diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 96f30c02f..3463fe0f0 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -3280,7 +3280,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-09-29T16:01:33.956428+00:00", + "generatedAt": "2026-09-29T16:17:37.824824+00:00", "summary": { "activeBlockCount": 165, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index ce434419a..e3ed0e6db 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -1,8 +1,8 @@ { - "communityAttemptedAt": "2026-09-29T16:06:42.268303+00:00", + "communityAttemptedAt": "2026-09-29T16:23:36.567600+00:00", "communityError": null, "communitySample": {}, - "communityUpdatedAt": "2026-09-29T16:06:42.268303+00:00", + "communityUpdatedAt": "2026-09-29T16:23:36.567600+00:00", "frameworkAttemptedAt": "2026-09-29T14:16:43.687953+00:00", "frameworkError": null, "frameworkStats": { @@ -434,121 +434,121 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-09-29T16:15:34.265250+00:00", + "generatedAt": "2026-09-29T16:23:36.567600+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, - "backlogHours": 1225.5338345864661, + "backlogHours": 1206.9333333333334, "canVerify": true, "error": null, "gpu": "Ascend_910-b3", "healthFactor": 1.0, "maxConcurrentTasks": 8, "qualityFactor": 2.5, - "queueFactor": 0.9544068996724555, - "queueWeight": 0.9544068996724555, - "recentSuccess": 51, - "recentSuccessRate": 0.38345864661654133, - "recentTerminal": 133, - "recentWilsonLowerBound": 0.30519662302307843, - "running": 8, - "selectionWeight": 2.3860172491811387, + "queueFactor": 0.9562180548728757, + "queueWeight": 0.9562180548728757, + "recentSuccess": 52, + "recentSuccessRate": 0.3851851851851852, + "recentTerminal": 135, + "recentWilsonLowerBound": 0.3073522180558335, + "running": 9, + "selectionWeight": 2.390545137182189, "stale": false, "submissionEligible": true, - "throughputPerHour": 22.166666666666668, - "waiting": 27166 + "throughputPerHour": 22.5, + "waiting": 27156 }, "Ascend_910-b4": { "available": true, - "backlogHours": 1180.3265306122448, + "backlogHours": 1188.3287671232877, "canVerify": true, "error": null, "gpu": "Ascend_910-b4", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 1.885895679514935, - "queueFactor": 0.9598028624791848, - "queueWeight": 0.9598028624791848, - "recentSuccess": 50, - "recentSuccessRate": 0.3401360544217687, - "recentTerminal": 147, - "recentWilsonLowerBound": 0.2684931463856841, + "qualityFactor": 1.7908054389706312, + "queueFactor": 0.9584488492044991, + "queueWeight": 0.9584488492044991, + "recentSuccess": 49, + "recentSuccessRate": 0.3356164383561644, + "recentTerminal": 146, + "recentWilsonLowerBound": 0.2641049442736961, "running": 8, - "selectionWeight": 1.810088071535562, + "selectionWeight": 1.7163954121305594, "stale": false, "submissionEligible": true, - "throughputPerHour": 24.5, - "waiting": 28918 + "throughputPerHour": 24.333333333333332, + "waiting": 28916 }, "Biren_166m": { "available": true, - "backlogHours": 129.8153846153846, + "backlogHours": 122.1159420289855, "canVerify": true, "error": null, "gpu": "Biren_166m", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 0.313108927886418, + "qualityFactor": 0.19004102080674282, "queueFactor": 1.3, "queueWeight": 1.3, - "recentSuccess": 32, - "recentSuccessRate": 0.1641025641025641, - "recentTerminal": 195, - "recentWilsonLowerBound": 0.1187048767284684, - "running": 8, - "selectionWeight": 0.40704160625234337, + "recentSuccess": 28, + "recentSuccessRate": 0.13526570048309178, + "recentTerminal": 207, + "recentWilsonLowerBound": 0.09527037451942912, + "running": 9, + "selectionWeight": 0.24705332704876568, "stale": false, "submissionEligible": false, - "throughputPerHour": 32.5, - "waiting": 4219 + "throughputPerHour": 34.5, + "waiting": 4213 }, "Cambricon_mlu-370-x4": { "available": true, - "backlogHours": 1208.181818181818, + "backlogHours": 1240.16, "canVerify": true, "error": null, "gpu": "Cambricon_mlu-370-x4", "healthFactor": 1.0, "maxConcurrentTasks": 7, - "qualityFactor": 0.3964696266538256, - "queueFactor": 0.9564505512604305, - "queueWeight": 0.9564505512604305, + "qualityFactor": 0.4145010201225394, + "queueFactor": 0.952330676234543, + "queueWeight": 0.952330676234543, "recentSuccess": 16, - "recentSuccessRate": 0.2077922077922078, - "recentTerminal": 77, - "recentWilsonLowerBound": 0.13214965937388248, + "recentSuccessRate": 0.21333333333333335, + "recentTerminal": 75, + "recentWilsonLowerBound": 0.13580086342007996, "running": 7, - "selectionWeight": 0.3792035929710686, + "selectionWeight": 0.3947420367932059, "stale": false, "submissionEligible": false, - "throughputPerHour": 12.833333333333334, - "waiting": 15505 + "throughputPerHour": 12.5, + "waiting": 15502 }, "Cambricon_mlu-370-x8": { "available": true, - "backlogHours": 416.5238095238095, + "backlogHours": 455.895652173913, "canVerify": true, "error": null, "gpu": "Cambricon_mlu-370-x8", "healthFactor": 1.0, "maxConcurrentTasks": 7, - "qualityFactor": 0.7095682524962655, - "queueFactor": 1.1221124770027944, - "queueWeight": 1.1221124770027944, - "recentSuccess": 30, - "recentSuccessRate": 0.23809523809523808, - "recentTerminal": 126, - "recentWilsonLowerBound": 0.17217416354451306, - "running": 7, - "selectionWeight": 0.7962153894111288, + "qualityFactor": 0.7165399859899001, + "queueFactor": 1.1065718405145242, + "queueWeight": 1.1065718405145242, + "recentSuccess": 28, + "recentSuccessRate": 0.24347826086956523, + "recentTerminal": 115, + "recentWilsonLowerBound": 0.17416253017380065, + "running": 9, + "selectionWeight": 0.7929029710990951, "stale": false, "submissionEligible": true, - "throughputPerHour": 21.0, - "waiting": 8747 + "throughputPerHour": 19.166666666666668, + "waiting": 8738 }, "Iluvatar_bi-100": { "available": true, - "backlogHours": 24.95684803001876, + "backlogHours": 24.40959409594096, "canVerify": true, "error": null, "gpu": "Iluvatar_bi-100", @@ -557,197 +557,197 @@ "qualityFactor": 0.05, "queueFactor": 1.3, "queueWeight": 1.3, - "recentSuccess": 12, - "recentSuccessRate": 0.0225140712945591, - "recentTerminal": 533, - "recentWilsonLowerBound": 0.012924898637856067, + "recentSuccess": 13, + "recentSuccessRate": 0.023985239852398525, + "recentTerminal": 542, + "recentWilsonLowerBound": 0.01406960528760084, "running": 24, "selectionWeight": 0.065, "stale": false, "submissionEligible": false, - "throughputPerHour": 88.83333333333333, - "waiting": 2217 + "throughputPerHour": 90.33333333333333, + "waiting": 2205 }, "Iluvatar_bi-150": { "available": true, - "backlogHours": 79.8125, + "backlogHours": 79.28682170542636, "canVerify": true, "error": null, "gpu": "Iluvatar_bi-150", "healthFactor": 1.0, "maxConcurrentTasks": 50, - "qualityFactor": 0.13028366910840977, + "qualityFactor": 0.12607693729005737, "queueFactor": 1.3, "queueWeight": 1.3, "recentSuccess": 41, - "recentSuccessRate": 0.10677083333333333, - "recentTerminal": 384, - "recentWilsonLowerBound": 0.07968474107232401, - "running": 5, - "selectionWeight": 0.16936876984093271, + "recentSuccessRate": 0.10594315245478036, + "recentTerminal": 