_va16": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1302.081081081081,
|
"backlogHours": 1267.9736842105265,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Vastai_va16",
|
"gpu": "Vastai_va16",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 16,
|
"maxConcurrentTasks": 16,
|
||||||
"qualityFactor": 0.05,
|
"qualityFactor": 0.05,
|
||||||
"queueFactor": 0.9727813655682584,
|
"queueFactor": 0.9754370970731275,
|
||||||
"queueWeight": 0.9727813655682584,
|
"queueWeight": 0.9754370970731275,
|
||||||
"recentSuccess": 6,
|
"recentSuccess": 6,
|
||||||
"recentSuccessRate": 0.08108108108108109,
|
"recentSuccessRate": 0.07894736842105263,
|
||||||
"recentTerminal": 74,
|
"recentTerminal": 76,
|
||||||
"recentWilsonLowerBound": 0.03768933680933338,
|
"recentWilsonLowerBound": 0.03668350552145427,
|
||||||
"running": 16,
|
"running": 16,
|
||||||
"selectionWeight": 0.048639068278412925,
|
"selectionWeight": 0.04877185485365638,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": false,
|
"submissionEligible": false,
|
||||||
"throughputPerHour": 12.333333333333334,
|
"throughputPerHour": 12.666666666666666,
|
||||||
"waiting": 16059
|
"waiting": 16061
|
||||||
},
|
},
|
||||||
"hygon_k100-ai": {
|
"hygon_k100-ai": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1083.2773109243699,
|
"backlogHours": 1074.25,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "hygon_k100-ai",
|
"gpu": "hygon_k100-ai",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 6,
|
"maxConcurrentTasks": 6,
|
||||||
"qualityFactor": 1.386578329989826,
|
"qualityFactor": 1.3573042378082314,
|
||||||
"queueFactor": 1.0,
|
"queueFactor": 1.0,
|
||||||
"queueWeight": 1.0,
|
"queueWeight": 1.0,
|
||||||
"recentSuccess": 34,
|
"recentSuccess": 34,
|
||||||
"recentSuccessRate": 0.2857142857142857,
|
"recentSuccessRate": 0.2833333333333333,
|
||||||
"recentTerminal": 119,
|
"recentTerminal": 120,
|
||||||
"recentWilsonLowerBound": 0.2122463378919113,
|
"recentWilsonLowerBound": 0.2104050919824472,
|
||||||
"running": 6,
|
"running": 4,
|
||||||
"selectionWeight": 1.386578329989826,
|
"selectionWeight": 1.3573042378082314,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 19.833333333333332,
|
"throughputPerHour": 20.0,
|
||||||
"waiting": 21485
|
"waiting": 21485
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"queueAttemptedAt": "2026-10-13T10:57:08.361906+00:00",
|
"queueAttemptedAt": "2026-10-13T11:08:23.274856+00:00",
|
||||||
"queueError": null,
|
"queueError": null,
|
||||||
"queueUpdatedAt": "2026-10-13T10:57:08.361906+00:00",
|
"queueUpdatedAt": "2026-10-13T11:08:23.274856+00:00",
|
||||||
"supportedGpus": [
|
"supportedGpus": [
|
||||||
"Cambricon_mlu-370-x4",
|
"Cambricon_mlu-370-x4",
|
||||||
"Vastai_va16",
|
"Vastai_va16",
|
||||||
|
|||||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"generatedAt": "2026-10-12T21:59:39.834509+00:00",
|
"generatedAt": "2026-10-13T11:06:54.500688+00:00",
|
||||||
"lastSyncTime": "2026-10-12T21:59:39.775381+00:00",
|
"lastSyncTime": "2026-10-13T11:06:54.163794+00:00",
|
||||||
"recentLimit": 300,
|
"recentLimit": 300,
|
||||||
"report": {
|
"report": {
|
||||||
"architectureCompatibilityBlocks": {
|
"architectureCompatibilityBlocks": {
|
||||||
@@ -231,27 +231,6 @@
|
|||||||
"targetGpu": "Ascend_910-b3",
|
"targetGpu": "Ascend_910-b3",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
},
|
},
|
||||||
"ascend_910-b3|vllm|text-generation|architectures:spark2_5forcausallm": {
|
|
||||||
"architectureSignature": "architectures:spark2_5forcausallm",
|
|
||||||
"architectures": [
|
|
||||||
"spark2_5forcausallm"
|
|
||||||
],
|
|
||||||
"evidenceCount": 1,
|
|
||||||
"expiresAt": "2026-10-13T03:21:22+00:00",
|
|
||||||
"framework": "vllm",
|
|
||||||
"latestFailureAt": "2026-09-13T03:21:22+00:00",
|
|
||||||
"latestSuccessfulAt": null,
|
|
||||||
"matchType": "architectures",
|
|
||||||
"modelType": null,
|
|
||||||
"sourceModelIds": [
|
|
||||||
"XHToken/Spark-X2.5-1.7B"
|
|
||||||
],
|
|
||||||
"sourceTaskIds": [
|
|
||||||
"4558358"
|
|
||||||
],
|
|
||||||
"targetGpu": "Ascend_910-b3",
|
|
||||||
"taskType": "text-generation"
|
|
||||||
},
|
|
||||||
"ascend_910-b3|vllm|text-generation|model_type:deepseek_v4_dspark": {
|
"ascend_910-b3|vllm|text-generation|model_type:deepseek_v4_dspark": {
|
||||||
"architectureSignature": "model_type:deepseek_v4_dspark",
|
"architectureSignature": "model_type:deepseek_v4_dspark",
|
||||||
"architectures": [],
|
"architectures": [],
|
||||||
@@ -593,27 +572,6 @@
|
|||||||
"targetGpu": "Ascend_910-b4",
|
"targetGpu": "Ascend_910-b4",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
},
|
},
|
||||||
"ascend_910-b4|vllm|text-generation|architectures:spark2_5forcausallm": {
|
|
||||||
"architectureSignature": "architectures:spark2_5forcausallm",
|
|
||||||
"architectures": [
|
|
||||||
"spark2_5forcausallm"
|
|
||||||
],
|
|
||||||
"evidenceCount": 1,
|
|
||||||
"expiresAt": "2026-10-13T02:47:21+00:00",
|
|
||||||
"framework": "vllm",
|
|
||||||
"latestFailureAt": "2026-09-13T02:47:21+00:00",
|
|
||||||
"latestSuccessfulAt": null,
|
|
||||||
"matchType": "architectures",
|
|
||||||
"modelType": null,
|
|
||||||
"sourceModelIds": [
|
|
||||||
"XHToken/Spark-X2.5-1.7B"
|
|
||||||
],
|
|
||||||
"sourceTaskIds": [
|
|
||||||
"4557197"
|
|
||||||
],
|
|
||||||
"targetGpu": "Ascend_910-b4",
|
|
||||||
"taskType": "text-generation"
|
|
||||||
},
|
|
||||||
"ascend_910-b4|vllm|text-generation|model_type:deepseek_v4_dspark": {
|
"ascend_910-b4|vllm|text-generation|model_type:deepseek_v4_dspark": {
|
||||||
"architectureSignature": "model_type:deepseek_v4_dspark",
|
"architectureSignature": "model_type:deepseek_v4_dspark",
|
||||||
"architectures": [],
|
"architectures": [],
|
||||||
@@ -1482,25 +1440,6 @@
|
|||||||
"targetGpu": "hygon_k100-ai",
|
"targetGpu": "hygon_k100-ai",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
},
|
},
|
||||||
"hygon_k100-ai|vllm|text-generation|model_type:gemma4": {
|
|
||||||
"architectureSignature": "model_type:gemma4",
|
|
||||||
"architectures": [],
|
|
||||||
"evidenceCount": 1,
|
|
||||||
"expiresAt": "2026-10-13T00:07:21+00:00",
|
|
||||||
"framework": "vllm",
|
|
||||||
"latestFailureAt": "2026-09-13T00:07:21+00:00",
|
|
||||||
"latestSuccessfulAt": null,
|
|
||||||
"matchType": "model_type",
|
|
||||||
"modelType": "gemma4",
|
|
||||||
"sourceModelIds": [
|
|
||||||
"nv-community/Gemma-4-31B-IT-NVFP4"
|
|
||||||
],
|
|
||||||
"sourceTaskIds": [
|
|
||||||
"4079956"
|
|
||||||
],
|
|
||||||
"targetGpu": "hygon_k100-ai",
|
|
||||||
"taskType": "text-generation"
|
|
||||||
},
|
|
||||||
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": {
|
"hygon_k100-ai|vllm|text-generation|model_type:qwen3_5": {
|
||||||
"architectureSignature": "model_type:qwen3_5",
|
"architectureSignature": "model_type:qwen3_5",
|
||||||
"architectures": [],
|
"architectures": [],
|
||||||
@@ -1909,27 +1848,6 @@
|
|||||||
"targetGpu": "Iluvatar_bi-150",
|
"targetGpu": "Iluvatar_bi-150",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
},
|
},
|
||||||
"iluvatar_bi-150|vllm|text-generation|architectures:spark2_5forcausallm": {
|
|
||||||
"architectureSignature": "architectures:spark2_5forcausallm",
|
|
||||||
"architectures": [
|
|
||||||
"spark2_5forcausallm"
|
|
||||||
],
|
|
||||||
"evidenceCount": 1,
|
|
||||||
"expiresAt": "2026-10-13T01:11:21+00:00",
|
|
||||||
"framework": "vllm",
|
|
||||||
"latestFailureAt": "2026-09-13T01:11:21+00:00",
|
|
||||||
"latestSuccessfulAt": null,
|
|
||||||
"matchType": "architectures",
|
|
||||||
"modelType": null,
|
|
||||||
"sourceModelIds": [
|
|
||||||
"XHToken/Spark-X2.5-1.7B"
|
|
||||||
],
|
|
||||||
"sourceTaskIds": [
|
|
||||||
"4557834"
|
|
||||||
],
|
|
||||||
"targetGpu": "Iluvatar_bi-150",
|
|
||||||
"taskType": "text-generation"
|
|
||||||
},
|
|
||||||
"iluvatar_bi-150|vllm|text-generation|architectures:zayaforcausallm": {
|
"iluvatar_bi-150|vllm|text-generation|architectures:zayaforcausallm": {
|
||||||
"architectureSignature": "architectures:zayaforcausallm",
|
"architectureSignature": "architectures:zayaforcausallm",
|
||||||
"architectures": [
|
"architectures": [
|
||||||
@@ -2553,25 +2471,6 @@
|
|||||||
"targetGpu": "Mthreads_s4000",
|
"targetGpu": "Mthreads_s4000",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
