state: generation 11129 (intent)
This commit is contained in:
@@ -427,6 +427,25 @@
|
|||||||
"targetGpu": "Ascend_910-b4",
|
"targetGpu": "Ascend_910-b4",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
},
|
},
|
||||||
|
"ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": {
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectures": [],
|
||||||
|
"evidenceCount": 1,
|
||||||
|
"expiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"latestFailureAt": "2026-09-20T02:52:50.869403+00:00",
|
||||||
|
"latestSuccessfulAt": null,
|
||||||
|
"matchType": "model_type",
|
||||||
|
"modelType": "qwen3_5_moe",
|
||||||
|
"sourceModelIds": [
|
||||||
|
"mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit"
|
||||||
|
],
|
||||||
|
"sourceTaskIds": [
|
||||||
|
"4969009"
|
||||||
|
],
|
||||||
|
"targetGpu": "Ascend_910-b4",
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
"ascend_910-b4|vllm|text-generation|architectures:nanbeigeforcausallm": {
|
"ascend_910-b4|vllm|text-generation|architectures:nanbeigeforcausallm": {
|
||||||
"architectureSignature": "architectures:nanbeigeforcausallm",
|
"architectureSignature": "architectures:nanbeigeforcausallm",
|
||||||
"architectures": [
|
"architectures": [
|
||||||
@@ -2414,14 +2433,14 @@
|
|||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-21T03:05:49.745018+00:00",
|
"generatedAt": "2026-09-21T03:09:25.825930+00:00",
|
||||||
"summary": {
|
"summary": {
|
||||||
"activeBlockCount": 119,
|
"activeBlockCount": 120,
|
||||||
"byGpuFramework": {
|
"byGpuFramework": {
|
||||||
"Ascend_910-b3|vllm": 13,
|
"Ascend_910-b3|vllm": 13,
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch": 5,
|
"Ascend_910-b3|vllm_tokenizer_patch": 5,
|
||||||
"Ascend_910-b4|vllm": 12,
|
"Ascend_910-b4|vllm": 12,
|
||||||
"Ascend_910-b4|vllm_tokenizer_patch": 3,
|
"Ascend_910-b4|vllm_tokenizer_patch": 4,
|
||||||
"Biren_166m|vllm": 3,
|
"Biren_166m|vllm": 3,
|
||||||
"Cambricon_mlu-370-x4|vllm": 1,
|
"Cambricon_mlu-370-x4|vllm": 1,
|
||||||
"Cambricon_mlu-370-x8|vllm": 8,
|
"Cambricon_mlu-370-x8|vllm": 8,
|
||||||
|
|||||||
@@ -425,121 +425,121 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"frameworkUpdatedAt": null,
|
"frameworkUpdatedAt": null,
|
||||||
"generatedAt": "2026-09-21T03:08:16.717397+00:00",
|
"generatedAt": "2026-09-21T03:09:34.706780+00:00",
|
||||||
"gpuStats": {
|
"gpuStats": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 819.4186046511628,
|
"backlogHours": 814.578034682081,
|
||||||
"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": 0.7179320696110454,
|
"qualityFactor": 0.8746743342176841,
|
||||||
"queueFactor": 0.9778693250472548,
|
"queueFactor": 0.9792588936973591,
|
||||||
"queueWeight": 0.9778693250472548,
|
"queueWeight": 0.9792588936973591,
|
||||||
"recentSuccess": 38,
|
"recentSuccess": 42,
|
||||||
"recentSuccessRate": 0.22093023255813954,
|
"recentSuccessRate": 0.24277456647398843,
|
||||||
"recentTerminal": 172,
|
"recentTerminal": 173,
|
||||||
"recentWilsonLowerBound": 0.1654034598109465,
|
"recentWilsonLowerBound": 0.1849214930019377,
|
||||||
"running": 8,
|
"running": 8,
|
||||||
"selectionWeight": 0.7020437483403317,
|
"selectionWeight": 0.8565326208714835,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 28.666666666666668,
|
"throughputPerHour": 28.833333333333332,
|
||||||
"waiting": 23490
|
"waiting": 23487
|
||||||
},
|
},
|
||||||
"Ascend_910-b4": {
|
"Ascend_910-b4": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1148.5945945945946,
|
"backlogHours": 1222.7482014388488,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Ascend_910-b4",
|
"gpu": "Ascend_910-b4",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 8,
|
"maxConcurrentTasks": 8,
|
||||||
"qualityFactor": 2.5,
|
"qualityFactor": 2.5,
|
||||||
"queueFactor": 0.9295691040474398,
|
"queueFactor": 0.9213759540084548,
|
||||||
"queueWeight": 0.9295691040474398,
|
"queueWeight": 0.9213759540084548,
|
||||||
"recentSuccess": 54,
|
"recentSuccess": 52,
|
||||||
"recentSuccessRate": 0.36486486486486486,
|
"recentSuccessRate": 0.37410071942446044,
|
||||||
"recentTerminal": 148,
|
"recentTerminal": 139,
|
||||||
"recentWilsonLowerBound": 0.2916373002819259,
|
"recentWilsonLowerBound": 0.2980592988538872,
|
||||||
"running": 8,
|
"running": 8,
|
||||||
"selectionWeight": 2.323922760118599,
|
"selectionWeight": 2.3034398850211373,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 24.666666666666668,
|
"throughputPerHour": 23.166666666666668,
|
||||||
"waiting": 28332
|
"waiting": 28327
|
||||||
},
|
},
|
||||||
"Biren_166m": {
|
"Biren_166m": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 143.2248803827751,
|
"backlogHours": 141.14150943396226,
|
||||||
"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": 0.6355132349431445,
|
"qualityFactor": 0.5522519196264482,
|
||||||
"queueFactor": 1.270293060812849,
|
"queueFactor": 1.2737647178209728,
|
||||||
"queueWeight": 1.270293060812849,
|
"queueWeight": 1.2737647178209728,
|
||||||
"recentSuccess": 43,
|
"recentSuccess": 42,
|
||||||
"recentSuccessRate": 0.20574162679425836,
|
"recentSuccessRate": 0.19811320754716982,
|
||||||
"recentTerminal": 209,
|
"recentTerminal": 212,
|
||||||
"recentWilsonLowerBound": 0.156484897123764,
|
"recentWilsonLowerBound": 0.1500411918346862,
|
||||||
"running": 8,
|
"running": 8,
|
||||||
"selectionWeight": 0.8072880524030023,
|
"selectionWeight": 0.7034390105690733,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 34.833333333333336,
|
"throughputPerHour": 35.333333333333336,
|
||||||
"waiting": 4989
|
"waiting": 4987
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x4": {
|
"Cambricon_mlu-370-x4": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1328.5588235294117,
|
"backlogHours": 1347.8507462686568,
|
||||||
"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": 0.6890858601676707,
|
"qualityFactor": 0.6795648430115433,
|
||||||
"queueFactor": 0.9094934541994483,
|
"queueFactor": 0.9080111014147382,
|
||||||
"queueWeight": 0.9094934541994483,
|
"queueWeight": 0.9080111014147382,
|
||||||
"recentSuccess": 17,
|
"recentSuccess": 17,
|
||||||
"recentSuccessRate": 0.25,
|
"recentSuccessRate": 0.2537313432835821,
|
||||||
"recentTerminal": 68,
|
"recentTerminal": 67,
|
||||||
"recentWilsonLowerBound": 0.16234881695499528,
|
"recentWilsonLowerBound": 0.1648777957769739,
|
||||||
"running": 7,
|
"running": 7,
|
||||||
"selectionWeight": 0.6267190792038928,
|
"selectionWeight": 0.6170524215856451,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 11.333333333333334,
|
"throughputPerHour": 11.166666666666666,
|
||||||
"waiting": 15057
|
"waiting": 15051
|
||||||
},
|
},
|
||||||
"Cambricon_mlu-370-x8": {
|
"Cambricon_mlu-370-x8": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 415.02985074626866,
|
"backlogHours": 441.04761904761904,
|
||||||
"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": 0.42037223414062097,
|
"qualityFactor": 0.3684276794468997,
|
||||||
"queueFactor": 1.0829160632506116,
|
"queueFactor": 1.0736546428934282,
|
||||||
"queueWeight": 1.0829160632506116,
|
"queueWeight": 1.0736546428934282,
|
||||||
"recentSuccess": 25,
|
"recentSuccess": 23,
|
||||||
"recentSuccessRate": 0.1865671641791045,
|
"recentSuccessRate": 0.18253968253968253,
|
||||||
"recentTerminal": 134,
|
"recentTerminal": 126,
|
||||||
"recentWilsonLowerBound": 0.1296838224720284,
|
"recentWilsonLowerBound": 0.12482691576112777,
|
||||||
"running": 7,
|
"running": 7,
|
||||||
"selectionWeight": 0.4552278448954256,
|
"selectionWeight": 0.3955640886086155,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 22.333333333333332,
|
"throughputPerHour": 21.0,
|
||||||
"waiting": 9269
|
"waiting": 9262
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-100": {
|
"Iluvatar_bi-100": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 47.70873786407767,
|
"backlogHours": 49.033112582781456,
|
||||||
"canVerify": true,
|
"canVerify": true,
|
||||||
"error": null,
|
"error": null,
|
||||||
"gpu": "Iluvatar_bi-100",
|
"gpu": "Iluvatar_bi-100",
|
||||||
@@ -549,124 +549,124 @@
|
|||||||
"queueFactor": 1.3,
|
"queueFactor": 1.3,
|
||||||
"queueWeight": 1.3,
|
"queueWeight": 1.3,
|
||||||
"recentSuccess": 6,
|
"recentSuccess": 6,
|
||||||
"recentSuccessRate": 0.019417475728155338,
|
"recentSuccessRate": 0.019867549668874173,
|
||||||
"recentTerminal": 309,
|
"recentTerminal": 302,
|
||||||
"recentWilsonLowerBound": 0.008928721406924705,
|
"recentWilsonLowerBound": 0.009136386915106036,
|
||||||
"running": 24,
|
"running": 24,
|
||||||
"selectionWeight": 0.065,
|
"selectionWeight": 0.065,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": false,
|
"submissionEligible": false,
|
||||||
"throughputPerHour": 51.5,
|
"throughputPerHour": 50.333333333333336,
|
||||||
"waiting": 2457
|
"waiting": 2468
|
||||||
},
|
},
|
||||||
"Iluvatar_bi-150": {
|
"Iluvatar_bi-150": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 150.243654822335,
|
"backlogHours": 152.15384615384616,
|
||||||
"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": 0.1585346901501332,
|
"qualityFactor": 0.15460840839702145,
|
||||||
"queueFactor": 1.2612096207441725,
|
"queueFactor": 1.2594907681530305,
|
||||||
"queueWeight": 1.2612096207441725,
|
"queueWeight": 1.2594907681530305,
|
||||||
"recentSuccess": 24,
|
"recentSuccess": 24,
|
||||||
"recentSuccessRate": 0.1218274111675127,
|
"recentSuccessRate": 0.12307692307692308,
|
||||||
"recentTerminal": 197,
|
"recentTerminal": 195,
|
||||||
"recentWilsonLowerBound": 0.0832494527329842,
|
"recentWilsonLowerBound": 0.08411829251882981,
|
||||||
"running": 7,
|
"running": 8,
|
||||||
"selectionWeight": 0.1999454764390444,
|
"selectionWeight": 0.194727863054882,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 32.833333333333336,
|
"throughputPerHour": 32.5,
|
||||||
"waiting": 4933
|
"waiting": 4945
|
||||||
},
|
},
|
||||||
"Iluvatar_mrv-100": {
|
"Iluvatar_mrv-100": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 3227.0,
|
"backlogHours": 2933.090909090909,
|
||||||
"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": 0.7298470900129251,
|
"qualityFactor": 1.0109348495576476,
|
||||||
"queueFactor": 0.7961352459138944,
|
"queueFactor": 0.80805068025296,
|
||||||
"queueWeight": 0.7961352459138944,
|
"queueWeight": 0.80805068025296,
|
||||||
"recentSuccess": 9,
|
"recentSuccess": 11,
|
||||||
"recentSuccessRate": 0.3,
|
"recentSuccessRate": 0.3333333333333333,
|
||||||
"recentTerminal": 30,
|
"recentTerminal": 33,
|
||||||
"recentWilsonLowerBound": 0.16664562643958936,
|
"recentWilsonLowerBound": 0.197500294678037,
|
||||||
"running": 2,
|
"running": 2,
|
||||||
"selectionWeight": 0.5810569924869804,
|
"selectionWeight": 0.8168865928764809,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 5.0,
|
"throughputPerHour": 5.5,
|
||||||
"waiting": 16135
|
"waiting": 16132
|
||||||
},
|
},
|
||||||
"Kunlunxin_p-800": {
|
"Kunlunxin_p-800": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 592.2777777777778,
|
"backlogHours": 576.3243243243244,
|
||||||
"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": 0.6857634461365623,
|
"qualityFactor": 0.6820860793425559,
|
||||||
"queueFactor": 1.0266629277988235,
|
"queueFactor": 1.0314243648344539,
|
||||||
"queueWeight": 1.0266629277988235,
|
"queueWeight": 1.0314243648344539,
|
||||||
"recentSuccess": 25,
|
"recentSuccess": 26,
|
||||||
"recentSuccessRate": 0.23148148148148148,
|
"recentSuccessRate": 0.23423423423423423,
|
||||||
"recentTerminal": 108,
|
"recentTerminal": 111,
|
||||||
"recentWilsonLowerBound": 0.1619925471777863,
|
"recentWilsonLowerBound": 0.16515556448978605,
|
||||||
"running": 8,
|
"running": 8,
|
||||||
"selectionWeight": 0.7040479073879738,
|
"selectionWeight": 0.7035202011483187,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 18.0,
|
"throughputPerHour": 18.5,
|
||||||
"waiting": 10661
|
"waiting": 10662
|
||||||
},
|
},
|
||||||
"MetaX_c-500": {
|
"MetaX_c-500": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 576.0521739130435,
|
"backlogHours": 602.1272727272727,
|
||||||