387, + "recentWilsonLowerBound": 0.07905922492581068, + "running": 6, + "selectionWeight": 0.16390001847707458, "stale": false, "submissionEligible": false, - "throughputPerHour": 64.0, - "waiting": 5108 + "throughputPerHour": 64.5, + "waiting": 5114 }, "Iluvatar_mrv-100": { "available": true, - "backlogHours": 2313.285714285714, + "backlogHours": 2369.121951219512, "canVerify": true, "error": null, "gpu": "Iluvatar_mrv-100", "healthFactor": 1.0, "maxConcurrentTasks": 2, - "qualityFactor": 1.0997795640666421, - "queueFactor": 0.8676568000222906, - "queueWeight": 0.8676568000222906, + "qualityFactor": 1.1457926315174614, + "queueFactor": 0.864214043565374, + "queueWeight": 0.864214043565374, "recentSuccess": 14, - "recentSuccessRate": 0.3333333333333333, - "recentTerminal": 42, - "recentWilsonLowerBound": 0.21012280761972318, + "recentSuccessRate": 0.34146341463414637, + "recentTerminal": 41, + "recentWilsonLowerBound": 0.21558617366643462, "running": 2, - "selectionWeight": 0.9542312172879724, + "selectionWeight": 0.9902100831711159, "stale": false, "submissionEligible": true, - "throughputPerHour": 7.0, - "waiting": 16193 + "throughputPerHour": 6.833333333333333, + "waiting": 16189 }, "Kunlunxin_p-800": { "available": true, - "backlogHours": 434.22047244094483, + "backlogHours": 414.406015037594, "canVerify": true, "error": null, "gpu": "Kunlunxin_p-800", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 0.5806127286461175, - "queueFactor": 1.1151308272600424, - "queueWeight": 1.1151308272600424, + "qualityFactor": 0.5148384661419954, + "queueFactor": 1.1225237134505774, + "queueWeight": 1.1225237134505774, "recentSuccess": 28, - "recentSuccessRate": 0.2204724409448819, - "recentTerminal": 127, - "recentWilsonLowerBound": 0.15717143105153952, + "recentSuccessRate": 0.21052631578947367, + "recentTerminal": 133, + "recentWilsonLowerBound": 0.14986350566500917, "running": 8, - "selectionWeight": 0.6474591524128555, + "selectionWeight": 0.577918386840912, "stale": false, - "submissionEligible": true, - "throughputPerHour": 21.166666666666668, - "waiting": 9191 + "submissionEligible": false, + "throughputPerHour": 22.166666666666668, + "waiting": 9186 }, "MetaX_c-500": { "available": true, - "backlogHours": 596.2857142857143, + "backlogHours": 558.8035714285714, "canVerify": true, "error": null, "gpu": "MetaX_c-500", "healthFactor": 1.0, "maxConcurrentTasks": 4, - "qualityFactor": 0.9835410560069334, - "queueFactor": 1.0633205456548116, - "queueWeight": 1.0633205456548116, - "recentSuccess": 29, - "recentSuccessRate": 0.2761904761904762, - "recentTerminal": 105, - "recentWilsonLowerBound": 0.19972009427826307, + "qualityFactor": 0.9140771944397162, + "queueFactor": 1.073298582779873, + "queueWeight": 1.073298582779873, + "recentSuccess": 30, + "recentSuccessRate": 0.26785714285714285, + "recentTerminal": 112, + "recentWilsonLowerBound": 0.19454473061185254, "running": 4, - "selectionWeight": 1.045819412347202, + "selectionWeight": 0.9810777573435497, "stale": false, "submissionEligible": true, - "throughputPerHour": 17.5, - "waiting": 10435 + "throughputPerHour": 18.666666666666668, + "waiting": 10431 }, "Mthreads_s4000": { "available": true, - "backlogHours": 1555.129411764706, + "backlogHours": 1573.5, "canVerify": true, "error": null, "gpu": "Mthreads_s4000", "healthFactor": 1.0, "maxConcurrentTasks": 4, - "qualityFactor": 1.6008042465958259, - "queueFactor": 0.9209104176903701, - "queueWeight": 0.9209104176903701, - "recentSuccess": 29, - "recentSuccessRate": 0.3411764705882353, - "recentTerminal": 85, - "recentWilsonLowerBound": 0.2492177176176207, - "running": 4, - "selectionWeight": 1.47419730737308, + "qualityFactor": 1.4744427212008864, + "queueFactor": 0.9189236306103578, + "queueWeight": 0.9189236306103578, + "recentSuccess": 28, + "recentSuccessRate": 0.3333333333333333, + "recentTerminal": 84, + "recentWilsonLowerBound": 0.24177064973177226, + "running": 5, + "selectionWeight": 1.354900258492934, "stale": false, "submissionEligible": true, - "throughputPerHour": 14.166666666666666, - "waiting": 22031 + "throughputPerHour": 14.0, + "waiting": 22029 }, "Sunrise_pt-200-x1": { "available": true, - "backlogHours": 2679.157894736842, + "backlogHours": 4241.0, "canVerify": true, "error": null, "gpu": "Sunrise_pt-200-x1", "healthFactor": 1.0, "maxConcurrentTasks": 2, - "qualityFactor": 0.3820029087550545, - "queueFactor": 0.8487555356172835, - "queueWeight": 0.8487555356172835, - "recentSuccess": 9, - "recentSuccessRate": 0.23684210526315788, - "recentTerminal": 38, - "recentWilsonLowerBound": 0.12993561496969508, + "qualityFactor": 0.7678051201982105, + "queueFactor": 0.7919343685785637, + "queueWeight": 0.7919343685785637, + "recentSuccess": 8, + "recentSuccessRate": 0.3333333333333333, + "recentTerminal": 24, + "recentWilsonLowerBound": 0.17971978688379645, "running": 2, - "selectionWeight": 0.3242270834277565, + "selectionWeight": 0.608051263055558, "stale": false, - "submissionEligible": false, - "throughputPerHour": 6.333333333333333, - "waiting": 16968 + "submissionEligible": true, + "throughputPerHour": 4.0, + "waiting": 16964 }, "Vastai_va16": { "available": true, - "backlogHours": 793.1009174311926, + "backlogHours": 823.3714285714286, "canVerify": true, "error": null, "gpu": "Vastai_va16", "healthFactor": 1.0, "maxConcurrentTasks": 16, - "qualityFactor": 0.3327642740618171, - "queueFactor": 1.0187863049874348, - "queueWeight": 1.0187863049874348, - "recentSuccess": 20, - "recentSuccessRate": 0.1834862385321101, - "recentTerminal": 109, - "recentWilsonLowerBound": 0.12203581560283454, + "qualityFactor": 0.40713188877259787, + "queueFactor": 1.0126749401338522, + "queueWeight": 1.0126749401338522, + "recentSuccess": 21, + "recentSuccessRate": 0.2, + "recentTerminal": 105, + "recentWilsonLowerBound": 0.13469807905069028, "running": 16, - "selectionWeight": 0.33901568520326475, + "selectionWeight": 0.4122922610893727, "stale": false, "submissionEligible": false, - "throughputPerHour": 18.166666666666668, - "waiting": 14408 + "throughputPerHour": 17.5, + "waiting": 14409 }, "hygon_k100-ai": { "available": true, - "backlogHours": 1002.6486486486486, + "backlogHours": 967.6173913043477, "canVerify": true, "error": null, "gpu": "hygon_k100-ai", "healthFactor": 1.0, "maxConcurrentTasks": 6, - "qualityFactor": 0.9475881788453734, - "queueFactor": 0.983580817559909, - "queueWeight": 0.983580817559909, - "recentSuccess": 30, - "recentSuccessRate": 0.2702702702702703, - "recentTerminal": 111, - "recentWilsonLowerBound": 0.19636788511059944, - "running": 6, - "selectionWeight": 0.9320295556588376, + "qualityFactor": 1.020567415918327, + "queueFactor": 0.9884481252776803, + "queueWeight": 0.9884481252776803, + "recentSuccess": 32, + "recentSuccessRate": 0.2782608695652174, + "recentTerminal": 115, + "recentWilsonLowerBound": 0.20453775426690435, + "running": 7, + "selectionWeight": 1.0087779489839568, "stale": false, "submissionEligible": true, - "throughputPerHour": 18.5, - "waiting": 18549 + "throughputPerHour": 