},
|
},
|
||||||
"mthreads_s4000|vllm|text-generation|model_type:nemotron_h": {
|
|
||||||
"architectureSignature": "model_type:nemotron_h",
|
|
||||||
"architectures": [],
|
|
||||||
"evidenceCount": 1,
|
|
||||||
"expiresAt": "2026-10-13T02:09:21+00:00",
|
|
||||||
"framework": "vllm",
|
|
||||||
"latestFailureAt": "2026-09-13T02:09:21+00:00",
|
|
||||||
"latestSuccessfulAt": null,
|
|
||||||
"matchType": "model_type",
|
|
||||||
"modelType": "nemotron_h",
|
|
||||||
"sourceModelIds": [
|
|
||||||
"primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8"
|
|
||||||
],
|
|
||||||
"sourceTaskIds": [
|
|
||||||
"4543931"
|
|
||||||
],
|
|
||||||
"targetGpu": "Mthreads_s4000",
|
|
||||||
"taskType": "text-generation"
|
|
||||||
},
|
|
||||||
"mthreads_s4000|vllm|text-generation|model_type:qwen3_5": {
|
"mthreads_s4000|vllm|text-generation|model_type:qwen3_5": {
|
||||||
"architectureSignature": "model_type:qwen3_5",
|
"architectureSignature": "model_type:qwen3_5",
|
||||||
"architectures": [],
|
"architectures": [],
|
||||||
@@ -2808,27 +2707,6 @@
|
|||||||
"targetGpu": "Vastai_va16",
|
"targetGpu": "Vastai_va16",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
},
|
},
|
||||||
"vastai_va16|vllm|text-generation|architectures:spark2_5forcausallm": {
|
|
||||||
"architectureSignature": "architectures:spark2_5forcausallm",
|
|
||||||
"architectures": [
|
|
||||||
"spark2_5forcausallm"
|
|
||||||
],
|
|
||||||
"evidenceCount": 1,
|
|
||||||
"expiresAt": "2026-10-13T09:33:21+00:00",
|
|
||||||
"framework": "vllm",
|
|
||||||
"latestFailureAt": "2026-09-13T09:33:21+00:00",
|
|
||||||
"latestSuccessfulAt": null,
|
|
||||||
"matchType": "architectures",
|
|
||||||
"modelType": null,
|
|
||||||
"sourceModelIds": [
|
|
||||||
"XHToken/Spark-X2.5-1.7B"
|
|
||||||
],
|
|
||||||
"sourceTaskIds": [
|
|
||||||
"4557415"
|
|
||||||
],
|
|
||||||
"targetGpu": "Vastai_va16",
|
|
||||||
"taskType": "text-generation"
|
|
||||||
},
|
|
||||||
"vastai_va16|vllm|text-generation|model_type:qwen3_5": {
|
"vastai_va16|vllm|text-generation|model_type:qwen3_5": {
|
||||||
"architectureSignature": "model_type:qwen3_5",
|
"architectureSignature": "model_type:qwen3_5",
|
||||||
"architectures": [],
|
"architectures": [],
|
||||||
@@ -2875,11 +2753,11 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"architectureCompatibilitySummary": {
|
"architectureCompatibilitySummary": {
|
||||||
"activeBlockCount": 143,
|
"activeBlockCount": 137,
|
||||||
"byGpuFramework": {
|
"byGpuFramework": {
|
||||||
"Ascend_910-b3|vllm": 9,
|
"Ascend_910-b3|vllm": 8,
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch": 10,
|
"Ascend_910-b3|vllm_tokenizer_patch": 10,
|
||||||
"Ascend_910-b4|vllm": 7,
|
"Ascend_910-b4|vllm": 6,
|
||||||
"Ascend_910-b4|vllm_tokenizer_patch": 9,
|
"Ascend_910-b4|vllm_tokenizer_patch": 9,
|
||||||
"Biren_166m|vllm": 3,
|
"Biren_166m|vllm": 3,
|
||||||
"Cambricon_mlu-370-x4|vllm": 4,
|
"Cambricon_mlu-370-x4|vllm": 4,
|
||||||
@@ -2889,7 +2767,7 @@
|
|||||||
"Cambricon_mlu-370-x8|vllm-customized": 6,
|
"Cambricon_mlu-370-x8|vllm-customized": 6,
|
||||||
"Cambricon_mlu-370-x8|vllm-mlu": 3,
|
"Cambricon_mlu-370-x8|vllm-mlu": 3,
|
||||||
"Iluvatar_bi-150|transformers": 5,
|
"Iluvatar_bi-150|transformers": 5,
|
||||||
"Iluvatar_bi-150|vllm": 5,
|
"Iluvatar_bi-150|vllm": 4,
|
||||||
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 5,
|
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 5,
|
||||||
"Iluvatar_bi-150|vllm_tokenizer_patch": 2,
|
"Iluvatar_bi-150|vllm_tokenizer_patch": 2,
|
||||||
"Iluvatar_mrv-100|vllm": 4,
|
"Iluvatar_mrv-100|vllm": 4,
|
||||||
@@ -2897,12 +2775,12 @@
|
|||||||
"Kunlunxin_p-800|vllm_tokenizer_patch": 9,
|
"Kunlunxin_p-800|vllm_tokenizer_patch": 9,
|
||||||
"MetaX_c-500|vllm": 1,
|
"MetaX_c-500|vllm": 1,
|
||||||
"MetaX_c-500|vllm_tokenizer_patch": 4,
|
"MetaX_c-500|vllm_tokenizer_patch": 4,
|
||||||
"Mthreads_s4000|vllm": 6,
|
"Mthreads_s4000|vllm": 5,
|
||||||
"Sunrise_pt-200-x1|vllm": 2,
|
"Sunrise_pt-200-x1|vllm": 2,
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 3,
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 3,
|
||||||
"Vastai_va16|vllm": 5,
|
"Vastai_va16|vllm": 4,
|
||||||
"Vastai_va16|vllm_fix_tokenizer": 2,
|
"Vastai_va16|vllm_fix_tokenizer": 2,
|
||||||
"hygon_k100-ai|vllm": 7,
|
"hygon_k100-ai|vllm": 6,
|
||||||
"hygon_k100-ai|vllm-patch-tokenizer": 5
|
"hygon_k100-ai|vllm-patch-tokenizer": 5
|
||||||
},
|
},
|
||||||
"ttlDays": 30
|
"ttlDays": 30
|
||||||
@@ -5047,19 +4925,19 @@
|
|||||||
"unresolvedFailureCount": 296
|
"unresolvedFailureCount": 296
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||||
"attributableFailureCount": 133,
|
"attributableFailureCount": 135,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 133,
|
"decisionTotal": 135,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 2,
|
"ambiguous_runtime": 2,
|
||||||
"backend_operator": 10,
|
"backend_operator": 11,
|
||||||
"framework_architecture_unsupported": 26,
|
"framework_architecture_unsupported": 27,
|
||||||
"platform_infrastructure": 29,
|
"platform_infrastructure": 29,
|
||||||
"tokenizer_compatibility": 97,
|
"tokenizer_compatibility": 97,
|
||||||
"参数/模板问题": 9
|
"参数/模板问题": 9
|
||||||
},
|
},
|
||||||
"failureCount": 173,
|
"failureCount": 175,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_fix_tokenizer",
|
"framework": "vllm_fix_tokenizer",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
@@ -5069,38 +4947,38 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Sunrise_pt-200-x1",
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 173,
|
"total": 175,
|
||||||
"unresolvedFailureCount": 11
|
"unresolvedFailureCount": 11
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||||
"attributableFailureCount": 624,
|
"attributableFailureCount": 625,
|
||||||
"decisionFailureRate": 0.9842,
|
"decisionFailureRate": 0.9843,
|
||||||
"decisionSuccessRate": 0.0158,
|
"decisionSuccessRate": 0.0157,
|
||||||
"decisionTotal": 634,
|
"decisionTotal": 635,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 109,
|
"ambiguous_runtime": 109,
|
||||||
"architecture_compatibility": 43,
|
"architecture_compatibility": 43,
|
||||||
"backend_operator": 30,
|
"backend_operator": 30,
|
||||||
"context_length": 34,
|
"context_length": 34,
|
||||||
"framework_architecture_unsupported": 147,
|
"framework_architecture_unsupported": 148,
|
||||||
"memory_capacity": 113,
|
"memory_capacity": 113,
|
||||||
"platform_infrastructure": 219,
|
"platform_infrastructure": 220,
|
||||||
"repository_structure": 75,
|
"repository_structure": 75,
|
||||||
"runtime_memory": 1,
|
"runtime_memory": 1,
|
||||||
"tokenizer_compatibility": 181,
|
"tokenizer_compatibility": 181,
|
||||||
"参数/模板问题": 9
|
"参数/模板问题": 9
|
||||||
},
|
},
|
||||||
"failureCount": 961,
|
"failureCount": 963,
|
||||||
"failureRate": 0.9897,
|
"failureRate": 0.9897,
|
||||||
"framework": "vllm",
|
"framework": "vllm",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 219,
|
"platformFailureCount": 220,
|
||||||
"successCount": 10,
|
"successCount": 10,
|
||||||
"successRate": 0.0103,
|
"successRate": 0.0103,
|
||||||
"targetGpu": "Sunrise_pt-200-x1",
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 971,
|
"total": 973,
|
||||||
"unresolvedFailureCount": 118
|
"unresolvedFailureCount": 118
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm|unknown": {
|
"Sunrise_pt-200-x1|vllm|unknown": {
|
||||||
@@ -5603,33 +5481,33 @@
|
|||||||
"unresolvedFailureCount": 6552
|
"unresolvedFailureCount": 6552
|
||||||
},
|
},
|
||||||
"vllm": {
|
"vllm": {
|
||||||
"attributableFailureCount": 3695,
|
"attributableFailureCount": 3696,
|
||||||
"decisionFailureRate": 0.9711,
|
"decisionFailureRate": 0.9711,
|
||||||
"decisionSuccessRate": 0.0289,
|
"decisionSuccessRate": 0.0289,
|
||||||
"decisionTotal": 3805,
|
"decisionTotal": 3806,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 1606,
|
"ambiguous_runtime": 1606,
|
||||||
"architecture_compatibility": 112,
|
"architecture_compatibility": 112,
|
||||||
"attention_backend": 3,
|
"attention_backend": 3,
|
||||||
"backend_operator": 95,
|
"backend_operator": 95,
|
||||||
"context_length": 161,
|
"context_length": 161,
|
||||||
"framework_architecture_unsupported": 1411,
|
"framework_architecture_unsupported": 1412,
|
||||||