"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": 0.47530730968866597,
|
"qualityFactor": 0.3919819083443804,
|
||||||
"queueFactor": 1.0309495726355582,
|
"queueFactor": 1.0246703840146045,
|
||||||
"queueWeight": 1.0309495726355582,
|
"queueWeight": 1.0246703840146045,
|
||||||
"recentSuccess": 23,
|
"recentSuccess": 21,
|
||||||
"recentSuccessRate": 0.2,
|
"recentSuccessRate": 0.19090909090909092,
|
||||||
"recentTerminal": 115,
|
"recentTerminal": 110,
|
||||||
"recentWilsonLowerBound": 0.1371296827840679,
|
"recentWilsonLowerBound": 0.12839312602494252,
|
||||||
"running": 4,
|
"running": 4,
|
||||||
"selectionWeight": 0.49001786779408707,
|
"selectionWeight": 0.4016522525500138,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 19.166666666666668,
|
"throughputPerHour": 18.333333333333332,
|
||||||
"waiting": 11041
|
"waiting": 11039
|
||||||
},
|
},
|
||||||
"Mthreads_s4000": {
|
"Mthreads_s4000": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1514.3720930232557,
|
"backlogHours": 1447.0666666666666,
|
||||||
"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": 1.2840319040486128,
|
"qualityFactor": 1.219881330871374,
|
||||||
"queueFactor": 0.8918089083739755,
|
"queueFactor": 0.8983884251723906,
|
||||||
"queueWeight": 0.8918089083739755,
|
"queueWeight": 0.8983884251723906,
|
||||||
"recentSuccess": 26,
|
"recentSuccess": 27,
|
||||||
"recentSuccessRate": 0.3023255813953488,
|
"recentSuccessRate": 0.3,
|
||||||
"recentTerminal": 86,
|
"recentTerminal": 90,
|
||||||
"recentWilsonLowerBound": 0.21543382392193752,
|
"recentWilsonLowerBound": 0.21510778051256527,
|
||||||
"running": 4,
|
"running": 4,
|
||||||
"selectionWeight": 1.1451110906669506,
|
"selectionWeight": 1.0959272677387337,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 14.333333333333334,
|
"throughputPerHour": 15.0,
|
||||||
"waiting": 21706
|
"waiting": 21706
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1": {
|
"Sunrise_pt-200-x1": {
|
||||||
@@ -677,15 +677,15 @@
|
|||||||
"gpu": "Sunrise_pt-200-x1",
|
"gpu": "Sunrise_pt-200-x1",
|
||||||
"healthFactor": 1.0,
|
"healthFactor": 1.0,
|
||||||
"maxConcurrentTasks": 2,
|
"maxConcurrentTasks": 2,
|
||||||
"qualityFactor": 0.16650290574589705,
|
"qualityFactor": 0.22500916514189215,
|
||||||
"queueFactor": 0.8604473934701,
|
"queueFactor": 0.8609046551871198,
|
||||||
"queueWeight": 0.8604473934701,
|
"queueWeight": 0.8609046551871198,
|
||||||
"recentSuccess": 8,
|
"recentSuccess": 9,
|
||||||
"recentSuccessRate": 0.16326530612244897,
|
"recentSuccessRate": 0.1836734693877551,
|
||||||
"recentTerminal": 49,
|
"recentTerminal": 49,
|
||||||
"recentWilsonLowerBound": 0.08512596988208977,
|
"recentWilsonLowerBound": 0.09976228838458356,
|
||||||
"running": 2,
|
"running": 2,
|
||||||
"selectionWeight": 0.14326699125425485,
|
"selectionWeight": 0.19371143773042235,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": true,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 8.166666666666666,
|
"throughputPerHour": 8.166666666666666,
|
||||||
@@ -693,52 +693,52 @@
|
|||||||
},
|
},
|
||||||
"Vastai_va16": {
|
"Vastai_va16": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 1220.7042253521126,
|
"backlogHours": 1237.8857142857144,
|
||||||
"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": 0.9211177022285634,
|
"queueFactor": 0.9196770438070431,
|
||||||
"queueWeight": 0.9211177022285634,
|
"queueWeight": 0.9196770438070431,
|
||||||
"recentSuccess": 6,
|
"recentSuccess": 6,
|
||||||
"recentSuccessRate": 0.08450704225352113,
|
"recentSuccessRate": 0.08571428571428572,
|
||||||
"recentTerminal": 71,
|
"recentTerminal": 70,
|
||||||
"recentWilsonLowerBound": 0.039305972354112026,
|
"recentWilsonLowerBound": 0.03987612654032837,
|
||||||
"running": 16,
|
"running": 16,
|
||||||
"selectionWeight": 0.04605588511142817,
|
"selectionWeight": 0.045983852190352156,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": false,
|
"submissionEligible": false,
|
||||||
"throughputPerHour": 11.833333333333334,
|
"throughputPerHour": 11.666666666666666,
|
||||||
"waiting": 14445
|
"waiting": 14442
|
||||||
},
|
},
|
||||||
"hygon_k100-ai": {
|
"hygon_k100-ai": {
|
||||||
"available": true,
|
"available": true,
|
||||||
"backlogHours": 316.6092715231788,
|
"backlogHours": 315.58415841584156,
|
||||||
"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": 0.05,
|
"qualityFactor": 0.05166531592922758,
|
||||||
"queueFactor": 1.1277897720528962,
|
"queueFactor": 1.1289381507458776,
|
||||||
"queueWeight": 1.1277897720528962,
|
"queueWeight": 1.1289381507458776,
|
||||||
"recentSuccess": 22,
|
"recentSuccess": 23,
|
||||||
"recentSuccessRate": 0.0728476821192053,
|
"recentSuccessRate": 0.07590759075907591,
|
||||||
"recentTerminal": 302,
|
"recentTerminal": 303,
|
||||||
"recentWilsonLowerBound": 0.04859629433610135,
|
"recentWilsonLowerBound": 0.05111064345958137,
|
||||||
"running": 6,
|
"running": 6,
|
||||||
"selectionWeight": 0.05638948860264481,
|
"selectionWeight": 0.05832694622284371,
|
||||||
"stale": false,
|
"stale": false,
|
||||||
"submissionEligible": false,
|
"submissionEligible": true,
|
||||||
"throughputPerHour": 50.333333333333336,
|
"throughputPerHour": 50.5,
|
||||||
"waiting": 15936
|
"waiting": 15937
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"queueAttemptedAt": "2026-09-21T02:58:43.321969+00:00",
|
"queueAttemptedAt": "2026-09-21T03:09:34.706780+00:00",
|
||||||
"queueError": null,
|
"queueError": null,
|
||||||
"queueUpdatedAt": "2026-09-21T02:58:43.321969+00:00",
|
"queueUpdatedAt": "2026-09-21T03:09:34.706780+00:00",
|
||||||
"supportedGpus": [
|
"supportedGpus": [
|
||||||
"Vastai_va16",
|
"Vastai_va16",
|
||||||
"Kunlunxin_p-800",
|
"Kunlunxin_p-800",
|
||||||
|
|||||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
|||||||
{
|
{
|
||||||
"generatedAt": "2026-09-21T03:05:49.686745+00:00",
|
"generatedAt": "2026-09-21T03:09:34.638519+00:00",
|
||||||
"lastSyncTime": "2026-09-21T03:05:47.759507+00:00",
|
"lastSyncTime": "2026-09-21T03:09:34.579964+00:00",
|
||||||
"recentLimit": 300,
|
"recentLimit": 300,
|
||||||
"report": {
|
"report": {
|
||||||
"architectureCompatibilityBlocks": {
|
"architectureCompatibilityBlocks": {
|
||||||
@@ -431,6 +431,25 @@
|
|||||||
"targetGpu": "Ascend_910-b4",
|
"targetGpu": "Ascend_910-b4",
|
||||||
"taskType": "text-generation"
|
"taskType": "text-generation"
|
||||||
},
|
},
|
||||||
|
"ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": {
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectures": [],
|
||||||
|
"evidenceCount": 1,
|
||||||
|
"expiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"latestFailureAt": "2026-09-20T02:52:50.869403+00:00",
|
||||||
|
"latestSuccessfulAt": null,
|
||||||
|
"matchType": "model_type",
|
||||||
|
"modelType": "qwen3_5_moe",
|
||||||
|
"sourceModelIds": [
|
||||||
|
"mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit"
|
||||||
|
],
|
||||||
|
"sourceTaskIds": [
|
||||||
|
"4969009"
|
||||||
|
],
|
||||||
|
"targetGpu": "Ascend_910-b4",
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
"ascend_910-b4|vllm|text-generation|architectures:nanbeigeforcausallm": {
|
"ascend_910-b4|vllm|text-generation|architectures:nanbeigeforcausallm": {
|
||||||
"architectureSignature": "architectures:nanbeigeforcausallm",
|
"architectureSignature": "architectures:nanbeigeforcausallm",
|
||||||
"architectures": [
|
"architectures": [
|
||||||
@@ -2419,12 +2438,12 @@
|
|||||||
}
|
}
|
||||||
},
|
},
|
||||||
"architectureCompatibilitySummary": {
|
"architectureCompatibilitySummary": {
|
||||||
"activeBlockCount": 119,
|
"activeBlockCount": 120,
|
||||||
"byGpuFramework": {
|
"byGpuFramework": {
|
||||||
"Ascend_910-b3|vllm": 13,
|
"Ascend_910-b3|vllm": 13,
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch": 5,
|
"Ascend_910-b3|vllm_tokenizer_patch": 5,
|
||||||
"Ascend_910-b4|vllm": 12,
|
"Ascend_910-b4|vllm": 12,
|
||||||
"Ascend_910-b4|vllm_tokenizer_patch": 3,
|
"Ascend_910-b4|vllm_tokenizer_patch": 4,
|
||||||
"Biren_166m|vllm": 3,
|
"Biren_166m|vllm": 3,
|
||||||
"Cambricon_mlu-370-x4|vllm": 1,
|
"Cambricon_mlu-370-x4|vllm": 1,
|
||||||
"Cambricon_mlu-370-x8|vllm": 8,
|
"Cambricon_mlu-370-x8|vllm": 8,
|
||||||
@@ -2717,15 +2736,15 @@
|
|||||||
"unresolvedFailureCount": 17
|
"unresolvedFailureCount": 17
|
||||||
},
|
},
|
||||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
||||||
"attributableFailureCount": 17,
|
"attributableFailureCount": 18,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 17,
|
"decisionTotal": 18,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 26,
|
"ambiguous_runtime": 26,
|
||||||
"framework_architecture_unsupported": 17
|
"framework_architecture_unsupported": 18
|
||||||
},
|
},
|
||||||
"failureCount": 43,
|
"failureCount": 44,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
@@ -2735,7 +2754,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Ascend_910-b4",
|
"targetGpu": "Ascend_910-b4",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 43,
|
"total": 44,
|
||||||
"unresolvedFailureCount": 26
|
"unresolvedFailureCount": 26
|
||||||
},
|
},
|
||||||
"Ascend_910-b4|vllm|text-generation": {
|
"Ascend_910-b4|vllm|text-generation": {
|
||||||
@@ -4454,9 +4473,9 @@
|
|||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|unknown|text-generation": {
|
"Sunrise_pt-200-x1|unknown|text-generation": {
|
||||||
"attributableFailureCount": 13,
|
"attributableFailureCount": 13,
|
||||||
"decisionFailureRate": 0.13,
|
"decisionFailureRate": 0.1287,
|
||||||
"decisionSuccessRate": 0.87,
|
"decisionSuccessRate": 0.8713,
|
||||||
"decisionTotal": 100,
|
"decisionTotal": 101,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 52,
|
"ambiguous_runtime": 52,
|
||||||
"context_length": 5,
|
"context_length": 5,
|
||||||
@@ -4465,16 +4484,16 @@
|
|||||||
"验证失败": 32
|
"验证失败": 32
|
||||||
},
|
},
|
||||||
"failureCount": 309,
|
"failureCount": 309,
|
||||||
"failureRate": 0.7803,
|
"failureRate": 0.7783,
|
||||||
"framework": "unknown",
|
"framework": "unknown",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
"successCount": 87,
|
"successCount": 88,
|
||||||
"successRate": 0.2197,
|
"successRate": 0.2217,
|
||||||
"targetGpu": "Sunrise_pt-200-x1",
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 396,
|
"total": 397,
|
||||||
"unresolvedFailureCount": 296
|
"unresolvedFailureCount": 296
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||||
@@ -4999,9 +5018,9 @@
|
|||||||
},
|
},
|
||||||
"unknown": {
|
"unknown": {
|
||||||
"attributableFailureCount": 1858,
|
"attributableFailureCount": 1858,
|
||||||
"decisionFailureRate": 0.6969,
|
"decisionFailureRate": 0.6967,
|
||||||
"decisionSuccessRate": 0.3031,
|
"decisionSuccessRate": 0.3033,
|
||||||
"decisionTotal": 2666,
|
"decisionTotal": 2667,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 1964,
|
"ambiguous_runtime": 1964,
|
||||||
"architecture_compatibility": 100,
|
"architecture_compatibility": 100,
|
||||||
@@ -5019,13 +5038,13 @@
|
|||||||
"验证失败": 673
|
"验证失败": 673
|
||||||
},
|
},
|
||||||
"failureCount": 8315,
|
"failureCount": 8315,
|
||||||
"failureRate": 0.9114,
|
"failureRate": 0.9113,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 42,
|
"platformFailureCount": 42,
|
||||||
"successCount": 808,
|
"successCount": 809,
|
||||||
"successRate": 0.0886,
|
"successRate": 0.0887,
|
||||||
"total": 9123,
|
"total": 9124,
|
||||||
"unresolvedFailureCount": 6415
|
"unresolvedFailureCount": 6415
|
||||||
},
|
},
|
||||||
"vllm": {
|
"vllm": {
|
||||||
@@ -5171,30 +5190,30 @@
|
|||||||
"unresolvedFailureCount": 141
|
"unresolvedFailureCount": 141
|
||||||
},
|
},
|
||||||
"vllm_tokenizer_patch": {
|
"vllm_tokenizer_patch": {
|
||||||
"attributableFailureCount": 51,
|
"attributableFailureCount": 52,
|
||||||
"decisionFailureRate": 0.9623,
|
"decisionFailureRate": 0.963,
|
||||||
"decisionSuccessRate": 0.0377,
|
"decisionSuccessRate": 0.037,
|
||||||
"decisionTotal": 53,
|
"decisionTotal": 54,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 39,
|
"ambiguous_runtime": 39,
|