19.166666666666668, + "waiting": 18546 } }, - "queueAttemptedAt": "2026-09-29T16:06:42.268303+00:00", + "queueAttemptedAt": "2026-09-29T16:23:36.567600+00:00", "queueError": null, - "queueUpdatedAt": "2026-09-29T16:06:42.268303+00:00", + "queueUpdatedAt": "2026-09-29T16:23:36.567600+00:00", "supportedGpus": [ "Vastai_va16", "Cambricon_mlu-370-x4", diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 8a3f83490..b744dfa48 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-09-29T16:15:34.265250+00:00", + "catalogUpdatedAt": "2026-09-29T16:23:36.567600+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-09-29T16:15:34.265250+00:00", + "generatedAt": "2026-09-29T16:28:30.891411+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -244,14 +244,6 @@ ], "updatedAt": "2026-09-29T10:49:43.142331+00:00" }, - "https://modelscope.cn/models/AlexWortega/llm-cipher-reasoning-loras|2026-09-03T05:28:45+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:11.268547+00:00" - }, "https://modelscope.cn/models/AlexWortega/llm-cipher-reasoning-loras|2026-09-03T05:28:45+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -548,6 +540,12 @@ ], "updatedAt": "2026-09-29T15:22:52.165162+00:00" }, + "https://modelscope.cn/models/ISTA-DASLab/Qwen3.8-27B-NVFP4-prefiller|2026-09-29T15:02:42+00:00|Sunrise_pt-200-x1": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-29T16:28:07.963767+00:00" + }, "https://modelscope.cn/models/ISTA-DASLab/Qwen3.8-27B-NVFP4-prefiller|2026-09-29T15:02:42+00:00|hygon_k100-ai": { "taskTypes": [ "text-generation", @@ -578,6 +576,12 @@ ], "updatedAt": "2026-09-29T15:22:51.052783+00:00" }, + "https://modelscope.cn/models/ISTA-DASLab/Qwen3.8-27B-disaggregated-NVFP4-prefill|2026-09-29T15:22:19+00:00|Sunrise_pt-200-x1": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-29T16:28:05.160049+00:00" + }, "https://modelscope.cn/models/ISTA-DASLab/Qwen3.8-27B-disaggregated-NVFP4-prefill|2026-09-29T15:22:19+00:00|hygon_k100-ai": { "taskTypes": [ "text-generation", @@ -964,6 +968,12 @@ ], "updatedAt": "2026-09-29T09:24:38.374813+00:00" }, + "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-DFlash2-EXL3-5.0bpw|2026-08-24T18:41:19+00:00|Sunrise_pt-200-x1": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-29T16:28:30.891411+00:00" + }, "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-DFlash2-EXL3-5.0bpw|2026-08-24T18:41:19+00:00|Vastai_va16": { "taskTypes": [ "text-generation" @@ -1042,6 +1052,12 @@ ], "updatedAt": "2026-09-29T15:54:06.348250+00:00" }, + "https://modelscope.cn/models/Mungert/s1-mini-GGUF|2026-09-29T15:53:22+00:00|Sunrise_pt-200-x1": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-29T16:27:58.448234+00:00" + }, "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-DSpark-GGUF|2026-09-09T18:25:18+00:00|Ascend_910-b3": { "taskTypes": [ "text-generation", @@ -1058,14 +1074,6 @@ ], "updatedAt": "2026-09-29T10:46:35.357179+00:00" }, - "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-DSpark-GGUF|2026-09-09T18:25:18+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:10.774998+00:00" - }, "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-DSpark-GGUF|2026-09-09T18:25:18+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -1140,14 +1148,6 @@ ], "updatedAt": "2026-09-29T10:46:35.571762+00:00" }, - "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-DSpark|2026-09-07T18:16:04+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:11.070113+00:00" - }, "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-DSpark|2026-09-07T18:16:04+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -1234,14 +1234,6 @@ ], "updatedAt": "2026-09-29T10:42:23.465217+00:00" }, - "https://modelscope.cn/models/SKYEVAL/Three_Kingdoms_LLM_Arena|2026-09-14T09:18:14+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:10.675933+00:00" - }, "https://modelscope.cn/models/SKYEVAL/Three_Kingdoms_LLM_Arena|2026-09-14T09:18:14+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -1734,14 +1726,6 @@ ], "updatedAt": "2026-09-29T10:56:44.328580+00:00" }, - "https://modelscope.cn/models/agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF|2026-09-03T03:52:57+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:11.383784+00:00" - }, "https://modelscope.cn/models/agentionai/Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF|2026-09-03T03:52:57+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -1816,14 +1800,6 @@ ], "updatedAt": "2026-09-29T10:56:44.456745+00:00" }, - "https://modelscope.cn/models/agentionai/Qwen3.8-Flash-Next-MTP-ROCmFP4-FAST-GGUF|2026-09-03T03:44:11+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:11.384221+00:00" - }, "https://modelscope.cn/models/agentionai/Qwen3.8-Flash-Next-MTP-ROCmFP4-FAST-GGUF|2026-09-03T03:44:11+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -1994,14 +1970,6 @@ ], "updatedAt": "2026-09-29T09:24:35.463121+00:00" }, - "https://modelscope.cn/models/b77968543/Spark-X2.5-4B-Q8_0|2026-09-01T15:35:36+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:11.486179+00:00" - }, "https://modelscope.cn/models/b77968543/Spark-X2.5-4B-Q8_0|2026-09-01T15:35:36+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -2125,6 +2093,12 @@ ], "updatedAt": "2026-09-29T08:41:39.956430+00:00" }, + "https://modelscope.cn/models/chenyumo/moziAI-27B-MTP|2026-09-25T03:59:57+00:00|Sunrise_pt-200-x1": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-29T16:28:24.344422+00:00" + }, "https://modelscope.cn/models/chenyumo/moziAI-27B-MTP|2026-09-25T03:59:57+00:00|Vastai_va16": { "taskTypes": [ "text-generation" @@ -2193,6 +2167,12 @@ ], "updatedAt": "2026-09-29T08:41:39.967759+00:00" }, + "https://modelscope.cn/models/chenyumo/moziAI-35B-A3B-MOE-MTP|2026-09-25T03:56:17+00:00|Sunrise_pt-200-x1": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-29T16:28:24.355165+00:00" + }, "https://modelscope.cn/models/chenyumo/moziAI-35B-A3B-MOE-MTP|2026-09-25T03:56:17+00:00|Vastai_va16": { "taskTypes": [ "text-generation" @@ -2258,14 +2238,6 @@ ], "updatedAt": "2026-09-28T18:53:13.382757+00:00" }, - "https://modelscope.cn/models/dealignai/Bonsai-2-27B-1bit-CRACK-GGUF|2026-09-18T13:05:43+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:10.459033+00:00" - }, "https://modelscope.cn/models/dealignai/Bonsai-2-27B-1bit-CRACK-GGUF|2026-09-18T13:05:43+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -2340,14 +2312,6 @@ ], "updatedAt": "2026-09-28T18:53:13.294291+00:00" }, - "https://modelscope.cn/models/dealignai/Bonsai-2-27B-Ternary-CRACK-GGUF|2026-09-18T14:52:28+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:10.363420+00:00" - }, "https://modelscope.cn/models/dealignai/Bonsai-2-27B-Ternary-CRACK-GGUF|2026-09-18T14:52:28+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -2460,6 +2424,12 @@ ], "updatedAt": "2026-09-29T09:50:50.967429+00:00" }, + "https://modelscope.cn/models/elejoai/offline-voice-model-packs|2026-09-28T09:46:06+00:00|Sunrise_pt-200-x1": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-29T16:28:21.958151+00:00" + }, "https://modelscope.cn/models/elejoai/offline-voice-model-packs|2026-09-28T09:46:06+00:00|Vastai_va16": { "taskTypes": [ "text-generation" @@ -2808,14 +2778,6 @@ ], "updatedAt": "2026-09-29T10:46:35.295468+00:00" }, - "https://modelscope.cn/models/icychick/Qwen3.5-text-0.8B-GGUF|2026-09-14T05:41:13+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:10.676332+00:00" - }, "https://modelscope.cn/models/icychick/Qwen3.5-text-0.8B-GGUF|2026-09-14T05:41:13+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -3433,6 +3395,12 @@ ], "updatedAt": "2026-09-29T10:31:50.355805+00:00" }, + "https://modelscope.cn/models/iyangqing/st-image|2026-09-29T10:26:37+00:00|Sunrise_pt-200-x1": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-29T16:28:20.371943+00:00" + }, "https://modelscope.cn/models/iyangqing/st-image|2026-09-29T10:26:37+00:00|Vastai_va16": { "taskTypes": [ "text-generation" @@ -3758,14 +3726,6 @@ ], "updatedAt": "2026-09-29T10:46:35.448934+00:00" }, - "https://modelscope.cn/models/laion/GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_global-batch-size_32_Qwen3-32B|2026-09-09T17:06:17+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:10.775251+00:00" - }, "https://modelscope.cn/models/laion/GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_global-batch-size_32_Qwen3-32B|2026-09-09T17:06:17+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -4095,14 +4055,6 @@ ], "updatedAt": "2026-09-28T18:49:25.788703+00:00" }, - "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash|2026-09-02T12:12:36+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:11.385828+00:00" - }, "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DFlash|2026-09-02T12:12:36+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -4177,14 +4129,6 @@ ], "updatedAt": "2026-09-28T18:49:25.788460+00:00" }, - "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark|2026-09-02T12:12:40+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:11.385540+00:00" - }, "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4-DSpark|2026-09-02T12:12:40+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -4578,14 +4522,6 @@ ], "updatedAt": "2026-09-28T18:53:13.464251+00:00" }, - "https://modelscope.cn/models/prism-ml/Ternary-Bonsai-2-27B-gguf-dev|2026-09-18T05:30:35+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:10.459202+00:00" - }, "https://modelscope.cn/models/prism-ml/Ternary-Bonsai-2-27B-gguf-dev|2026-09-18T05:30:35+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -4800,6 +4736,12 @@ ], "updatedAt": "2026-09-29T09:44:05.724918+00:00" }, + "https://modelscope.cn/models/prithivMLmods/JSBAI-Coder-4B-GGUF|2026-09-26T14:36:02+00:00|Sunrise_pt-200-x1": { + "taskTypes": [ + "text-generation" + ], + "updatedAt": "2026-09-29T16:28:23.353554+00:00" + }, "https://modelscope.cn/models/prithivMLmods/JSBAI-Coder-4B-GGUF|2026-09-26T14:36:02+00:00|Vastai_va16": { "taskTypes": [ "text-generation" @@ -4982,14 +4924,6 @@ ], "updatedAt": "2026-09-29T10:46:35.772273+00:00" }, - "https://modelscope.cn/models/svvkii/qwen2.5-7b-5persona-lora|2026-09-03T09:05:03+00:00|Cambricon_mlu-370-x4": { - "taskTypes": [ - "text-generation", - "text-to-image-generation", - "visual-multi-modal" - ], - "updatedAt": "2026-09-28T14:56:11.267537+00:00" - }, "https://modelscope.cn/models/svvkii/qwen2.5-7b-5persona-lora|2026-09-03T09:05:03+00:00|Cambricon_mlu-370-x8": { "taskTypes": [ "text-generation", @@ -5048,6 +4982,54 @@ ], "updatedAt": "2026-09-29T09:20:18.082075+00:00" }, + "https://modelscope.cn/models/theGAI/MiniCPM5-1B-FullSFT-swift-mixture|2026-09-29T16:15:17+00:00|Ascend_910-b3": { + "taskTypes": [ + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-09-29T16:27:58.151018+00:00" + }, + "https://modelscope.cn/models/theGAI/MiniCPM5-1B-FullSFT-swift-mixture|2026-09-29T16:15:17+00:00|Ascend_910-b4": { + "taskTypes": [ + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-09-29T16:27:58.259400+00:00" + }, + "https://modelscope.cn/models/theGAI/MiniCPM5-1B-FullSFT-swift-mixture|2026-09-29T16:15:17+00:00|Iluvatar_mrv-100": { + "taskTypes": [ + "asr", + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-09-29T16:28:11.151463+00:00" + }, + "https://modelscope.cn/models/theGAI/MiniCPM5-1B-FullSFT-swift-mixture|2026-09-29T16:15:17+00:00|MetaX_c-500": { + "taskTypes": [ + "feature_emb", + "text-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-09-29T16:28:11.463761+00:00" + }, + "https://modelscope.cn/models/theGAI/MiniCPM5-1B-FullSFT-swift-mixture|2026-09-29T16:15:17+00:00|Mthreads_s4000": { + "taskTypes": [ + "text-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-09-29T16:28:05.173487+00:00" + }, + "https://modelscope.cn/models/theGAI/MiniCPM5-1B-FullSFT-swift-mixture|2026-09-29T16:15:17+00:00|hygon_k100-ai": { + "taskTypes": [ + "text-generation", + "text-to-image-generation", + "visual-multi-modal" + ], + "updatedAt": "2026-09-29T16:28:10.354518+00:00" + }, "https://modelscope.cn/models/ubergarm/Qwen3.8-27B-GGUF|2026-08-23T14:34:35+00:00|Ascend_910-b3": { "taskTypes": [ "text-generation", @@ -6331,6 +6313,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-09-29T16:15:34.265250+00:00", + "taskTreeUpdatedAt": "2026-09-29T16:23:36.567600+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index b39ed53e9..70fcd37f7 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-09-29T15:27:45.827363+00:00", - "lastSyncTime": "2026-09-29T15:27:45.443270+00:00", + "generatedAt": "2026-09-29T16:17:37.730197+00:00", + "lastSyncTime": "2026-09-29T16:17:37.246258+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -3402,29 +3402,29 @@ "unresolvedFailureCount": 1 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation": { - "attributableFailureCount": 33, - "decisionFailureRate": 0.8919, - "decisionSuccessRate": 0.1081, - "decisionTotal": 37, + "attributableFailureCount": 34, + "decisionFailureRate": 0.8947, + "decisionSuccessRate": 0.1053, + "decisionTotal": 38, "failureBreakdown": { - "ambiguous_runtime": 58, - "context_length": 4, + "ambiguous_runtime": 62, + "context_length": 5, "framework_architecture_unsupported": 28, "memory_capacity": 1, "参数/模板问题": 8 }, - "failureCount": 99, - "failureRate": 0.9612, + "failureCount": 104, + "failureRate": 0.963, "framework": "vllm_tokenizer_patch", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 4, - "successRate": 0.0388, + "successRate": 0.037, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 103, - "unresolvedFailureCount": 66 + "total": 108, + "unresolvedFailureCount": 70 }, "Ascend_910-b3|vllm|text-generation": { "attributableFailureCount": 69, @@ -6125,14 +6125,14 @@ "unresolvedFailureCount": 341 }, "vllm_tokenizer_patch": { - "attributableFailureCount": 130, - "decisionFailureRate": 0.9286, - "decisionSuccessRate": 0.0714, - "decisionTotal": 140, + "attributableFailureCount": 131, + "decisionFailureRate": 0.9291, + "decisionSuccessRate": 0.0709, + "decisionTotal": 141, "failureBreakdown": { - "ambiguous_runtime": 170, + "ambiguous_runtime": 174, "backend_operator": 15, - "context_length": 4, + "context_length": 5, "framework_architecture_unsupported": 78, "memory_capacity": 2, "model_load": 23, @@ -6142,27 +6142,27 @@ "tokenizer_compatibility": 2, "参数/模板问题": 29 }, - "failureCount": 331, - "failureRate": 0.9707, + "failureCount": 336, + "failureRate": 0.9711, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 10, - "successRate": 0.0293, - "total": 341, - "unresolvedFailureCount": 199 + "successRate": 0.0289, + "total": 346, + "unresolvedFailureCount": 203 } }, - "generatedAt": "2026-09-29T15:27:45.813485+00:00", + "generatedAt": "2026-09-29T16:17:37.716802+00:00", "gpuSummaries": { "Ascend_910-b3": { - "attributableFailureCount": 103, - "decisionFailureRate": 0.824, - "decisionSuccessRate": 0.176, - "decisionTotal": 125, + "attributableFailureCount": 104, + "decisionFailureRate": 0.8254, + "decisionSuccessRate": 0.1746, + "decisionTotal": 126, "failureBreakdown": { - "ambiguous_runtime": 124, - "context_length": 4, + "ambiguous_runtime": 128, + "context_length": 5, "framework_architecture_unsupported": 93, "memory_capacity": 2, "repository_structure": 1, @@ -6171,15 +6171,15 @@ "日志缺失": 3, "验证失败": 27 }, - "failureCount": 296, - "failureRate": 0.9308, + "failureCount": 301, + "failureRate": 0.9319, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "successCount": 22, - "successRate": 0.0692, - "total": 318, - "unresolvedFailureCount": 193 + "successRate": 0.0681, + "total": 323, + "unresolvedFailureCount": 197 }, "Ascend_910-b4": { "attributableFailureCount": 324, @@ -6845,15 +6845,15 @@ "unresolvedFailureCount": 6 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": { - "attributableFailureCount": 2, + "attributableFailureCount": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 2, + "decisionTotal": 3, "failureBreakdown": { - "ambiguous_runtime": 8, - "context_length": 2 + "ambiguous_runtime": 11, + "context_length": 3 }, - "failureCount": 10, + "failureCount": 14, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "llama", @@ -6865,8 +6865,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 10, - "unresolvedFailureCount": 8 + "total": 14, + "unresolvedFailureCount": 11 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": { "attributableFailureCount": 0, @@ -7471,9 +7471,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 10 + "ambiguous_runtime": 11 }, - "failureCount": 10, + "failureCount": 11, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "modelType": "starcoder2", @@ -7485,8 +7485,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 10, - "unresolvedFailureCount": 10 + "total": 11, + "unresolvedFailureCount": 11 }, "Ascend_910-b3|vllm|text-generation|bailing_hybrid|none": { "attributableFailureCount": 1, @@ -23303,9 +23303,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 1 + "ambiguous_runtime": 2 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, @@ -23317,8 +23317,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 + "total": 2, + "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm|text-generation": { "attributableFailureCount": 2, @@ -24077,9 +24077,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "参数/模板问题": 7 + "参数/模板问题": 6 }, - "failureCount": 7, + "failureCount": 6, "failureRate": 1.0, "framework": "unknown", "lastPlatformFailureAt": null, @@ -24091,8 +24091,8 @@ "successRate": 0.0, "targetGpu": "hygon_k100-ai", "taskType": "text-generation", - "total": 7, - "unresolvedFailureCount": 7 + "total": 6, + "unresolvedFailureCount": 6 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation": { "attributableFailureCount": 5, @@ -24150,6 +24150,31 @@ } }, "recentProfileCombinationStats": { + "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors": { + "attributableFailureCount": 0, + "consecutiveFailures": 0, + "decisionFailureRate": 0.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 0, + "failureBreakdown": { + "ambiguous_runtime": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "lastTerminalAt": "2026-09-29T16:17:37.246200+00:00", + "modelType": "llama", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b3", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 1 + }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -27556,6 +27581,30 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|27": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "context_length": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "loadSizeLog2Bucket": 27, + "modelType": "llama", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b3", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|28": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -27586,10 +27635,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": { - "ambiguous_runtime": 1, + "ambiguous_runtime": 2, "context_length": 1 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 30, @@ -27602,8 +27651,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 1 + "total": 3, + "unresolvedFailureCount": 2 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|32": { "attributableFailureCount": 0, @@ -27635,9 +27684,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 4 + "ambiguous_runtime": 6 }, - "failureCount": 4, + "failureCount": 6, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 33, @@ -27650,8 +27699,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 4, - "unresolvedFailureCount": 4 + "total": 6, + "unresolvedFailureCount": 6 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|35": { "attributableFailureCount": 0, @@ -28522,9 +28571,9 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 3 + "ambiguous_runtime": 4 }, - "failureCount": 3, + "failureCount": 4, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "loadSizeLog2Bucket": 31, @@ -28537,8 +28586,8 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", - "total": 3, - "unresolvedFailureCount": 3 + "total": 4, + "unresolvedFailureCount": 4 }, "Ascend_910-b3|vllm_tokenizer_patch|text-generation|starcoder2|compressed-tensors|32": { "attributableFailureCount": 0, @@ -52773,19 +52822,19 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 17113, - "totalRecords": 17334, + "terminalRecords": 17118, + "totalRecords": 17339, "totals": { - "attributableFailureCount": 6134, - "decisionFailureRate": 0.8633, - "decisionSuccessRate": 0.1367, - "decisionTotal": 7105, + "attributableFailureCount": 6135, + "decisionFailureRate": 0.8634, + "decisionSuccessRate": 0.1366, + "decisionTotal": 7106, "failureBreakdown": { - "ambiguous_runtime": 4443, + "ambiguous_runtime": 4447, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 128, - "context_length": 322, + "context_length": 323, "framework_architecture_unsupported": 2188, "memory_capacity": 1206, "model_load": 550, @@ -52797,15 +52846,15 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 16142, + "failureCount": 16147, "failureRate": 0.9433, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 942, "successCount": 971, "successRate": 0.0567, - "total": 17113, - "unresolvedFailureCount": 9066 + "total": 17118, + "unresolvedFailureCount": 9070 }, "warnings": [ "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", @@ -52834,6 +52883,7 @@ "组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", @@ -52858,11 +52908,10 @@ "组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" + "组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" ] }, "storageMode": "decision_state_only", - "summarizedRecords": 17334, + "summarizedRecords": 17339, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 798593efb..383a2ab30 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -223,6 +223,7 @@ {"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-customized", "lastSyncTime": "2026-09-22T01:37:13.856976+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449433, "modelscopeLicense": "llama2", "modelscopeParams": 3204165888, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3425449433}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:37:00.639410+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4997216", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-23T18:55:34.958625+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998609696, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020499021, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020499021}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:33:50.394331+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4997188", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-09-23T13:59:55.453747+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T08:31:34.413070+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4997093", "taskType": "text-generation", "verifyResult": null} +{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-29T16:17:37.246200+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197700, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093197700}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:29:25.979829+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997053", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-23T18:18:45.361433+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T08:17:20.243727+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4996859", "taskType": "text-generation", "verifyResult": null} {"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-customized", "lastSyncTime": "2026-09-22T08:29:00.965161+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "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": 4465562659, "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": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:11:51.336512+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996820", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-23T15:01:41.955014+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "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": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:09:36.692226+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4996782", "taskType": "text-generation", "verifyResult": -1} @@ -297,4 +298,3 @@ {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446781+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:08+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4795634", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446625+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849006", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446646+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969661", "taskType": "text-generation", "verifyResult": null} -{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T02:55:04.446677+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T02:53:07+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754068", "taskType": "text-generation", "verifyResult": null} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index aa8743dc9..f52bb6870 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -2571,6 +2571,7 @@ {"batchId": "0817f9f08f1d4e50b53dc8287319c01b", "completedAt": "2026-09-29T05:00:42.637974+00:00", "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configSource": "modelhub_live", "createdAt": "2026-09-29T05:00:40.990914+00:00", "framework": "vllm", "intentId": "3149476ff3264cbf9b1a19b62524a352", "lastModified": "2026-09-04T03:50:10+00:00", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-MoVA-36B-A4B-FP8", "reason": null, "reconciledAt": "2026-09-29T16:03:39.502907+00:00", "repoId": "IFM/K2-Horizon-MoVA-36B-A4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5163384", "taskType": "text-generation"} {"batchId": "e74cc5c284244a0e998a8a47519cd390", "completedAt": "2026-09-29T05:17:59.899620+00:00", "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configSource": "modelhub_live", "createdAt": "2026-09-29T05:15:56.837437+00:00", "framework": "vllm_fix_tokenizer", "intentId": "74260f63702140d8afe997c5d4a67641", "lastModified": "2026-09-03T05:57:31+00:00", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-4.2-3b", "reason": null, "reconciledAt": "2026-09-29T16:03:39.501964+00:00", "repoId": "ibm-granite/granite-4.2-3b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Vastai_va16", "taskId": "5163600", "taskType": "text-generation"} {"batchId": "af702292a17240468562311292c55106", "completedAt": "2026-09-29T11:50:56.209394+00:00", "configFingerprint": "48e1c6e7a33871d6d3101f837eae3cb6ea059723ae10471e3868971f0c6c8603", "configSource": "modelhub_live", "createdAt": "2026-09-29T11:50:53.929786+00:00", "framework": "llamacpp", "intentId": "09c7701eabf64cc18e1fe7816198f274", "lastModified": "2026-09-23T16:46:11+00:00", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-7B-GGUF", "reason": null, "reconciledAt": "2026-09-29T16:03:39.502904+00:00", "repoId": "IFM/K2-Horizon-7B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5169654", "taskType": "text-generation"} +{"batchId": "5ef0981b27f74ac98a6e9fc9a1d8398e", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T16:28:31.080712+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6fa89facec014ad58e9af265c5a36f7d", "lastModified": "2026-09-29T16:15:17+00:00", "modelAddress": "https://modelscope.cn/models/theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "repoId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"} {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925444+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683768+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ba30792e89b44ef5804d5f3613d7df71", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} {"batchId": "6ad67bedd5104b958247ed686fa4a8d7", "completedAt": "2026-09-29T14:16:48.925408+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-09-29T14:16:45.683638+00:00", "framework": "vllm_tokenizer_patch", "intentId": "69aec4d25f21464c860135eb90d77735", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"} {"batchId": "af702292a17240468562311292c55106", "completedAt": "2026-09-29T11:50:56.209408+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-29T11:50:53.929909+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c488d875b85a4d699fe135674c2b940b", "repoId": "mlx-community/LFM2.5-1.2B-Instruct-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index 342b761de..211c715d1 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.22.1", "checksums": { ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", - ".modelhub_state/architecture_compatibility_blacklist.json": "52516ccd67edfd712e9a8781c42a823b3a710cb3f5a3a246cbb4f1d4e7d05d6e", + ".modelhub_state/architecture_compatibility_blacklist.json": "18ca4143cc8afcbda788263f00def692bc8ee714c67e0d00e69c6623e0f6388a", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "584875d0ddb0db7798443b8a7f5e00ec8248ab6ac609863eb7f7216a2b717280", - ".modelhub_state/official_capabilities.json": "f18024df9c67f89df3a96fd5186ad98ada1443c14998940fb0f2ce97e078d9e9", - ".modelhub_state/outcome_checkpoint.json": "3dc66ceb8c4d51d2e0e911155258b03f3cadaba9e03e919c14b0898e7cec648e", + ".modelhub_state/market_intelligence.json": "7c48a869d439bae5cd53e29c5eecf53ac7a246496ed06638ee8d91f6611354e3", + ".modelhub_state/official_capabilities.json": "18aa42bb874ab4fa1a2859a097414798117d7c11fdd558e06af4448f18b66e46", + ".modelhub_state/outcome_checkpoint.json": "79562b64d91dee32e315547c61e0a8b0eeb4c4631ec7c698b14368a220949468", ".modelhub_state/queue_cleanup_latest.json": "49a85c11309f7edea696715997c353c42ca533519a99ab3a549526cccde3cad7", - ".modelhub_state/recent_outcomes.jsonl": "a5944382be474d737eca3b659f91780298be27b986e7a366041b6325b6640b52", + ".modelhub_state/recent_outcomes.jsonl": "81e91996ffb3668bc470e02ef1be371acb37d0b6aa5850bd175907421dd7d460", ".modelhub_state/recovery_active_tasks.jsonl": "029d40cf6b27d481c32e3b743556f87502b4e062b5f5b975d6c7b01e35098dce", - ".modelhub_state/recovery_intents.jsonl": "4b870e2dbcd98d084b7966b12c2a5cf010cf452ad5de0b06581d108e1770dbbe", + ".modelhub_state/recovery_intents.jsonl": "e3b905d52cd6dfb3da25168d8ee274da72468e44ad650af24ad2b8b51b04fd1b", ".modelhub_state/routing_intelligence.json": "788ec7b87db35ebf94b17ae57f4be332f6bab83eed177934dcd71767afd83f06", ".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c", ".modelhub_state/worker_crashes.jsonl": "05bcde79076023fd20785b8270312f776430b95a2d4322ee53ef24e354c39f06", "ledger/submissions.jsonl": "a9019a0dce8bb6f90778a79474b11e84741814a33dcc60ac95dd806ecc7fb29e", - "outcomes/submissions.jsonl": "6b53a78fee598cabc14f140d0fbec8255628e2e15fb1186e6d5495864b21475a" + "outcomes/submissions.jsonl": "eb20c6a6d40cf237dd29210db85ea9b361f312915e405acf95b6a610446f4033" }, - "generation": 18448, - "phase": "cycle", + "generation": 18449, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-09-29T16:16:35.080440+00:00", + "updatedAt": "2026-09-29T16:28:31.210613+00:00", "writerId": "9d958b95ce4146c9939da0f14b9201ff" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 3c0bfb82b..6e661774c 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -311,7 +311,6 @@ {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671271+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.554113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671248+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:53:59.224352+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970246", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.670810+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "modelscopeLicense": "other", "modelscopeParams": 329251584, "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": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:53:59.235830+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970247", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670624+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236688, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236688}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:35.535522+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970356", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.671236+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:35.447710+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4970349", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671020+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:58:41.296912+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970360", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:21:49.901858+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T04:10:03.058495+00:00", "targetGpu": "MetaX_c-500", "taskId": "4970512", "taskType": "text-generation", "verifyResult": null} @@ -336,7 +335,6 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:33:34.552425+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293356304, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295851911, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295851911}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T11:19:51.641136+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4977829", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T19:56:29.962409+00:00", "modelId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7686303632, "estimatedRequiredGiB": 8.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 7688299919, "modelscopeLicense": "llama2", "modelscopeParams": 13960238080, "modelscopeTags": ["license:llama2", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7688299919}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T11:52:06.534997+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4978249", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:16:30.961235+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385544296, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407367933, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407367933}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T12:13:32.801809+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4978494", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:31:51.860953+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457676, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "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": 4096457676}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T12:24:13.176382+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4978632", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:49:19.683309+00:00", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7857274344, "estimatedRequiredGiB": 8.785, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7860631926, "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": 7860631926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T12:37:15.056589+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4979021", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T21:06:45.850274+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:01:42.205703+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979280", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754909+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457730, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "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": 4096457730}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:38:07.337494+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4980575", "taskType": "text-generation", "verifyResult": null} @@ -371,10 +369,8 