"memory_capacity": 725,
|
"memory_capacity": 725,
|
||||||
"model_load": 228,
|
"model_load": 228,
|
||||||
"platform_infrastructure": 883,
|
"platform_infrastructure": 884,
|
||||||
"repository_structure": 470,
|
"repository_structure": 470,
|
||||||
"runtime_memory": 66,
|
"runtime_memory": 66,
|
||||||
"tokenizer_compatibility": 424,
|
"tokenizer_compatibility": 424,
|
||||||
"参数/模板问题": 87
|
"参数/模板问题": 87
|
||||||
},
|
},
|
||||||
"failureCount": 6271,
|
"failureCount": 6273,
|
||||||
"failureRate": 0.9828,
|
"failureRate": 0.9828,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 883,
|
"platformFailureCount": 884,
|
||||||
"successCount": 110,
|
"successCount": 110,
|
||||||
"successRate": 0.0172,
|
"successRate": 0.0172,
|
||||||
"total": 6381,
|
"total": 6383,
|
||||||
"unresolvedFailureCount": 1693
|
"unresolvedFailureCount": 1693
|
||||||
},
|
},
|
||||||
"vllm-customized": {
|
"vllm-customized": {
|
||||||
@@ -5727,28 +5605,28 @@
|
|||||||
"unresolvedFailureCount": 57
|
"unresolvedFailureCount": 57
|
||||||
},
|
},
|
||||||
"vllm_fix_tokenizer": {
|
"vllm_fix_tokenizer": {
|
||||||
"attributableFailureCount": 182,
|
"attributableFailureCount": 184,
|
||||||
"decisionFailureRate": 0.9733,
|
"decisionFailureRate": 0.9735,
|
||||||
"decisionSuccessRate": 0.0267,
|
"decisionSuccessRate": 0.0265,
|
||||||
"decisionTotal": 187,
|
"decisionTotal": 189,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 419,
|
"ambiguous_runtime": 419,
|
||||||
"backend_operator": 10,
|
"backend_operator": 11,
|
||||||
"framework_architecture_unsupported": 52,
|
"framework_architecture_unsupported": 53,
|
||||||
"memory_capacity": 10,
|
"memory_capacity": 10,
|
||||||
"model_load": 13,
|
"model_load": 13,
|
||||||
"platform_infrastructure": 29,
|
"platform_infrastructure": 29,
|
||||||
"tokenizer_compatibility": 97,
|
"tokenizer_compatibility": 97,
|
||||||
"参数/模板问题": 22
|
"参数/模板问题": 22
|
||||||
},
|
},
|
||||||
"failureCount": 652,
|
"failureCount": 654,
|
||||||
"failureRate": 0.9924,
|
"failureRate": 0.9924,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 29,
|
"platformFailureCount": 29,
|
||||||
"successCount": 5,
|
"successCount": 5,
|
||||||
"successRate": 0.0076,
|
"successRate": 0.0076,
|
||||||
"total": 657,
|
"total": 659,
|
||||||
"unresolvedFailureCount": 441
|
"unresolvedFailureCount": 441
|
||||||
},
|
},
|
||||||
"vllm_tokenizer_patch": {
|
"vllm_tokenizer_patch": {
|
||||||
@@ -5780,7 +5658,7 @@
|
|||||||
"unresolvedFailureCount": 334
|
"unresolvedFailureCount": 334
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-10-12T21:59:39.821882+00:00",
|
"generatedAt": "2026-10-13T11:06:54.485257+00:00",
|
||||||
"gpuSummaries": {
|
"gpuSummaries": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"attributableFailureCount": 130,
|
"attributableFailureCount": 130,
|
||||||
@@ -6116,32 +5994,32 @@
|
|||||||
"unresolvedFailureCount": 331
|
"unresolvedFailureCount": 331
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1": {
|
"Sunrise_pt-200-x1": {
|
||||||
"attributableFailureCount": 776,
|
"attributableFailureCount": 779,
|
||||||
"decisionFailureRate": 0.8828,
|
"decisionFailureRate": 0.8832,
|
||||||
"decisionSuccessRate": 0.1172,
|
"decisionSuccessRate": 0.1168,
|
||||||
"decisionTotal": 879,
|
"decisionTotal": 882,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 164,
|
"ambiguous_runtime": 164,
|
||||||
"architecture_compatibility": 44,
|
"architecture_compatibility": 44,
|
||||||
"backend_operator": 40,
|
"backend_operator": 41,
|
||||||
"context_length": 39,
|
"context_length": 39,
|
||||||
"framework_architecture_unsupported": 175,
|
"framework_architecture_unsupported": 177,
|
||||||
"memory_capacity": 113,
|
"memory_capacity": 113,
|
||||||
"platform_infrastructure": 248,
|
"platform_infrastructure": 249,
|
||||||
"repository_structure": 83,
|
"repository_structure": 83,
|
||||||
"runtime_memory": 1,
|
"runtime_memory": 1,
|
||||||
"tokenizer_compatibility": 281,
|
"tokenizer_compatibility": 281,
|
||||||
"参数/模板问题": 231,
|
"参数/模板问题": 231,
|
||||||
"验证失败": 32
|
"验证失败": 32
|
||||||
},
|
},
|
||||||
"failureCount": 1451,
|
"failureCount": 1455,
|
||||||
"failureRate": 0.9337,
|
"failureRate": 0.9339,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 248,
|
"platformFailureCount": 249,
|
||||||
"successCount": 103,
|
"successCount": 103,
|
||||||
"successRate": 0.0663,
|
"successRate": 0.0661,
|
||||||
"total": 1554,
|
"total": 1558,
|
||||||
"unresolvedFailureCount": 427
|
"unresolvedFailureCount": 427
|
||||||
},
|
},
|
||||||
"Vastai_va16": {
|
"Vastai_va16": {
|
||||||
@@ -23526,16 +23404,16 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
|
||||||
"attributableFailureCount": 6,
|
"attributableFailureCount": 7,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 6,
|
"decisionTotal": 7,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"framework_architecture_unsupported": 6,
|
"framework_architecture_unsupported": 7,
|
||||||
"platform_infrastructure": 1,
|
"platform_infrastructure": 1,
|
||||||
"参数/模板问题": 1
|
"参数/模板问题": 1
|
||||||
},
|
},
|
||||||
"failureCount": 8,
|
"failureCount": 9,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_fix_tokenizer",
|
"framework": "vllm_fix_tokenizer",
|
||||||
"modelType": "qwen3_5_moe",
|
"modelType": "qwen3_5_moe",
|
||||||
@@ -23547,7 +23425,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Sunrise_pt-200-x1",
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 8,
|
"total": 9,
|
||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
|
||||||
@@ -23736,6 +23614,29 @@
|
|||||||
"total": 1,
|
"total": 1,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|stablelm|none": {
|
||||||
|
"attributableFailureCount": 1,
|
||||||
|
"decisionFailureRate": 1.0,
|
||||||
|
"decisionSuccessRate": 0.0,
|
||||||
|
"decisionTotal": 1,
|
||||||
|
"failureBreakdown": {
|
||||||
|
"backend_operator": 1
|
||||||
|
},
|
||||||
|
"failureCount": 1,
|
||||||
|
"failureRate": 1.0,
|
||||||
|
"framework": "vllm_fix_tokenizer",
|
||||||
|
"modelType": "stablelm",
|
||||||
|
"pendingCount": 0,
|
||||||
|
"pendingRate": 0.0,
|
||||||
|
"platformFailureCount": 0,
|
||||||
|
"quantizationMethod": "none",
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
|
"taskType": "text-generation",
|
||||||
|
"total": 1,
|
||||||
|
"unresolvedFailureCount": 0
|
||||||
|
},
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
|
||||||
"attributableFailureCount": 3,
|
"attributableFailureCount": 3,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
@@ -23939,6 +23840,29 @@
|
|||||||
"total": 1,
|
"total": 1,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
|
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5_text|none": {
|
||||||
|
"attributableFailureCount": 0,
|
||||||
|
"decisionFailureRate": 0.0,
|
||||||
|
"decisionSuccessRate": 0.0,
|
||||||
|
"decisionTotal": 0,
|
||||||
|
"failureBreakdown": {
|
||||||
|
"platform_infrastructure": 1
|
||||||
|
},
|
||||||
|
"failureCount": 1,
|
||||||
|
"failureRate": 1.0,
|
||||||
|
"framework": "vllm",
|
||||||
|
"modelType": "qwen3_5_text",
|
||||||
|
"pendingCount": 0,
|
||||||
|
"pendingRate": 0.0,
|
||||||
|
"platformFailureCount": 1,
|
||||||
|
"quantizationMethod": "none",
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
|
"taskType": "text-generation",
|
||||||
|
"total": 1,
|
||||||
|
"unresolvedFailureCount": 0
|
||||||
|
},
|
||||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors": {
|
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 1,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
@@ -24011,15 +23935,15 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none": {
|
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none": {
|
||||||
"attributableFailureCount": 2,
|
"attributableFailureCount": 3,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 2,
|
"decisionTotal": 3,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"framework_architecture_unsupported": 2,
|
"framework_architecture_unsupported": 3,
|
||||||
"platform_infrastructure": 7
|
"platform_infrastructure": 7
|
||||||
},
|
},
|
||||||
"failureCount": 9,
|
"failureCount": 10,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm",
|
"framework": "vllm",
|
||||||
"modelType": "qwen3_5",
|
"modelType": "qwen3_5",
|
||||||