||||||
"framework_architecture_unsupported": 48,
|
"framework_architecture_unsupported": 49,
|
||||||
"memory_capacity": 1,
|
"memory_capacity": 1,
|
||||||
"model_load": 1,
|
"model_load": 1,
|
||||||
"tokenizer_compatibility": 1,
|
"tokenizer_compatibility": 1,
|
||||||
"参数/模板问题": 19
|
"参数/模板问题": 19
|
||||||
},
|
},
|
||||||
"failureCount": 109,
|
"failureCount": 110,
|
||||||
"failureRate": 0.982,
|
"failureRate": 0.9821,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
"successCount": 2,
|
"successCount": 2,
|
||||||
"successRate": 0.018,
|
"successRate": 0.0179,
|
||||||
"total": 111,
|
"total": 112,
|
||||||
"unresolvedFailureCount": 58
|
"unresolvedFailureCount": 58
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"generatedAt": "2026-09-21T03:05:49.677394+00:00",
|
"generatedAt": "2026-09-21T03:09:34.628728+00:00",
|
||||||
"gpuSummaries": {
|
"gpuSummaries": {
|
||||||
"Ascend_910-b3": {
|
"Ascend_910-b3": {
|
||||||
"attributableFailureCount": 90,
|
"attributableFailureCount": 90,
|
||||||
@@ -5222,14 +5241,14 @@
|
|||||||
"unresolvedFailureCount": 128
|
"unresolvedFailureCount": 128
|
||||||
},
|
},
|
||||||
"Ascend_910-b4": {
|
"Ascend_910-b4": {
|
||||||
"attributableFailureCount": 310,
|
"attributableFailureCount": 311,
|
||||||
"decisionFailureRate": 0.8333,
|
"decisionFailureRate": 0.8338,
|
||||||
"decisionSuccessRate": 0.1667,
|
"decisionSuccessRate": 0.1662,
|
||||||
"decisionTotal": 372,
|
"decisionTotal": 373,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 158,
|
"ambiguous_runtime": 158,
|
||||||
"context_length": 1,
|
"context_length": 1,
|
||||||
"framework_architecture_unsupported": 170,
|
"framework_architecture_unsupported": 171,
|
||||||
"memory_capacity": 18,
|
"memory_capacity": 18,
|
||||||
"model_load": 85,
|
"model_load": 85,
|
||||||
"platform_infrastructure": 1,
|
"platform_infrastructure": 1,
|
||||||
@@ -5239,14 +5258,14 @@
|
|||||||
"日志缺失": 14,
|
"日志缺失": 14,
|
||||||
"验证失败": 175
|
"验证失败": 175
|
||||||
},
|
},
|
||||||
"failureCount": 912,
|
"failureCount": 913,
|
||||||
"failureRate": 0.9363,
|
"failureRate": 0.9364,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 1,
|
"platformFailureCount": 1,
|
||||||
"successCount": 62,
|
"successCount": 62,
|
||||||
"successRate": 0.0637,
|
"successRate": 0.0636,
|
||||||
"total": 974,
|
"total": 975,
|
||||||
"unresolvedFailureCount": 601
|
"unresolvedFailureCount": 601
|
||||||
},
|
},
|
||||||
"Biren_166m": {
|
"Biren_166m": {
|
||||||
@@ -5520,9 +5539,9 @@
|
|||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1": {
|
"Sunrise_pt-200-x1": {
|
||||||
"attributableFailureCount": 732,
|
"attributableFailureCount": 732,
|
||||||
"decisionFailureRate": 0.8938,
|
"decisionFailureRate": 0.8927,
|
||||||
"decisionSuccessRate": 0.1062,
|
"decisionSuccessRate": 0.1073,
|
||||||
"decisionTotal": 819,
|
"decisionTotal": 820,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 162,
|
"ambiguous_runtime": 162,
|
||||||
"architecture_compatibility": 44,
|
"architecture_compatibility": 44,
|
||||||
@@ -5538,13 +5557,13 @@
|
|||||||
"验证失败": 32
|
"验证失败": 32
|
||||||
},
|
},
|
||||||
"failureCount": 1372,
|
"failureCount": 1372,
|
||||||
"failureRate": 0.9404,
|
"failureRate": 0.9397,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 218,
|
"platformFailureCount": 218,
|
||||||
"successCount": 87,
|
"successCount": 88,
|
||||||
"successRate": 0.0596,
|
"successRate": 0.0603,
|
||||||
"total": 1459,
|
"total": 1460,
|
||||||
"unresolvedFailureCount": 422
|
"unresolvedFailureCount": 422
|
||||||
},
|
},
|
||||||
"Vastai_va16": {
|
"Vastai_va16": {
|
||||||
@@ -5624,7 +5643,7 @@
|
|||||||
"hygon_k100-ai": 64.0
|
"hygon_k100-ai": 64.0
|
||||||
},
|
},
|
||||||
"pendingRecords": 0,
|
"pendingRecords": 0,
|
||||||
"policyCancelledRecords": 167,
|
"policyCancelledRecords": 173,
|
||||||
"profileCombinationStats": {
|
"profileCombinationStats": {
|
||||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|bailing_hybrid|none": {
|
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|bailing_hybrid|none": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 1,
|
||||||
@@ -6544,6 +6563,29 @@
|
|||||||
"total": 3,
|
"total": 3,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
|
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
|
||||||
|
"attributableFailureCount": 1,
|
||||||
|
"decisionFailureRate": 1.0,
|
||||||
|
"decisionSuccessRate": 0.0,
|
||||||
|
"decisionTotal": 1,
|
||||||
|
"failureBreakdown": {
|
||||||
|
"framework_architecture_unsupported": 1
|
||||||
|
},
|
||||||
|
"failureCount": 1,
|
||||||
|
"failureRate": 1.0,
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"modelType": "qwen3_5_moe",
|
||||||
|
"pendingCount": 0,
|
||||||
|
"pendingRate": 0.0,
|
||||||
|
"platformFailureCount": 0,
|
||||||
|
"quantizationMethod": "none",
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"targetGpu": "Ascend_910-b4",
|
||||||
|
"taskType": "text-generation",
|
||||||
|
"total": 1,
|
||||||
|
"unresolvedFailureCount": 0
|
||||||
|
},
|
||||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": {
|
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none": {
|
||||||
"attributableFailureCount": 2,
|
"attributableFailureCount": 2,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
@@ -13734,11 +13776,11 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 7,
|
"decisionTotal": 7,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 6,
|
"ambiguous_runtime": 5,
|
||||||
"framework_architecture_unsupported": 6,
|
"framework_architecture_unsupported": 6,
|
||||||
"tokenizer_compatibility": 1
|
"tokenizer_compatibility": 1
|
||||||
},
|
},
|
||||||
"failureCount": 13,
|
"failureCount": 12,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm",
|
"framework": "vllm",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -13750,21 +13792,21 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Ascend_910-b3",
|
"targetGpu": "Ascend_910-b3",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 13,
|
"total": 12,
|
||||||
"unresolvedFailureCount": 6
|
"unresolvedFailureCount": 5
|
||||||
},
|
},
|
||||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
||||||
"attributableFailureCount": 5,
|
"attributableFailureCount": 6,
|
||||||
"consecutiveFailures": 5,
|
"consecutiveFailures": 6,
|
||||||
"consecutivePlatformFailures": 0,
|
"consecutivePlatformFailures": 0,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 5,
|
"decisionTotal": 6,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 9,
|
"ambiguous_runtime": 9,
|
||||||
"framework_architecture_unsupported": 5
|
"framework_architecture_unsupported": 6
|
||||||
},
|
},
|
||||||
"failureCount": 14,
|
"failureCount": 15,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm_tokenizer_patch",
|
"framework": "vllm_tokenizer_patch",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -13776,7 +13818,7 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Ascend_910-b4",
|
"targetGpu": "Ascend_910-b4",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 14,
|
"total": 15,
|
||||||
"unresolvedFailureCount": 9
|
"unresolvedFailureCount": 9
|
||||||
},
|
},
|
||||||
"Ascend_910-b4|vllm|text-generation": {
|
"Ascend_910-b4|vllm|text-generation": {
|
||||||
@@ -14386,21 +14428,21 @@
|
|||||||
"consecutivePlatformFailures": 0,
|
"consecutivePlatformFailures": 0,
|
||||||
"decisionFailureRate": 0.0,
|
"decisionFailureRate": 0.0,
|
||||||
"decisionSuccessRate": 1.0,
|
"decisionSuccessRate": 1.0,
|
||||||
"decisionTotal": 3,
|
"decisionTotal": 4,
|
||||||
"failureBreakdown": {},
|
"failureBreakdown": {},
|
||||||
"failureCount": 0,
|
"failureCount": 0,
|
||||||
"failureRate": 0.0,
|
"failureRate": 0.0,
|
||||||
"framework": "unknown",
|
"framework": "unknown",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
"lastTerminalAt": "2026-09-21T02:49:19.765032+00:00",
|
"lastTerminalAt": "2026-09-21T03:09:23.977124+00:00",
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 0,
|
"platformFailureCount": 0,
|
||||||
"successCount": 3,
|
"successCount": 4,
|
||||||
"successRate": 1.0,
|
"successRate": 1.0,
|
||||||
"targetGpu": "Sunrise_pt-200-x1",
|
"targetGpu": "Sunrise_pt-200-x1",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 3,
|
"total": 4,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||||
@@ -14482,10 +14524,10 @@
|
|||||||
"decisionSuccessRate": 0.0,
|
"decisionSuccessRate": 0.0,
|
||||||
"decisionTotal": 5,
|
"decisionTotal": 5,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 13,
|
"ambiguous_runtime": 12,
|
||||||
"framework_architecture_unsupported": 5
|
"framework_architecture_unsupported": 5
|
||||||
},
|
},
|
||||||
"failureCount": 18,
|
"failureCount": 17,
|
||||||
"failureRate": 1.0,
|
"failureRate": 1.0,
|
||||||
"framework": "vllm",
|
"framework": "vllm",
|
||||||
"lastPlatformFailureAt": null,
|
"lastPlatformFailureAt": null,
|
||||||
@@ -14497,8 +14539,8 @@
|
|||||||
"successRate": 0.0,
|
"successRate": 0.0,
|
||||||
"targetGpu": "Vastai_va16",
|
"targetGpu": "Vastai_va16",
|
||||||
"taskType": "text-generation",
|
"taskType": "text-generation",
|
||||||
"total": 18,
|
"total": 17,
|
||||||
"unresolvedFailureCount": 13
|
"unresolvedFailureCount": 12
|
||||||
},
|
},
|
||||||
"hygon_k100-ai|llamacpp|text-generation": {
|
"hygon_k100-ai|llamacpp|text-generation": {
|
||||||
"attributableFailureCount": 0,
|
"attributableFailureCount": 0,
|
||||||
@@ -15208,6 +15250,31 @@
|
|||||||
"total": 1,
|
"total": 1,
|
||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
},
|
},
|
||||||
|
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
|
||||||
|
"attributableFailureCount": 1,
|
||||||
|
"consecutiveFailures": 1,
|
||||||
|
"decisionFailureRate": 1.0,
|
||||||
|
"decisionSuccessRate": 0.0,
|
||||||
|
"decisionTotal": 1,
|
||||||
|
"failureBreakdown": {
|
||||||
|
"framework_architecture_unsupported": 1
|
||||||
|
},
|
||||||
|
"failureCount": 1,
|
||||||
|
"failureRate": 1.0,
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"lastTerminalAt": "2026-09-21T03:09:23.977064+00:00",
|
||||||
|
"modelType": "qwen3_5_moe",
|
||||||
|
"pendingCount": 0,
|
||||||
|
"pendingRate": 0.0,
|
||||||
|
"platformFailureCount": 0,
|
||||||
|
"quantizationMethod": "none",
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"targetGpu": "Ascend_910-b4",
|
||||||
|
"taskType": "text-generation",
|
||||||
|
"total": 1,
|
||||||
|
"unresolvedFailureCount": 0
|
||||||
|
},
|
||||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
|
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5|none": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 1,
|
||||||
"consecutiveFailures": 1,
|
"consecutiveFailures": 1,
|
||||||
@@ -19524,6 +19591,30 @@
|
|||||||
"total": 3,
|
"total": 3,
|
||||||
"unresolvedFailureCount": 0
|
"unresolvedFailureCount": 0
|
||||||
},
|
},
|
||||||
|
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none|34": {
|
||||||
|
"attributableFailureCount": 1,
|
||||||
|
"decisionFailureRate": 1.0,
|
||||||
|
"decisionSuccessRate": 0.0,
|
||||||
|
"decisionTotal": 1,
|
||||||
|
"failureBreakdown": {
|
||||||
|
"framework_architecture_unsupported": 1
|
||||||
|
},
|
||||||
|
"failureCount": 1,
|
||||||
|
"failureRate": 1.0,
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"loadSizeLog2Bucket": 34,
|
||||||
|
"modelType": "qwen3_5_moe",
|
||||||
|
"pendingCount": 0,
|
||||||
|
"pendingRate": 0.0,
|
||||||
|
"platformFailureCount": 0,
|
||||||
|
"quantizationMethod": "none",
|
||||||
|
"successCount": 0,
|
||||||
|
"successRate": 0.0,
|
||||||
|
"targetGpu": "Ascend_910-b4",
|
||||||
|
"taskType": "text-generation",
|
||||||
|
"total": 1,
|
||||||
|
"unresolvedFailureCount": 0
|
||||||
|
},
|
||||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|32": {
|
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|qwen3_5_text|none|32": {
|
||||||
"attributableFailureCount": 1,
|
"attributableFailureCount": 1,
|
||||||
"decisionFailureRate": 1.0,
|
"decisionFailureRate": 1.0,
|
||||||
@@ -29955,20 +30046,20 @@
|
|||||||
"unresolvedFailureCount": 1
|
"unresolvedFailureCount": 1
|
||||||
}
