state: generation 10931 (intent)
This commit is contained in:
@@ -324,6 +324,25 @@
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:gemma4_unified": {
|
||||
"architectureSignature": "model_type:gemma4_unified",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-20T02:52:43.767336+00:00",
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"latestFailureAt": "2026-09-20T02:52:43.767336+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "gemma4_unified",
|
||||
"sourceModelIds": [
|
||||
"mlx-community/gemma-4-12B-it-qat-OptiQ-4bit"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4969004"
|
||||
],
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
@@ -2266,14 +2285,14 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T21:33:11.658018+00:00",
|
||||
"generatedAt": "2026-09-20T21:55:29.314192+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 111,
|
||||
"activeBlockCount": 112,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 11,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 4,
|
||||
"Ascend_910-b4|vllm": 12,
|
||||
"Ascend_910-b4|vllm_tokenizer_patch": 2,
|
||||
"Ascend_910-b4|vllm_tokenizer_patch": 3,
|
||||
"Biren_166m|vllm": 3,
|
||||
"Cambricon_mlu-370-x8|vllm": 6,
|
||||
"Cambricon_mlu-370-x8|vllm-mlu": 5,
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-20T21:31:43.948011+00:00",
|
||||
"communityAttemptedAt": "2026-09-20T21:55:44.516119+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-20T21:31:43.948011+00:00",
|
||||
"communityUpdatedAt": "2026-09-20T21:55:44.516119+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-20T17:22:53.568270+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -425,121 +425,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-20T21:36:00.876118+00:00",
|
||||
"generatedAt": "2026-09-20T21:55:44.516119+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 941.16,
|
||||
"backlogHours": 980.1666666666666,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.1411458042467975,
|
||||
"queueFactor": 0.995362345871555,
|
||||
"queueWeight": 0.995362345871555,
|
||||
"recentSuccess": 42,
|
||||
"recentSuccessRate": 0.28,
|
||||
"recentTerminal": 150,
|
||||
"recentWilsonLowerBound": 0.21432932072113414,
|
||||
"qualityFactor": 0.996003703819594,
|
||||
"queueFactor": 0.992465584765776,
|
||||
"queueWeight": 0.992465584765776,
|
||||
"recentSuccess": 41,
|
||||
"recentSuccessRate": 0.2847222222222222,
|
||||
"recentTerminal": 144,
|
||||
"recentWilsonLowerBound": 0.21735591931294387,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.1358535646965746,
|
||||
"selectionWeight": 0.9884993983401921,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 25.0,
|
||||
"waiting": 23529
|
||||
"throughputPerHour": 24.0,
|
||||
"waiting": 23524
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1206.8085106382978,
|
||||
"backlogHours": 1279.0827067669172,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.0619512082751106,
|
||||
"queueFactor": 0.9589257305462435,
|
||||
"queueWeight": 0.9589257305462435,
|
||||
"recentSuccess": 50,
|
||||
"recentSuccessRate": 0.3546099290780142,
|
||||
"recentTerminal": 141,
|
||||
"recentWilsonLowerBound": 0.2804602036792118,
|
||||
"qualityFactor": 1.7020675281196884,
|
||||
"queueFactor": 0.9536206594284847,
|
||||
"queueWeight": 0.9536206594284847,
|
||||
"recentSuccess": 47,
|
||||
"recentSuccessRate": 0.3533834586466165,
|
||||
"recentTerminal": 133,
|
||||
"recentWilsonLowerBound": 0.2773009746386,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.97725806874592,
|
||||
"selectionWeight": 1.6231267585573081,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.5,
|
||||
"waiting": 28360
|
||||
"throughputPerHour": 22.166666666666668,
|
||||
"waiting": 28353
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 182.89024390243904,
|
||||
"backlogHours": 179.2814371257485,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.3234949822933848,
|
||||
"queueFactor": 1.272629968048792,
|
||||
"queueWeight": 1.272629968048792,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.17073170731707318,
|
||||
"recentTerminal": 164,
|
||||
"recentWilsonLowerBound": 0.120845353418255,
|
||||
"qualityFactor": 0.31515144591836824,
|
||||
"queueFactor": 1.2805016620553165,
|
||||
"queueWeight": 1.2805016620553165,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.17964071856287425,