@@ -24031,7 +23955,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Sunrise_pt-200-x1",
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 9,
|
"total": 10,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3|none": {
|
"Sunrise_pt-200-x1|vllm|text-generation|qwen3|none": {
|
||||||
@@ -54891,14 +54815,14 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|33": {
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|33": {
|
||||||
"attributableFailureCount": 2,
|
"attributableFailureCount": 3,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 2,
|
"decisionTotal": 3,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"framework_architecture_unsupported": 2
|
"framework_architecture_unsupported": 3
|
||||||
},
|
},
|
||||||
"failureCount": 2,
|
"failureCount": 3,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_fix_tokenizer",
|
"framework": "vllm_fix_tokenizer",
|
||||||
"loadSizeLog2Bucket": 33,
|
"loadSizeLog2Bucket": 33,
|
||||||
@@ -54911,7 +54835,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Sunrise_pt-200-x1",
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 2,
|
"total": 3,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": {
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": {
|
||||||
@@ -55205,6 +55129,30 @@
|
|||||||
"total": 1,
|
"total": 1,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|stablelm|none|31": {
|
||||||
|
"attributableFailureCount": 1,
|
||||||
|
"decisionFailureRate": 1.0,
|
||||||
|
"decisionSuccessRate": 0.0,
|
||||||
|
"decisionTotal": 1,
|
||||||
|
"failureBreakdown": {
|
||||||
|
"backend_operator": 1
|
||||||
|
},
|
||||||
|
"failureCount": 1,
|
||||||
|
"failureRate": 1.0,
|
||||||
|
"framework": "vllm_fix_tokenizer",
|
||||||
|
"loadSizeLog2Bucket": 31,
|
||||||
|
"modelType": "stablelm",
|
||||||
|
"pendingCount": 0,
|
||||||
|
"pendingRate": 0.0,
|
||||||
|
"platformFailureCount": 0,
|
||||||
|
"quantizationMethod": "none",
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
|
"taskType": "text-generation",
|
||||||
|
"total": 1,
|
||||||
|
"unresolvedFailureCount": 0
|
||||||
|
},
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": {
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 1,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
@@ -55513,6 +55461,30 @@
|
|||||||
"total": 1,
|
"total": 1,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
|
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5_text|none|32": {
|
||||||
|
"attributableFailureCount": 0,
|
||||||
|
"decisionFailureRate": 0.0,
|
||||||
|
"decisionSuccessRate": 0.0,
|
||||||
|
"decisionTotal": 0,
|
||||||
|
"failureBreakdown": {
|
||||||
|
"platform_infrastructure": 1
|
||||||
|
},
|
||||||
|
"failureCount": 1,
|
||||||
|
"failureRate": 1.0,
|
||||||
|
"framework": "vllm",
|
||||||
|
"loadSizeLog2Bucket": 32,
|
||||||
|
"modelType": "qwen3_5_text",
|
||||||
|
"pendingCount": 0,
|
||||||
|
"pendingRate": 0.0,
|
||||||
|
"platformFailureCount": 1,
|
||||||
|
"quantizationMethod": "none",
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
|
"taskType": "text-generation",
|
||||||
|
"total": 1,
|
||||||
|
"unresolvedFailureCount": 0
|
||||||
|
},
|
||||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors|33": {
|
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|compressed-tensors|33": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 1,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
@@ -55684,15 +55656,15 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|34": {
|
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|34": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 2,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 1,
|
"decisionTotal": 2,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"framework_architecture_unsupported": 1,
|
"framework_architecture_unsupported": 2,
|
||||||
"platform_infrastructure": 3
|
"platform_infrastructure": 3
|
||||||
},
|
},
|
||||||
"failureCount": 4,
|
"failureCount": 5,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm",
|
"framework": "vllm",
|
||||||
"loadSizeLog2Bucket": 34,
|
"loadSizeLog2Bucket": 34,
|
||||||
@@ -55705,7 +55677,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Sunrise_pt-200-x1",
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 4,
|
"total": 5,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm|text-generation|qwen3|none|13": {
|
"Sunrise_pt-200-x1|vllm|text-generation|qwen3|none|13": {
|
||||||
@@ -59264,23 +59236,23 @@
|
|||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"terminalRecords": 17853,
|
"terminalRecords": 17857,
|
||||||
"totalRecords": 18378,
|
"totalRecords": 18382,
|
||||||
"totals": {
|
"totals": {
|
||||||
"attributableFailureCount": 6321,
|
"attributableFailureCount": 6324,
|
||||||
"decisionFailureRate": 0.8654,
|
"decisionFailureRate": 0.8655,
|
||||||
"decisionSuccessRate": 0.1346,
|
"decisionSuccessRate": 0.1345,
|
||||||
"decisionTotal": 7304,
|
"decisionTotal": 7307,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 4637,
|
"ambiguous_runtime": 4637,
|
||||||
"architecture_compatibility": 212,
|
"architecture_compatibility": 212,
|
||||||
"attention_backend": 3,
|
"attention_backend": 3,
|
||||||
"backend_operator": 131,
|
"backend_operator": 132,
|
||||||
"context_length": 327,
|
"context_length": 327,
|
||||||
"framework_architecture_unsupported": 2333,
|
"framework_architecture_unsupported": 2335,
|
||||||
"memory_capacity": 1206,
|
"memory_capacity": 1206,
|
||||||
"model_load": 571,
|
"model_load": 571,
|
||||||
"platform_infrastructure": 960,
|
"platform_infrastructure": 961,
|
||||||
"repository_structure": 742,
|
"repository_structure": 742,
|
||||||
"runtime_memory": 101,
|
"runtime_memory": 101,
|
||||||
"tokenizer_compatibility": 695,
|
"tokenizer_compatibility": 695,
|
||||||
@@ -59288,31 +59260,31 @@
|
|||||||
"日志缺失": 719,
|
"日志缺失": 719,
|
||||||
"验证失败": 676
|
"验证失败": 676
|
||||||
},
|
},
|
||||||
"failureCount": 16870,
|
"failureCount": 16874,
|
||||||
"failureRate": 0.9449,
|
"failureRate": 0.945,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 960,
|
"platformFailureCount": 961,
|
||||||
"successCount": 983,
|
"successCount": 983,
|
||||||
"successRate": 0.0551,
|
"successRate": 0.055,
|
||||||
"total": 17853,
|
"total": 17857,
|
||||||
"unresolvedFailureCount": 9589
|
"unresolvedFailureCount": 9589
|
||||||
},
|
},
|
||||||
"warnings": [
|
"warnings": [
|
||||||
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
|
||||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
|
||||||
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
|
||||||
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
|
||||||
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
|
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
|
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
|
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
|
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||||
"组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
"组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||||
"组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
"组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||||
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||||
@@ -59358,6 +59330,6 @@
|
|||||||
]
|
]
|
||||||
},
|
},
|
||||||
"storageMode": "decision_state_only",
|
"storageMode": "decision_state_only",
|
||||||
"summarizedRecords": 18378,
|
"summarizedRecords": 18382,
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
File diff suppressed because it is too large
Load Diff
File diff suppressed because it is too large
Load Diff
@@ -2,24 +2,24 @@
|
|||||||
"agentVersion": "2026.09.04.4",
|
"agentVersion": "2026.09.04.4",
|
||||||
"checksums": {
|
"checksums": {
|
||||||
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
|
||||||
".modelhub_state/architecture_compatibility_blacklist.json": "15df620d51e00406aa92e74ed6ba8321535c34d7f793db63a14f4447b84c8c82",
|
".modelhub_state/architecture_compatibility_blacklist.json": "6e6b93cdcef07b2b192f9d01ea8bc9f1f5e88ce2200fd0483ba064c4c33ade17",
|
||||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||||
".modelhub_state/market_intelligence.json": "731f776689f05bba8c5dd0f46746923b19bb84a8e24c2af1b1ded627104c5dfa",
|
".modelhub_state/market_intelligence.json": "c2425759d1b74409386ad39858ec02432cb09be307b8ba28dc5019a0d001f7cd",