|
}
|
||||||
},
|
},
|
||||||
"terminalRecords": 16062,
|
"terminalRecords": 16064,
|
||||||
"totalRecords": 16229,
|
"totalRecords": 16237,
|
||||||
"totals": {
|
"totals": {
|
||||||
"attributableFailureCount": 5832,
|
"attributableFailureCount": 5833,
|
||||||
"decisionFailureRate": 0.8617,
|
"decisionFailureRate": 0.8616,
|
||||||
"decisionSuccessRate": 0.1383,
|
"decisionSuccessRate": 0.1384,
|
||||||
"decisionTotal": 6768,
|
"decisionTotal": 6770,
|
||||||
"failureBreakdown": {
|
"failureBreakdown": {
|
||||||
"ambiguous_runtime": 3839,
|
"ambiguous_runtime": 3839,
|
||||||
"architecture_compatibility": 212,
|
"architecture_compatibility": 212,
|
||||||
"attention_backend": 1,
|
"attention_backend": 1,
|
||||||
"backend_operator": 102,
|
"backend_operator": 102,
|
||||||
"context_length": 318,
|
"context_length": 318,
|
||||||
"framework_architecture_unsupported": 2036,
|
"framework_architecture_unsupported": 2037,
|
||||||
"memory_capacity": 1197,
|
"memory_capacity": 1197,
|
||||||
"model_load": 489,
|
"model_load": 489,
|
||||||
"platform_infrastructure": 922,
|
"platform_infrastructure": 922,
|
||||||
@@ -29979,14 +30070,14 @@
|
|||||||
"日志缺失": 719,
|
"日志缺失": 719,
|
||||||
"验证失败": 673
|
"验证失败": 673
|
||||||
},
|
},
|
||||||
"failureCount": 15126,
|
"failureCount": 15127,
|
||||||
"failureRate": 0.9417,
|
"failureRate": 0.9417,
|
||||||
"pendingCount": 0,
|
"pendingCount": 0,
|
||||||
"pendingRate": 0.0,
|
"pendingRate": 0.0,
|
||||||
"platformFailureCount": 922,
|
"platformFailureCount": 922,
|
||||||
"successCount": 936,
|
"successCount": 937,
|
||||||
"successRate": 0.0583,
|
"successRate": 0.0583,
|
||||||
"total": 16062,
|
"total": 16064,
|
||||||
"unresolvedFailureCount": 8372
|
"unresolvedFailureCount": 8372
|
||||||
},
|
},
|
||||||
"warnings": [
|
"warnings": [
|
||||||
@@ -30040,6 +30131,6 @@
|
|||||||
]
|
]
|
||||||
},
|
},
|
||||||
"storageMode": "decision_state_only",
|
"storageMode": "decision_state_only",
|
||||||
"summarizedRecords": 16229,
|
"summarizedRecords": 16237,
|
||||||
"version": 1
|
"version": 1
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -14,13 +14,13 @@
|
|||||||
100
|
100
|
||||||
],
|
],
|
||||||
"accounts": 12,
|
"accounts": 12,
|
||||||
"activeScanned": 1178,
|
"activeScanned": 1170,
|
||||||
"ageCleanupMode": "admission_only",
|
"ageCleanupMode": "admission_only",
|
||||||
"agePolicySkipped": {
|
"agePolicySkipped": {
|
||||||
"cleanupDisabled": true,
|
"cleanupDisabled": true,
|
||||||
"reason": "admission_only"
|
"reason": "admission_only"
|
||||||
},
|
},
|
||||||
"architectureBlockCount": 119,
|
"architectureBlockCount": 120,
|
||||||
"architectureFrameworkCatalog": {
|
"architectureFrameworkCatalog": {
|
||||||
"ascend_910-b3|text-generation": [
|
"ascend_910-b3|text-generation": [
|
||||||
"llamacpp",
|
"llamacpp",
|
||||||
@@ -37,11 +37,6 @@
|
|||||||
"vllm_fix_tokenizer",
|
"vllm_fix_tokenizer",
|
||||||
"vllm_tokenizer_patch"
|
"vllm_tokenizer_patch"
|
||||||
],
|
],
|
||||||
"cambricon_mlu-370-x4|text-generation": [
|
|
||||||
"vllm",
|
|
||||||
"vllm-customized",
|
|
||||||
"vllm-mlu"
|
|
||||||
],
|
|
||||||
"cambricon_mlu-370-x8|text-generation": [
|
"cambricon_mlu-370-x8|text-generation": [
|
||||||
"vllm",
|
"vllm",
|
||||||
"vllm-customized",
|
"vllm-customized",
|
||||||
@@ -52,12 +47,6 @@
|
|||||||
"vllm",
|
"vllm",
|
||||||
"vllm-patch-tokenizer"
|
"vllm-patch-tokenizer"
|
||||||
],
|
],
|
||||||
"iluvatar_bi-100|text-generation": [
|
|
||||||
"transformers",
|
|
||||||
"vllm",
|
|
||||||
"vllm-patch-tokenizer",
|
|
||||||
"vllm_fix_tokenizer"
|
|
||||||
],
|
|
||||||
"iluvatar_bi-150|text-generation": [
|
"iluvatar_bi-150|text-generation": [
|
||||||
"llamacpp",
|
"llamacpp",
|
||||||
"transformers",
|
"transformers",
|
||||||
@@ -66,19 +55,11 @@
|
|||||||
"vllm_fix_tokenizer",
|
"vllm_fix_tokenizer",
|
||||||
"vllm_tokenizer_patch"
|
"vllm_tokenizer_patch"
|
||||||
],
|
],
|
||||||
"iluvatar_mrv-100|text-generation": [
|
|
||||||
"transformers",
|
|
||||||
"vllm"
|
|
||||||
],
|
|
||||||
"kunlunxin_p-800|text-generation": [
|
"kunlunxin_p-800|text-generation": [
|
||||||
"vllm",
|
"vllm",
|
||||||
"vllm_fix_tokenizer",
|
"vllm_fix_tokenizer",
|
||||||
"vllm_tokenizer_patch"
|
"vllm_tokenizer_patch"
|
||||||
],
|
],
|
||||||
"metax_c-500|text-generation": [
|
|
||||||
"vllm",
|
|
||||||
"vllm_tokenizer_patch"
|
|
||||||
],
|
|
||||||
"mthreads_s4000|text-generation": [
|
"mthreads_s4000|text-generation": [
|
||||||
"llamacpp",
|
"llamacpp",
|
||||||
"vllm",
|
"vllm",
|
||||||
@@ -88,15 +69,138 @@
|
|||||||
"sglang",
|
"sglang",
|
||||||
"vllm",
|
"vllm",
|
||||||
"vllm_fix_tokenizer"
|
"vllm_fix_tokenizer"
|
||||||
],
|
|
||||||
"vastai_va16|text-generation": [
|
|
||||||
"vllm",
|
|
||||||
"vllm_fix_tokenizer"
|
|
||||||
]
|
]
|
||||||
},
|
},
|
||||||
"architectureFrameworkCatalogErrors": {},
|
"architectureFrameworkCatalogErrors": {},
|
||||||
"architectureIncompatibleCount": 0,
|
"architectureIncompatibleCount": 6,
|
||||||
"architectureIncompatibleTasks": [],
|
"architectureIncompatibleTasks": [
|
||||||
|
{
|
||||||
|
"accountIndex": 2,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4938406,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 7,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "Edge0/Edge0-35B-A3B-preview",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4844610,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 8,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4857321,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 8,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4923309,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 9,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4845112,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 9,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4857320,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
}
|
||||||
|
],
|
||||||
"architectureModelConfigErrors": {
|
"architectureModelConfigErrors": {
|
||||||
"GestaltLabs/Ornstein-3.5-9B-V2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/GestaltLabs/Ornstein-3.5-9B-V2-GGUF/resolve/master/config.json (status=404)",
|
"GestaltLabs/Ornstein-3.5-9B-V2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/GestaltLabs/Ornstein-3.5-9B-V2-GGUF/resolve/master/config.json (status=404)",
|
||||||
"LiquidAI/LFM2.5-2.6B-DSpark-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B-DSpark-GGUF/resolve/master/config.json (status=404)",
|
"LiquidAI/LFM2.5-2.6B-DSpark-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B-DSpark-GGUF/resolve/master/config.json (status=404)",
|
||||||
@@ -120,22 +224,167 @@
|
|||||||
"z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
|
"z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
|
||||||
},
|
},
|
||||||
"architectureModelConfigsComplete": 59,
|
"architectureModelConfigsComplete": 59,
|
||||||
"architectureOnly": false,
|
"architectureOnly": true,
|
||||||
"architecturePolicySkipped": {
|
"architecturePolicySkipped": {
|
||||||
"frameworkCatalogUnknown": 0,
|
"frameworkCatalogUnknown": 0,
|
||||||
"frameworkContextUnknown": 70,
|
"frameworkContextUnknown": 70,
|
||||||
"modelArchitectureUnknown": 134,
|
"modelArchitectureUnknown": 134,
|
||||||
"noMatchingBlock": 1021,
|
"noMatchingBlock": 1007,
|
||||||
"partiallyBlockedFrameworkSet": 23,
|
"partiallyBlockedFrameworkSet": 23,
|
||||||
"runningMatchedProtected": 0,
|
"runningMatchedProtected": 0,
|
||||||
"submissionContextMismatch": 0,
|
"submissionContextMismatch": 0,
|
||||||
"submissionContextUnknown": 0
|
"submissionContextUnknown": 0
|
||||||
},
|
},
|
||||||
"cancelledCount": 0,
|
"cancelledCount": 6,
|
||||||
"cancelledTasks": [],
|
"cancelledTasks": [
|
||||||
|
{
|
||||||
|
"accountIndex": 2,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4938406,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 7,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "Edge0/Edge0-35B-A3B-preview",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4844610,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 8,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4857321,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 8,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4923309,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 9,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4845112,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
},
|
||||||
|
{
|
||||||
|
"accountIndex": 9,
|
||||||
|
"architectureBlockEvidenceCount": 1,
|
||||||
|
"architectureBlockExpiresAt": "2026-10-20T02:52:50.869403+00:00",
|
||||||
|
"architectureMatchScope": "exact_framework",
|
||||||
|
"architectureMatchType": "model_type",
|
||||||
|
"architectureSignature": "model_type:qwen3_5_moe",
|
||||||
|
"architectureSignatures": [
|
||||||
|
"model_type:qwen3_5_moe"
|
||||||
|
],
|
||||||
|
"cleanupReasons": [
|
||||||
|
"known_framework_architecture_incompatible"
|
||||||
|
],
|
||||||
|
"evaluatedFrameworks": [
|
||||||
|
"vllm_tokenizer_patch"
|
||||||
|
],
|
||||||
|
"framework": "vllm_tokenizer_patch",
|
||||||
|
"gpuType": "Ascend_910-b4",
|
||||||
|
"modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B",
|
||||||
|
"reason": "known_framework_architecture_incompatible",
|
||||||
|
"status": "waiting",
|
||||||
|
"taskId": 4857320,
|
||||||
|
"taskType": "text-generation"
|
||||||
|
}
|
||||||
|
],
|
||||||
"certainOomCount": 0,
|
"certainOomCount": 0,
|
||||||
"certainOomTasks": [],
|
"certainOomTasks": [],
|
||||||
"cleanupCandidateCount": 0,
|
"cleanupCandidateCount": 6,
|
||||||
"dryRun": false,
|
"dryRun": false,
|
||||||
"listingErrors": {},
|
"listingErrors": {},
|
||||||
"modelAgeErrors": {},
|
"modelAgeErrors": {},
|
||||||
@@ -160,19 +409,17 @@
|
|||||||
],
|
],
|
||||||
"oldOverflowCount": 0,
|
"oldOverflowCount": 0,
|
||||||
"oldOverflowTasks": [],
|
"oldOverflowTasks": [],
|
||||||
"policyCancelledRecorded": 0,
|
"policyCancelledRecorded": 6,
|
||||||
"policyNoLongerAppliesCount": 0,
|
"policyNoLongerAppliesCount": 0,
|
||||||
"policyNoLongerAppliesTasks": [],
|
"policyNoLongerAppliesTasks": [],
|
||||||
"recentModelDays": 7,
|
"recentModelDays": 7,
|
||||||
"recentModelReserveSlots": 5,
|
"recentModelReserveSlots": 5,
|
||||||
"repositorySizeErrors": {
|
"repositorySizeErrors": {},
|
||||||
"empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete"
|
"repositorySizesComplete": 0,
|
||||||
},
|
|
||||||
"repositorySizesComplete": 337,
|
|
||||||
"skipped": {
|
"skipped": {
|
||||||
"fitsKnownCapacity": 1176,
|
"fitsKnownCapacity": 0,
|
||||||
"gpuCapacityUnknown": 0,
|
"gpuCapacityUnknown": 0,
|
||||||
"repositorySizeUnknown": 2
|
"repositorySizeUnknown": 0
|
||||||
},
|
},
|
||||||
"stopErrors": [],
|
"stopErrors": [],
|
||||||
"uniqueModels": 338
|
"uniqueModels": 338
|
||||||
|
|||||||
@@ -1,3 +1,4 @@
|
|||||||
|
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-21T03:09:23.977124+00:00", "modelId": "BAAI/Artificial-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-21T03:07:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457977", "taskType": "text-generation", "verifyResult": 1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T03:05:47.759507+00:00", "modelId": "fla-hub/rwkv7-191M-world", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T03:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079091", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T03:05:47.759507+00:00", "modelId": "fla-hub/rwkv7-191M-world", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T03:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079091", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T02:58:30.354798+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:57:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079148", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T02:58:30.354798+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:57:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079148", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T02:58:30.354826+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:57:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4080024", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T02:58:30.354826+00:00", "modelId": "tencent-community/WeDLM-7B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T02:57:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4080024", "taskType": "text-generation", "verifyResult": -1}