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T01:52:39.246386+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14864536516, "estimatedRequiredGiB": 16.635, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 14884986381, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3818458992, "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": 14884986381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:36:14.789170+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984694", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T01:52:39.246349+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788663591}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:49:20.875289+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4984851", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T02:15:17.867333+00:00", "modelId": "RedHatAI/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658256, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T17:59:59.555224+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985000", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T02:42:24.494006+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2024670536, "estimatedRequiredGiB": 2.273, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033824885, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T16:44:23.353846+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 2033824885}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T18:39:41.567990+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985663", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-21T02:42:24.494032+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T18:39:53.164098+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4985692", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T02:55:04.446573+00:00", "modelId": "neuralmagic/starcoder2-7b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7855165704, "estimatedRequiredGiB": 8.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 7858541078, "modelscopeLicense": "other", "modelscopeParams": 7400416256, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7858541078}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T18:54:50.771337+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985844", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T02:55:04.446688+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-8B-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093203965, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm", "custom_tag:quantized", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T16:44:23.353846+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b3", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9093203965}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T18:54:50.778321+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4985848", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:02:20.757732+00:00", "modelId": "neuralmagic/Qwen2-0.5B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 903168128, "estimatedRequiredGiB": 1.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 914658310, "modelscopeLicense": "apache-2.0", "modelscopeParams": 630167424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 914658310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:17.970020+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985910", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T03:02:20.757780+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:32.459840+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985911", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:45:50.542869+00:00", "modelId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325064, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325064}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:30:14.636274+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986332", "taskType": "text-generation", "verifyResult": null} @@ -408,7 +404,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:21:18.661372+00:00", "modelId": "blue2star/Qwen-Image-2.1-PE-T2I-ComfyUI", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29306922460, "estimatedRequiredGiB": 32.775, "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": 29326950127, "modelscopeLicense": "other", "modelscopeParams": 18821595084, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:prompt-rewriting", "custom_tag:text-to-image"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29326950127}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:17:20.209866+00:00", "targetGpu": "Biren_166m", "taskId": "4996857", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T16:50:30.559284+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-NVFP4", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20886763512, "estimatedRequiredGiB": 23.388, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-21T08:29:25.977872+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997055", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T16:50:30.559229+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:29:25.981023+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997054", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T16:50:30.559112+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197700, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093197700}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:29:25.979829+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997053", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T16:50:30.559160+00:00", "modelId": "RedHatAI/Mistral-Nemo-Instruct-2407-quantized.w8a16", "modelProfile": {"architectures": ["MistralForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13594088584, "estimatedRequiredGiB": 15.203, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mistral", "modelscopeFileSize": 13603621925, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12247782400, "modelscopeTags": ["license:apache-2.0", "model_type:mistral", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 13603621925}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:29:48.235778+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997092", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559176+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:33:57.835795+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4997190", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T16:50:30.559312+00:00", "modelId": "blue2star/Qwen-Image-2.1-PE-I2I-ComfyUI", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29306922460, "estimatedRequiredGiB": 32.775, "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": 29326959151, "modelscopeLicense": "other", "modelscopeParams": 18821595084, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:prompt-rewriting", "custom_tag:image-editing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29326959151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T08:43:01.432709+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4997305", "taskType": "text-generation", "verifyResult": null}