|
||||||
".modelhub_state/official_capabilities.json": "f96f79c95c22c6dcffdd5a75b3366fe62058549f496cbd9906240f1b2a6cb217",
|
".modelhub_state/official_capabilities.json": "36bfe7e1fad7df5681a316bd3d7ac64d3dd86dfd10afb6d2b574b301e991eee2",
|
||||||
".modelhub_state/outcome_checkpoint.json": "1eb98d127eca02b41be09323863d8d5c0102cb4926b3f3e7cd1da06f2a79fcca",
|
".modelhub_state/outcome_checkpoint.json": "2fe8772a55fb9358eb817a6136e02bf22a77b55c29f9edafe6a45254051f30e5",
|
||||||
".modelhub_state/queue_cleanup_latest.json": "bc7e56c9d1a333f4bf796226c2496765a92f9d4ceb25f0ccd845d6f32075d0de",
|
".modelhub_state/queue_cleanup_latest.json": "bc7e56c9d1a333f4bf796226c2496765a92f9d4ceb25f0ccd845d6f32075d0de",
|
||||||
".modelhub_state/recent_outcomes.jsonl": "d5f3321c7c835be11fc790c6b04936eee563f577da3818cfa5dc8aa7c8332239",
|
".modelhub_state/recent_outcomes.jsonl": "d5f3321c7c835be11fc790c6b04936eee563f577da3818cfa5dc8aa7c8332239",
|
||||||
".modelhub_state/recovery_active_tasks.jsonl": "380879852fff5824ffd7430b4cddc3094276bacc7a6f265409b689c778ed8f8b",
|
".modelhub_state/recovery_active_tasks.jsonl": "4799e3708bfebc863aff9aa9b9a66095b2f6ddf2f33c435d3f06f7ae7ef6397f",
|
||||||
".modelhub_state/recovery_intents.jsonl": "52f28c35f58ab3cfff308697af4e2c21f3f44865aa0562366b5263b44a1d8bd5",
|
".modelhub_state/recovery_intents.jsonl": "8f4d25b7d94e316c965cfabcaae011efd0595afa15645e887c84d15524529acb",
|
||||||
".modelhub_state/routing_intelligence.json": "870e0e30334b79e5564b90bdc759e2cd7e5832b6abdf7cb214d01616ddb0cb10",
|
".modelhub_state/routing_intelligence.json": "870e0e30334b79e5564b90bdc759e2cd7e5832b6abdf7cb214d01616ddb0cb10",
|
||||||
".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b",
|
".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b",
|
||||||
".modelhub_state/worker_crashes.jsonl": "a6b56caed5c7afeb803f8701393cf4660f7e9799eb5ff84af826a142e16d9b00",
|
".modelhub_state/worker_crashes.jsonl": "a6b56caed5c7afeb803f8701393cf4660f7e9799eb5ff84af826a142e16d9b00",
|
||||||
"ledger/submissions.jsonl": "933fcf7b7fa8ad4a5fbea3af5f3a4a5976735a0d010863212338e735e8ae9f65",
|
"ledger/submissions.jsonl": "933fcf7b7fa8ad4a5fbea3af5f3a4a5976735a0d010863212338e735e8ae9f65",
|
||||||
"outcomes/submissions.jsonl": "f39c74f0eaaaf13d084d07dbc9ba28e3e8a146c3203f6823243cf87f7a9e6fb0"
|
"outcomes/submissions.jsonl": "abfbd4751d35aca702061894f2b9ad177c5f021cddbe7882061ebe8c4abb9a0f"
|
||||||
},
|
},
|
||||||
"generation": 24269,
|
"generation": 24270,
|
||||||
"phase": "cycle",
|
"phase": "cycle",
|
||||||
"schemaVersion": 1,
|
"schemaVersion": 1,
|
||||||
"updatedAt": "2026-10-13T11:05:52.368187+00:00",
|
"updatedAt": "2026-10-13T11:11:28.102939+00:00",
|
||||||
"writerId": "0b4d13138a434e929040a457f5ff8e93"
|
"writerId": "0b4d13138a434e929040a457f5ff8e93"
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -8,7 +8,6 @@
|
|||||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T21:42:08.215400+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "49c09622b187326c7d52c77c501ea1ed17ae85611b418c974c6d1dd95d2ec84c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "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": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:40:05.806797+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4649761", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T21:42:08.215400+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "49c09622b187326c7d52c77c501ea1ed17ae85611b418c974c6d1dd95d2ec84c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "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": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:40:05.806797+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4649761", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T22:35:47.104165+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "99fcfb5673a881c74d82451063f2e7a90a328c33bce1e63a9d0bf3ccffd99170", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "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": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:30:50.543106+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650543", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T22:35:47.104165+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "99fcfb5673a881c74d82451063f2e7a90a328c33bce1e63a9d0bf3ccffd99170", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "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": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:30:50.543106+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650543", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T22:44:15.950234+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "05c5a771e8ede0f61c61c1696314e8cb295d87d07704eedc68e43f7483931e45", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "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": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:39:36.525018+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4650654", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T22:44:15.950234+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "05c5a771e8ede0f61c61c1696314e8cb295d87d07704eedc68e43f7483931e45", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "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": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:39:36.525018+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4650654", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T10:30:17.601408+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703969742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703969742}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T02:23:39.690219+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659268", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613082+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679222028, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679222028}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T13:58:59.194804+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667926", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613082+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679222028, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679222028}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T13:58:59.194804+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667926", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613054+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72656575880, "estimatedRequiredGiB": 81.21, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72665883326, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72665883326}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T13:58:59.550329+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667927", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613054+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72656575880, "estimatedRequiredGiB": 81.21, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72665883326, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72665883326}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T13:58:59.550329+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667927", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:43:37.806846+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679220993, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679220993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:33:50.986624+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668642", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:43:37.806846+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679220993, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679220993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:33:50.986624+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668642", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -44,7 +43,6 @@
|