|
||||||
@@ -242,6 +243,7 @@
|
|||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-21T01:35:45.556098+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.136367+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969024", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-mlu", "lastSyncTime": "2026-09-21T01:35:45.556098+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.741, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663396475, "modelscopeLicense": "other", "modelscopeParams": 182975232, "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": 663396475}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:51.136367+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969024", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473054+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v3-9B", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18483466448, "estimatedRequiredGiB": 20.702, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 18523972484, "modelscopeLicense": "gemma", "modelscopeParams": 9241705984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18523972484}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.898445+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969015", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T18:53:01.473054+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v3-9B", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18483466448, "estimatedRequiredGiB": 20.702, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 18523972484, "modelscopeLicense": "gemma", "modelscopeParams": 9241705984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18523972484}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.898445+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969015", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:33:11.158049+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.893989+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969012", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:33:11.158049+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.893989+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969012", "taskType": "text-generation", "verifyResult": -1}
|
||||||
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T03:09:23.977064+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.869403+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969009", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:06:45.850250+00:00", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19935028960, "estimatedRequiredGiB": 22.299, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 19953127685, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19953127685}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.839341+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969006", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:06:45.850250+00:00", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19935028960, "estimatedRequiredGiB": 22.299, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 19953127685, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19953127685}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.839341+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969006", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["gemma4"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T03:02:20.757762+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "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:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.836633+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969008", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["gemma4"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T03:02:20.757762+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "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:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.836633+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969008", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:49:19.683277+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:43.837507+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969003", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:49:19.683277+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:43.837507+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969003", "taskType": "text-generation", "verifyResult": -1}
|
||||||
@@ -296,5 +298,3 @@
|
|||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-17T10:44:59.509445+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:41:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497070", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-17T10:44:59.509445+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:41:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497070", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-17T10:35:53.413598+00:00", "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:29:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610367", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-17T10:35:53.413598+00:00", "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:29:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610367", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-17T10:10:02.608119+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:05:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4490374", "taskType": "text-generation", "verifyResult": -1}
|
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-17T10:10:02.608119+00:00", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T10:05:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4490374", "taskType": "text-generation", "verifyResult": -1}
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-17T04:34:21.545391+00:00", "modelId": "BAAI/Law_Justice-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T04:33:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471925", "taskType": "text-generation", "verifyResult": -1}
|
|
||||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-17T03:40:30.307157+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-17T03:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505133", "taskType": "text-generation", "verifyResult": -1}
|
|
||||||
|
|||||||
@@ -1961,6 +1961,42 @@
|
|||||||
{"batchId": "243f4088a4994c3cbc472ef19e52886e", "completedAt": "2026-09-21T02:21:28.412435+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:21:26.798256+00:00", "framework": "vllm", "intentId": "444f704301f944879fae4a3fce3a65ea", "lastModified": "2026-09-20T14:39:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "reason": null, "reconciledAt": "2026-09-21T03:05:57.242885+00:00", "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4992047", "taskType": "text-generation"}
|
{"batchId": "243f4088a4994c3cbc472ef19e52886e", "completedAt": "2026-09-21T02:21:28.412435+00:00", "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:21:26.798256+00:00", "framework": "vllm", "intentId": "444f704301f944879fae4a3fce3a65ea", "lastModified": "2026-09-20T14:39:27+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "reason": null, "reconciledAt": "2026-09-21T03:05:57.242885+00:00", "repoId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "4992047", "taskType": "text-generation"}
|
||||||
{"batchId": "243f4088a4994c3cbc472ef19e52886e", "completedAt": "2026-09-21T02:21:28.412447+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:21:26.798380+00:00", "framework": "vllm", "intentId": "eea322d8e8624c00812a6ff7ecd1b244", "lastModified": "2026-09-17T13:36:05+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "reason": null, "reconciledAt": "2026-09-21T03:05:57.242585+00:00", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4992046", "taskType": "text-generation"}
|
{"batchId": "243f4088a4994c3cbc472ef19e52886e", "completedAt": "2026-09-21T02:21:28.412447+00:00", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:21:26.798380+00:00", "framework": "vllm", "intentId": "eea322d8e8624c00812a6ff7ecd1b244", "lastModified": "2026-09-17T13:36:05+00:00", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "reason": null, "reconciledAt": "2026-09-21T03:05:57.242585+00:00", "repoId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "4992046", "taskType": "text-generation"}
|
||||||
{"batchId": "4ebeabe10e824f7ab597594406b6205f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:51:56.239072+00:00", "framework": "vllm-customized", "intentId": "67b30ce588ad4c6f9412e291c75fcecc", "lastModified": "2026-09-20T14:50:03+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "reconciledAt": "2026-09-21T03:05:57.245438+00:00", "repoId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4992371", "taskType": "text-generation"}
|
{"batchId": "4ebeabe10e824f7ab597594406b6205f", "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:51:56.239072+00:00", "framework": "vllm-customized", "intentId": "67b30ce588ad4c6f9412e291c75fcecc", "lastModified": "2026-09-20T14:50:03+00:00", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "reconciledAt": "2026-09-21T03:05:57.245438+00:00", "repoId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4992371", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.555968+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b21c2e9db2fc42c3899ad1b494c0bf78", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.556971+00:00", "framework": "vllm_fix_tokenizer", "intentId": "173ec5f2cbbc4148b47133e20aeaa56d", "lastModified": "2026-08-24T19:35:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557035+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8013c9089d2940268c91b114d9e94d80", "lastModified": "2026-08-24T19:10:38+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "repoId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557080+00:00", "framework": "vllm-mlu", "intentId": "cc9dcafb85344e738976036273ab6593", "lastModified": "2026-08-24T19:57:49+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557149+00:00", "framework": "vllm", "intentId": "c2fd8f6e6f8447f08128dc9542eeef2d", "lastModified": "2026-08-24T19:39:27+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "repoId": "neuralmagic/starcoder2-3b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557210+00:00", "framework": "vllm", "intentId": "a9f13fb1dbcd4a5e9a765d11833ae2af", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557269+00:00", "framework": "vllm", "intentId": "b17c22a2aa37424fbe11665cb2950c32", "lastModified": "2026-08-24T19:39:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557328+00:00", "framework": "vllm", "intentId": "8fb2a00847a6422f83ecf92fd67fed9d", "lastModified": "2026-08-24T19:26:17+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557417+00:00", "framework": "vllm", "intentId": "021fa45a85de42d18cfee559fdf547cb", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557482+00:00", "framework": "vllm", "intentId": "b2a167588e084209b02d611dfbeb4c4e", "lastModified": "2026-08-24T19:41:12+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557539+00:00", "framework": "vllm", "intentId": "84f59afdbef04797be7aaea42bb5eb48", "lastModified": "2026-08-24T19:25:45+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-2-7b-chat-quantized.w8a8", "repoId": "RedHatAI/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557596+00:00", "framework": "vllm", "intentId": "cc5c2e2b1a6a4aa49426be59fbb25f9d", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557653+00:00", "framework": "vllm", "intentId": "dedc7edf43ed4165be6036717cf3a883", "lastModified": "2026-08-24T20:08:44+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557729+00:00", "framework": "vllm", "intentId": "69d289f7399046dc9c71586dca9a3643", "lastModified": "2026-08-24T19:39:28+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557787+00:00", "framework": "vllm", "intentId": "505bf5f419ce4d968f7a2345cb17e447", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557844+00:00", "framework": "vllm", "intentId": "0964b2e4a372466394d03d9111957982", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557901+00:00", "framework": "vllm", "intentId": "8bc100ff46b642a6ab8e3bbee5a98d13", "lastModified": "2026-08-24T19:53:24+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.557958+00:00", "framework": "vllm", "intentId": "6938b5953adc4b329152d78feb39399b", "lastModified": "2026-08-24T19:36:07+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "repoId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w4a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558014+00:00", "framework": "vllm", "intentId": "d8bbf02d284041b396c8b89f6cca50de", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558070+00:00", "framework": "vllm", "intentId": "836b19cc3f5042738981ac6f021eaf55", "lastModified": "2026-09-01T03:52:21+00:00", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "repoId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558127+00:00", "framework": "vllm", "intentId": "e6e7a276612c46f1a51d6a703587cb5a", "lastModified": "2026-09-08T13:43:47+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "repoId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558184+00:00", "framework": "vllm", "intentId": "012b33523947498897c6ad2f2ca83a37", "lastModified": "2026-08-26T16:41:36+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "repoId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-8BIT", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558240+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2c109aecbd52404683c3fa072cf95a70", "lastModified": "2026-08-24T19:21:33+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558284+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a471d47e1acb4d368eec329e9f33e966", "lastModified": "2026-08-24T19:34:42+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-FP8", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558327+00:00", "framework": "vllm-patch-tokenizer", "intentId": "61b04169ae9049d8ab5c29366b9516d3", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558369+00:00", "framework": "vllm-patch-tokenizer", "intentId": "46f87227ec65464685bb60bf1f02a2cd", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558412+00:00", "framework": "vllm-patch-tokenizer", "intentId": "6d99d70168954b6098d1fce1805d088c", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558455+00:00", "framework": "vllm-patch-tokenizer", "intentId": "674e8b31d1b141e6a518ad774cb216da", "lastModified": "2026-08-24T19:48:09+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558497+00:00", "framework": "vllm-patch-tokenizer", "intentId": "25997315b2d949189f7b7836f5a6f09c", "lastModified": "2026-08-24T19:42:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "repoId": "neuralmagic/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558538+00:00", "framework": "vllm-patch-tokenizer", "intentId": "ade5f3328390402fa3cb080ed30644f8", "lastModified": "2026-08-24T20:21:52+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558580+00:00", "framework": "vllm-patch-tokenizer", "intentId": "3e96bd2d86b74ea0b8fac8840c68fd6f", "lastModified": "2026-08-24T20:09:49+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Llama-3.2-3B-Instruct-FP8", "repoId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558622+00:00", "framework": "vllm-patch-tokenizer", "intentId": "2e85fb1258b44b858d843e2774a38e23", "lastModified": "2026-08-24T19:20:59+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a8", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558673+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e8208942b81a41c4b1ac543edc23077d", "lastModified": "2026-08-24T20:18:47+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-27b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558719+00:00", "framework": "vllm-patch-tokenizer", "intentId": "621ca79f277541b3947fc7f43c3453f7", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558762+00:00", "framework": "vllm", "intentId": "8cd6962ffe23458d95ed285f9732a1dd", "lastModified": "2026-08-24T19:34:25+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "repoId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
|
||||||
|
{"batchId": "c6d83be00c99470d841857088d66d9b1", "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configSource": "modelhub_live", "createdAt": "2026-09-21T03:11:09.558810+00:00", "framework": "vllm", "intentId": "765e405dd2454d4a8a84eaf0bb67d118", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"}
|
||||||
{"batchId": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388181+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135936+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1948200c63fd4072ac075656ec8053ee", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
{"batchId": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388181+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135936+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1948200c63fd4072ac075656ec8053ee", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
||||||
{"batchId": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388178+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135881+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bf3aed8733f24050b6c911eb5a98d891", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
{"batchId": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388178+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135881+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bf3aed8733f24050b6c911eb5a98d891", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-6bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
||||||
{"batchId": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388175+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135828+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d6d64229eafe4036a52529aaa805b830", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
{"batchId": "c4c47c96388a48c996d907d392c73b35", "completedAt": "2026-09-21T02:14:01.388175+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-21T02:07:21.135828+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d6d64229eafe4036a52529aaa805b830", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
||||||
|
|||||||
@@ -2,24 +2,24 @@
|
|||||||
"agentVersion": "2026.09.20.2",
|
"agentVersion": "2026.09.20.2",
|
||||||
"checksums": {
|
"checksums": {
|
||||||
".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
|
".modelhub_state/account_capacity.json": "68d2a8390ad022f2ddcd30841f3860c4535387fa64cb46dc7507eb16837e798f",
|
||||||
".modelhub_state/architecture_compatibility_blacklist.json": "4288898c4aeca45c1e6292cf8647110f499575cf0017c73a00fd8f9cd8e851f3",
|
".modelhub_state/architecture_compatibility_blacklist.json": "aaf8b4affd3136e261d9501f8e831832e46f50d96cb28a805faa0ab75afb04cf",
|
||||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||||
".modelhub_state/market_intelligence.json": "99c7726704d3002ce35f6f3dbd4dbcb51cecfe9c64ff25a715ddef408e708925",
|
".modelhub_state/market_intelligence.json": "d7190024d8a37d448005f74d4b261347441eb5999f60f428c35b05bf7fc018e6",
|
||||||
".modelhub_state/official_capabilities.json": "766d3698d586260dc727396d2913447f76e0fc6b2db45423a85eac57c26eaa3c",
|
".modelhub_state/official_capabilities.json": "7b60dc6baed57d3c5c0121e9ac52593869b9af31991da2bd99381539b8deacba",
|
||||||
".modelhub_state/outcome_checkpoint.json": "6d2012049c6c4797af85504b3f3bd5f147547d2772099c61fd2568c5c512fe2d",
|
".modelhub_state/outcome_checkpoint.json": "c9e67ce6c8f52b4e4fd797ea09980f8fbe0a7585fc5aefd95a9e120a9557c22d",
|
||||||
".modelhub_state/queue_cleanup_latest.json": "1a5b9063a973b0e097beb9037b6be7976b9f16eaa163e6ccb2c92f67ad7dc65f",
|
".modelhub_state/queue_cleanup_latest.json": "294596e0492bf1839a4c2e817f44101a0d6d6c4779bf685b402ef658b7bffabd",
|
||||||
".modelhub_state/recent_outcomes.jsonl": "ae3e5b9f196d77dd155d4bd615e88ed06ebf41d3e4e254d0b9c951c6558a1541",
|
".modelhub_state/recent_outcomes.jsonl": "254ebb9091d505dfca62fa053b0d43c6b5fe34a92e9c453216b3faaf0a55f63b",
|
||||||
".modelhub_state/recovery_active_tasks.jsonl": "9b6030185dfd7968c28eb4ce8d77f9fa739a58e4f26a32c6aa6d31b632645f98",
|
".modelhub_state/recovery_active_tasks.jsonl": "9b6030185dfd7968c28eb4ce8d77f9fa739a58e4f26a32c6aa6d31b632645f98",
|
||||||
".modelhub_state/recovery_intents.jsonl": "d0112d5614dd8b5e92437b98c205a1b4781028bccc8f4d9c4f176555729f0aae",
|
".modelhub_state/recovery_intents.jsonl": "fd5ce535ad2070500673696526179a249815f9ea6fb9e97651077c25752415b6",
|
||||||
".modelhub_state/routing_intelligence.json": "a27c2ca5d63103031c8ffb9b5d9d41a0d0d174f4c58e138f98c42bdb550def90",
|
".modelhub_state/routing_intelligence.json": "a27c2ca5d63103031c8ffb9b5d9d41a0d0d174f4c58e138f98c42bdb550def90",
|
||||||
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
|
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
|
||||||
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
|
".modelhub_state/worker_crashes.jsonl": "07505b69e0b050da5f90f8b046a3069d3e1ca2574ca39896bc7d8a66293167f7",
|
||||||
"ledger/submissions.jsonl": "ca3fbf25b8f261c314737aa5e015e297bc78155dd2ab15df002d6987510ce2e1",
|
"ledger/submissions.jsonl": "ca3fbf25b8f261c314737aa5e015e297bc78155dd2ab15df002d6987510ce2e1",
|
||||||
"outcomes/submissions.jsonl": "8bd71917cfb5d8be65246c19cc764433f5a005706456b3c9530ecaeff434e6ef"
|
"outcomes/submissions.jsonl": "0db2d2577767bac55989e1bf2dd694de8ee1252de5d5750755162193bfded03f"
|
||||||
},
|
},
|
||||||
"generation": 11128,
|
"generation": 11129,
|
||||||
"phase": "cycle",
|
"phase": "intent",
|
||||||
"schemaVersion": 1,
|
"schemaVersion": 1,
|
||||||
"updatedAt": "2026-09-21T03:08:23.375567+00:00",
|
"updatedAt": "2026-09-21T03:11:09.690147+00:00",
|
||||||
"writerId": "8b35139af6674067a339a670222d4b67"
|
"writerId": "8b35139af6674067a339a670222d4b67"
|
||||||
}
|
}
|
||||||
|
|||||||
@@ -205,10 +205,8 @@
|
|||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T22:28:30.242556+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T14:24:08.911334+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4829350", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T22:28:30.242556+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T14:24:08.911334+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4829350", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-14T03:29:33.013591+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T19:22:45.622511+00:00", "targetGpu": "Biren_166m", "taskId": "4834315", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-14T03:29:33.013591+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T19:22:45.622511+00:00", "targetGpu": "Biren_166m", "taskId": "4834315", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-14T06:17:54.916608+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T22:17:43.666489+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4836986", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-14T06:17:54.916608+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T22:17:43.666489+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4836986", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-14T14:52:54.921127+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T06:48:00.583349+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4844610", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-14T15:01:42.525014+00:00", "modelId": "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "modelProfile": {"architectures": ["Qwen4ExpForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 32000153976, "estimatedRequiredGiB": 96.509, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen4_exp", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 