|||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499779+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.093470+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725852", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499779+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.093470+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725852", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-09T03:24:59.424997+00:00", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "810417097cbc089138743623f5b2d9e7e0819ca3b5e09a46ae05ee92ae0998ba", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1490357184, "estimatedRequiredGiB": 43.21, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:llama-cpp", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38663413453}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T19:24:44.852247+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4726325", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-09T03:24:59.424997+00:00", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "810417097cbc089138743623f5b2d9e7e0819ca3b5e09a46ae05ee92ae0998ba", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1490357184, "estimatedRequiredGiB": 43.21, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:llama-cpp", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38663413453}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T19:24:44.852247+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4726325", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-09T03:46:44.543748+00:00", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0c20bbf40c5417bddba738862516ad2bc8c9ec5013c0fd3e0fa9220f64035056", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1490357184, "estimatedRequiredGiB": 43.21, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:llama-cpp", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38663413453}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T19:44:39.694828+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4726617", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-09T03:46:44.543748+00:00", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0c20bbf40c5417bddba738862516ad2bc8c9ec5013c0fd3e0fa9220f64035056", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1490357184, "estimatedRequiredGiB": 43.21, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:llama-cpp", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38663413453}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T19:44:39.694828+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4726617", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:43:52.702366+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794148, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "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": 8435794148}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:42:29.518873+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4729173", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504528+00:00", "modelId": "siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "modelProfile": {"architectures": ["HunYuanMoEV1ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1700, "estimatedRequiredGiB": 90.469, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hunyuan", "modelscopeFileSize": 80949912827, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 80393195968, "modelscopeTags": ["license:Apache License 2.0", "model_type:hunyuan", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 80949912827}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.924564+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729534", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504528+00:00", "modelId": "siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "modelProfile": {"architectures": ["HunYuanMoEV1ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1700, "estimatedRequiredGiB": 90.469, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hunyuan", "modelscopeFileSize": 80949912827, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 80393195968, "modelscopeTags": ["license:Apache License 2.0", "model_type:hunyuan", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 80949912827}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.924564+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729534", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504584+00:00", "modelId": "dealignai/MiniMax-M2.7-JANGTQ-CRACK", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60691028969, "estimatedRequiredGiB": 67.863, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60722546540, "modelscopeLicense": null, "modelscopeParams": 15303654400, "modelscopeTags": ["model_type:minimax_m2", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:turboquant", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:apple-silicon", "custom_tag:mlx", "custom_tag:moe", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:crack", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60722546540}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.031559+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729530", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504584+00:00", "modelId": "dealignai/MiniMax-M2.7-JANGTQ-CRACK", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60691028969, "estimatedRequiredGiB": 67.863, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60722546540, "modelscopeLicense": null, "modelscopeParams": 15303654400, "modelscopeTags": ["model_type:minimax_m2", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:turboquant", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:apple-silicon", "custom_tag:mlx", "custom_tag:moe", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:crack", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60722546540}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.031559+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729530", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504536+00:00", "modelId": "mlx-community/Hy3-OptiQ-2bit", "modelProfile": {"architectures": ["HYV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 88126421229, "estimatedRequiredGiB": 98.5, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hy_v3", "modelscopeFileSize": 88136486889, "modelscopeLicense": "apache-2.0", "modelscopeParams": 24386771776, "modelscopeTags": ["license:apache-2.0", "model_type:hy_v3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:2bit", "custom_tag:mixed-precision", "custom_tag:moe", "custom_tag:ssd-streaming", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 88136486889}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.159484+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729532", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504536+00:00", "modelId": "mlx-community/Hy3-OptiQ-2bit", "modelProfile": {"architectures": ["HYV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 88126421229, "estimatedRequiredGiB": 98.5, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hy_v3", "modelscopeFileSize": 88136486889, "modelscopeLicense": "apache-2.0", "modelscopeParams": 24386771776, "modelscopeTags": ["license:apache-2.0", "model_type:hy_v3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:2bit", "custom_tag:mixed-precision", "custom_tag:moe", "custom_tag:ssd-streaming", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 88136486889}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.159484+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729532", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -99,7 +97,6 @@
|
|||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-17T18:16:51.858895+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62431083040, "estimatedRequiredGiB": 69.776, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 62434089468, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 62434089468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T10:12:07.431503+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4913277", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-17T18:16:51.858895+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 62431083040, "estimatedRequiredGiB": 69.776, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 62434089468, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 62434089468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T10:12:07.431503+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4913277", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T18:28:37.152661+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "289bdbc89807736c7fc9eba7819ba7c6f178bbf5fb1f56a5683ad9b7fa830bfd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T10:17:26.606251+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4913350", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T18:28:37.152661+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "289bdbc89807736c7fc9eba7819ba7c6f178bbf5fb1f56a5683ad9b7fa830bfd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T10:17:26.606251+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4913350", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T00:21:25.658461+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T16:18:42.162554+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4918893", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T00:21:25.658461+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T16:18:42.162554+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4918893", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T10:35:01.790461+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13756989526, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T02:29:42.495408+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4926623", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T17:26:39.586895+00:00", "modelId": "rengensheng/Ternary-Bonsai-2-27B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "ae25b7990c7dee096113ec65c0e54ee3ae00205524523882157b7ed10068496b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629246976, "estimatedRequiredGiB": 8.757, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7835440764, "modelscopeLicense": "apache-2.0", "modelscopeParams": 460730096, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7835440764}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T09:17:39.257829+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4932473", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T17:26:39.586895+00:00", "modelId": "rengensheng/Ternary-Bonsai-2-27B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "ae25b7990c7dee096113ec65c0e54ee3ae00205524523882157b7ed10068496b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629246976, "estimatedRequiredGiB": 8.757, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7835440764, "modelscopeLicense": "apache-2.0", "modelscopeParams": 460730096, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7835440764}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T09:17:39.257829+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4932473", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T17:44:35.896312+00:00", "modelId": "rengensheng/Ternary-Bonsai-2-27B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "96fb2eca023ffaf5f3a7f1befecfe8080483f3ff3ed3b3fce6364bcc1f40fd92", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629246976, "estimatedRequiredGiB": 8.757, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7835440764, "modelscopeLicense": "apache-2.0", "modelscopeParams": 460730096, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7835440764}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T09:36:29.093079+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4932714", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T17:44:35.896312+00:00", "modelId": "rengensheng/Ternary-Bonsai-2-27B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "96fb2eca023ffaf5f3a7f1befecfe8080483f3ff3ed3b3fce6364bcc1f40fd92", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629246976, "estimatedRequiredGiB": 8.757, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7835440764, "modelscopeLicense": "apache-2.0", "modelscopeParams": 460730096, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7835440764}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T09:36:29.093079+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4932714", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T18:00:28.788017+00:00", "modelId": "rengensheng/Ternary-Bonsai-2-27B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "23334d2dcbe57c09d582b0146945adcb58473c0d3e0dc0da7ef6d516e24eb645", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629246976, "estimatedRequiredGiB": 8.757, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7835440764, "modelscopeLicense": "apache-2.0", "modelscopeParams": 460730096, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7835440764}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T09:54:06.949570+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4932877", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T18:00:28.788017+00:00", "modelId": "rengensheng/Ternary-Bonsai-2-27B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "23334d2dcbe57c09d582b0146945adcb58473c0d3e0dc0da7ef6d516e24eb645", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629246976, "estimatedRequiredGiB": 8.757, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7835440764, "modelscopeLicense": "apache-2.0", "modelscopeParams": 460730096, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7835440764}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T09:54:06.949570+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4932877", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -133,7 +130,6 @@
|
|||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.191900+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.445927+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981853", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.191900+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.445927+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981853", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192060+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.441456+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981851", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192060+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.441456+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981851", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192031+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16313701503, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.502255+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981861", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T00:08:58.192031+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474987, "estimatedRequiredGiB": 18.232, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16313701503, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16313701503}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.502255+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981861", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191928+00:00", "modelId": "IntervitensInc/kek_mk3", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3289069288, "estimatedRequiredGiB": 3.683, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 3295875324, "modelscopeLicense": null, "modelscopeParams": 1644515328, "modelscopeTags": ["model_type:stablelm", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3295875324}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.465809+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981855", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191915+00:00", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.453969+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981852", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191915+00:00", "modelId": "prithivMLmods/CEERS-2112-14B-Instruct", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29540133904, "estimatedRequiredGiB": 33.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 29547221374, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14770033664, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:Code", "custom_tag:Math", "custom_tag:Reasoning", "custom_tag:text-generation-inference", "custom_tag:Reinforcement-learning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29547221374}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.453969+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981852", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191874+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.636731+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981863", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191874+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.636731+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981863", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191909+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.639728+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981864", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191909+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.639728+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981864", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -947,8 +943,8 @@