14924740499, "modelscopeTags": ["license:other", "model_type:qwen4_exp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen4_exp", "custom_tag:moe", "custom_tag:sparse-attention", "custom_tag:ngram-embedding", "custom_tag:imatrix"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 86355120331}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T06:58:38.810772+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844797", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-14T15:01:42.525014+00:00", "modelId": "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-3.3bpw", "modelProfile": {"architectures": ["Qwen4ExpForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 32000153976, "estimatedRequiredGiB": 96.509, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen4_exp", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 14924740499, "modelscopeTags": ["license:other", "model_type:qwen4_exp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen4_exp", "custom_tag:moe", "custom_tag:sparse-attention", "custom_tag:ngram-embedding", "custom_tag:imatrix"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 86355120331}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T06:58:38.810772+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844797", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-14T15:01:42.525004+00:00", "modelId": "huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903777808, "estimatedRequiredGiB": 80.381, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71923892164, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:huihui", "custom_tag:offensive-security", "custom_tag:pentesting", "custom_tag:tool-calling", "custom_tag:cyberstrike", "custom_tag:qwen3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 71923892164}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T06:58:38.815931+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844799", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-14T15:01:42.525004+00:00", "modelId": "huihui-ai/Huihui-CyberStrike-OffSec-35B-abliterated", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 71903777808, "estimatedRequiredGiB": 80.381, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 71923892164, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:huihui", "custom_tag:offensive-security", "custom_tag:pentesting", "custom_tag:tool-calling", "custom_tag:cyberstrike", "custom_tag:qwen3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 71923892164}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T06:58:38.815931+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4844799", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-14T15:20:07.717928+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "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": 13269528840}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:16:07.103690+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4845112", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-14T15:20:07.717905+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:16:07.108792+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4845111", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-14T15:20:07.717905+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:16:07.108792+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4845111", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-14T15:57:15.747158+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "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": 13269528840}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:52:17.993254+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4845635", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-14T15:57:15.747158+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269528840, "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": 13269528840}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:52:17.993254+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4845635", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-14T15:57:15.747166+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:54:31.201810+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4845679", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-14T15:57:15.747166+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T07:54:31.201810+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4845679", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -235,8 +233,6 @@
|
|||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T04:29:33.321810+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T20:23:33.974791+00:00", "targetGpu": "MetaX_c-500", "taskId": "4856813", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T04:29:33.321810+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T20:23:33.974791+00:00", "targetGpu": "MetaX_c-500", "taskId": "4856813", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-15T04:46:58.912654+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T20:41:43.211677+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857006", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-15T04:46:58.912654+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T20:41:43.211677+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857006", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-15T05:05:56.013457+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T20:59:57.940217+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857211", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-15T05:05:56.013457+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T20:59:57.940217+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4857211", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-15T05:15:31.609429+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "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": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:09:06.637418+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4857320", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-15T05:15:31.609440+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529266, "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": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:09:06.635873+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4857321", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T05:25:28.408813+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:17:59.038422+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4857428", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-15T05:25:28.408813+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:17:59.038422+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4857428", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-15T05:34:43.803008+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "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": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:27:24.586588+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857632", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-15T05:34:43.803008+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20063537850, "estimatedRequiredGiB": 22.446, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20083973356, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5529413488, "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": 20083974016}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:27:24.586588+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857632", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-15T05:34:43.803064+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529266, "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": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:27:24.589018+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857633", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-15T05:34:43.803064+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529266, "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": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T21:27:24.589018+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4857633", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -338,7 +334,6 @@
|
|||||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-18T01:30:42.351697+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-17T17:21:09.458913+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4920098", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-18T01:30:42.351697+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-17T17:21:09.458913+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4920098", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T01:30:42.351677+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597699026, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597699026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T17:21:09.457458+00:00", "targetGpu": "Biren_166m", "taskId": "4920097", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T01:30:42.351677+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597699026, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597699026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T17:21:09.457458+00:00", "targetGpu": "Biren_166m", "taskId": "4920097", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T01:30:42.351638+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T17:21:09.456098+00:00", "targetGpu": "Biren_166m", "taskId": "4920099", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T01:30:42.351638+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T17:21:09.456098+00:00", "targetGpu": "Biren_166m", "taskId": "4920099", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-18T05:46:07.695608+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 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": "2026-09-17T21:45:54.233698+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4923309", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-18T06:24:52.891825+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 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": "2026-09-17T22:21:10.450004+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4923702", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-18T06:24:52.891825+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 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": "2026-09-17T22:21:10.450004+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4923702", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-18T07:01:53.813894+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-17T22:55:35.549905+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4924043", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-18T07:01:53.813894+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-17T22:55:35.549905+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4924043", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T07:20:15.618254+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-15T22:59:41.110897+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T23:13:41.953804+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4924273", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-18T07:20:15.618254+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13736538977, "estimatedRequiredGiB": 15.375, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 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, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-15T22:59:41.110897+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 13756989526}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T23:13:41.953804+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4924273", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -370,7 +365,6 @@
|