|
|||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-13T08:24:01.042745+00:00", "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T00:12:55.758955+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5499072", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-13T08:24:01.042745+00:00", "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T00:12:55.758955+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5499072", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-13T08:24:01.042771+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T00:12:55.762998+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5499071", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-13T08:24:01.042771+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T00:12:55.762998+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5499071", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-13T10:30:23.641569+00:00", "modelId": "h2oai/h2o-lightning-4b-nemotron-nano", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7947142672, "estimatedRequiredGiB": 8.901, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 7964754709, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-making", "custom_tag:calibration", "custom_tag:jevbench", "custom_tag:nemotron"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7964754709}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T02:15:43.660714+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5500779", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-13T10:30:23.641569+00:00", "modelId": "h2oai/h2o-lightning-4b-nemotron-nano", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7947142672, "estimatedRequiredGiB": 8.901, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 7964754709, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-making", "custom_tag:calibration", "custom_tag:jevbench", "custom_tag:nemotron"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7964754709}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T02:15:43.660714+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5500779", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/plamo-2-translate-8bit", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10124903941, "estimatedRequiredGiB": 11.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 10135674640, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10135674640}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T03:04:33.264341+00:00", "targetGpu": "Biren_166m", "taskId": "5501491", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T11:06:54.163786+00:00", "modelId": "mlx-community/plamo-2-translate-8bit", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10124903941, "estimatedRequiredGiB": 11.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 10135674640, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10135674640}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T03:04:33.264341+00:00", "targetGpu": "Biren_166m", "taskId": "5501491", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/plamo-2-translate-bf16", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19056520807, "estimatedRequiredGiB": 21.309, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 19067261675, "modelscopeLicense": "other", "modelscopeParams": 9528235008, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:bf16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19067261675}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T03:04:33.272826+00:00", "targetGpu": "Biren_166m", "taskId": "5501492", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T11:06:54.163756+00:00", "modelId": "mlx-community/plamo-2-translate-bf16", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19056520807, "estimatedRequiredGiB": 21.309, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 19067261675, "modelscopeLicense": "other", "modelscopeParams": 9528235008, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:bf16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19067261675}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T03:04:33.272826+00:00", "targetGpu": "Biren_166m", "taskId": "5501492", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "yiku233/qwen2.5-coder-7b-nl2sql", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15715871392, "estimatedRequiredGiB": 17.582, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 15731820910, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:nl2sql", "custom_tag:text-to-sql", "custom_tag:lora", "custom_tag:distillation", "custom_tag:dpo", "custom_tag:qwen2_5_coder", "custom_tag:mysql", "custom_tag:agent"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15731820910}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T05:25:47.741926+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5503345", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": null, "modelId": "yiku233/qwen2.5-coder-7b-nl2sql", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15715871392, "estimatedRequiredGiB": 17.582, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 15731820910, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:nl2sql", "custom_tag:text-to-sql", "custom_tag:lora", "custom_tag:distillation", "custom_tag:dpo", "custom_tag:qwen2_5_coder", "custom_tag:mysql", "custom_tag:agent"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15731820910}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T05:25:47.741926+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5503345", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/humanizer-12b-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8964644930, "estimatedRequiredGiB": 10.055, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 8997071286, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1009125399, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "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:gemma4", "custom_tag:humanizer", "custom_tag:text-rewriting", "custom_tag:style-transfer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8997071286}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T05:25:48.059228+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5503344", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/humanizer-12b-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8964644930, "estimatedRequiredGiB": 10.055, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 8997071286, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1009125399, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "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:gemma4", "custom_tag:humanizer", "custom_tag:text-rewriting", "custom_tag:style-transfer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8997071286}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T05:25:48.059228+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5503344", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/plamo-2-translate-8bit", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10124903941, "estimatedRequiredGiB": 11.327, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 10135674640, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10135674640}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T06:31:35.967060+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5504126", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlx-community/plamo-2-translate-8bit", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10124903941, "estimatedRequiredGiB": 11.327, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 10135674640, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10135674640}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T06:31:35.967060+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5504126", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
|||||||
Reference in New Issue
Block a user