|||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-19T01:53:05.577161+00:00", "modelId": "IFM/K2-Horizon-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.378, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11075960403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11075960403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T17:46:20.716353+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4938092", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-19T01:53:05.577161+00:00", "modelId": "IFM/K2-Horizon-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.378, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11075960403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11075960403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T17:46:20.716353+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4938092", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-19T02:01:59.403449+00:00", "modelId": "prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8595477990, "estimatedRequiredGiB": 9.621, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "prism_hadamard_qwen35", "modelscopeFileSize": 8608734989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2589078768, "modelscopeTags": ["license:apache-2.0", "model_type:prism_hadamard_qwen35", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:mlx", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8608734989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T17:56:47.451096+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4938210", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-19T02:01:59.403449+00:00", "modelId": "prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8595477990, "estimatedRequiredGiB": 9.621, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "prism_hadamard_qwen35", "modelscopeFileSize": 8608734989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2589078768, "modelscopeTags": ["license:apache-2.0", "model_type:prism_hadamard_qwen35", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:mlx", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8608734989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T17:56:47.451096+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4938210", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-19T02:01:59.403510+00:00", "modelId": "IFM/K2-Horizon-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.378, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11075960403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11075960403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T17:56:47.449292+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4938209", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-19T02:01:59.403510+00:00", "modelId": "IFM/K2-Horizon-7B-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11053505536, "estimatedRequiredGiB": 12.378, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11075960403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8999178240, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11075960403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T17:56:47.449292+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4938209", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-19T02:19:07.486735+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:17:22.750439+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4938406", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-19T02:44:40.297028+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:41:55.617980+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4938690", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-19T02:44:40.297028+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:41:55.617980+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4938690", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-19T03:01:51.490259+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:58:28.435554+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4938823", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-19T03:01:51.490259+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T18:58:28.435554+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4938823", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-19T03:45:21.131949+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T19:38:31.546614+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4939248", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-19T03:45:21.131949+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T19:38:31.546614+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4939248", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -410,7 +404,6 @@
|
|||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647569+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:43.745571+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969000", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647569+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:43.745571+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969000", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647473+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T02:52:43.835992+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969002", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647473+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T02:52:43.835992+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969002", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647845+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T02:52:50.837922+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969007", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647845+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T02:52:50.837922+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969007", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647704+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.869403+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969009", "taskType": "text-generation", "verifyResult": null}
|
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647374+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.900575+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969014", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647374+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.900575+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969014", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647433+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.873755+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969010", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647433+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 20926892207, "modelscopeLicense": "gemma", "modelscopeParams": 28842037282, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20926892207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.873755+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969010", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647793+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.895856+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969011", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647793+00:00", "modelId": "mlx-community/Devstral-Small-2-24B-Instruct-2512-OptiQ-4bit", "modelProfile": {"architectures": ["Mistral3ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17367755740, "estimatedRequiredGiB": 19.429, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral3", "modelscopeFileSize": 17385072379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4929899520, "modelscopeTags": ["license:apache-2.0", "model_type:mistral3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:mistral", "custom_tag:mistral3", "custom_tag:devstral"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17385072379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.895856+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969011", "taskType": "text-generation", "verifyResult": null}
|
||||||
@@ -967,7 +960,7 @@
|
|||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:02:20.757732+00:00", "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658310, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:17.970020+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985910", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:02:20.757732+00:00", "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658310, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:17.970020+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985910", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T03:02:20.757780+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:32.459840+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985911", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T03:02:20.757780+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:32.459840+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985911", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-7b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857274344, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860632064, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860632064}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:09:12.237648+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4986045", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-7b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857274344, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860632064, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 7400416256, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7860632064}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:09:12.237648+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4986045", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:09:12.206917+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4986039", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:09:23.977096+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:09:12.206917+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4986039", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:12:09.492560+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4986098", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:12:09.492560+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4986098", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30679155168, "estimatedRequiredGiB": 34.312, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 30702164068, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15180130288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:14b", "custom_tag:deltanet", "custom_tag:linear-attention", "custom_tag:hybrid-attention", "custom_tag:distillation", "custom_tag:pruned", "custom_tag:reasoning", "custom_tag:tool-calling", "custom_tag:agent", "custom_tag:coding", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30702164068}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:23:30.183489+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4986237", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30679155168, "estimatedRequiredGiB": 34.312, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 30702164068, "modelscopeLicense": "apache-2.0", "modelscopeParams": 15180130288, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:14b", "custom_tag:deltanet", "custom_tag:linear-attention", "custom_tag:hybrid-attention", "custom_tag:distillation", "custom_tag:pruned", "custom_tag:reasoning", "custom_tag:tool-calling", "custom_tag:agent", "custom_tag:coding", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30702164068}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:23:30.183489+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4986237", "taskType": "text-generation", "verifyResult": null}
|
||||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:28:11.202603+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4986310", "taskType": "text-generation", "verifyResult": null}
|
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "3b6ff6a21da290a9b1ca3ac432aa93c3d06a816b4b694cc9a45180f81f107aa5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T19:28:11.202603+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4986310", "taskType": "text-generation", "verifyResult": null}
|
||||||
|
|||||||
Reference in New Issue
Block a user