|
||||
"recentTerminal": 167,
|
||||
"recentWilsonLowerBound": 0.12882975377757394,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.41168940897997486,
|
||||
"selectionWeight": 0.4035519502976067,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 27.333333333333332,
|
||||
"waiting": 4999
|
||||
"throughputPerHour": 27.833333333333332,
|
||||
"waiting": 4990
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1735.0384615384617,
|
||||
"backlogHours": 1735.7307692307693,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.9708169130265738,
|
||||
"queueFactor": 0.9081014324397353,
|
||||
"queueWeight": 0.9081014324397353,
|
||||
"qualityFactor": 0.8215980573533637,
|
||||
"queueFactor": 0.9109364724770921,
|
||||
"queueWeight": 0.9109364724770921,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.3076923076923077,
|
||||
"recentTerminal": 52,
|
||||
"recentWilsonLowerBound": 0.19914562391353519,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.8816002293561536,
|
||||
"selectionWeight": 0.7484236361595047,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.666666666666666,
|
||||
"waiting": 15037
|
||||
"waiting": 15043
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 413.55555555555554,
|
||||
"backlogHours": 439.4645669291338,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.33317284389047436,
|
||||
"queueFactor": 1.1260317800457675,
|
||||
"queueWeight": 1.1260317800457675,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.17777777777777778,
|
||||
"recentTerminal": 135,
|
||||
"recentWilsonLowerBound": 0.12247545696005419,
|
||||
"qualityFactor": 0.3610361403683465,
|
||||
"queueFactor": 1.1193653664180774,
|
||||
"queueWeight": 1.1193653664180774,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.1968503937007874,
|
||||
"recentTerminal": 127,
|
||||
"recentWilsonLowerBound": 0.13704040055668698,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.37516321046890144,
|
||||
"selectionWeight": 0.40413135155358265,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.5,
|
||||
"waiting": 9305
|
||||
"throughputPerHour": 21.166666666666668,
|
||||
"waiting": 9302
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 40.29032258064516,
|
||||
"backlogHours": 40.76712328767123,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -549,196 +549,196 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.06451612903225806,
|
||||
"recentTerminal": 372,
|
||||
"recentWilsonLowerBound": 0.04373425268891228,
|
||||
"recentSuccessRate": 0.06575342465753424,
|
||||
"recentTerminal": 365,
|
||||
"recentWilsonLowerBound": 0.04458056738012717,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 62.0,
|
||||
"waiting": 2498
|
||||
"throughputPerHour": 60.833333333333336,
|
||||
"waiting": 2480
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 105.83571428571429,
|
||||
"backlogHours": 105.7153024911032,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.10699913524281071,
|
||||
"qualityFactor": 0.07448869488744207,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.10357142857142858,
|
||||
"recentTerminal": 280,
|
||||
"recentWilsonLowerBound": 0.07308472995929172,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.13909887581565392,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.09608540925266904,
|
||||
"recentTerminal": 281,
|
||||
"recentWilsonLowerBound": 0.06687684091223194,
|
||||
"running": 10,
|
||||
"selectionWeight": 0.0968353033536747,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 46.666666666666664,
|
||||
"waiting": 4939
|
||||
"throughputPerHour": 46.833333333333336,
|
||||
"waiting": 4951
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2549.3684210526317,
|
||||
"backlogHours": 2421.9,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.1154525902684482,
|
||||
"queueFactor": 0.8571677768333111,
|
||||
"queueWeight": 0.8571677768333111,
|
||||
"qualityFactor": 0.8370844255606612,
|
||||
"queueFactor": 0.866536806261629,
|
||||
"queueWeight": 0.866536806261629,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.34210526315789475,
|
||||
"recentTerminal": 38,
|
||||
"recentWilsonLowerBound": 0.21212220026458956,
|
||||
"recentSuccessRate": 0.325,
|
||||
"recentTerminal": 40,
|
||||
"recentWilsonLowerBound": 0.20084316962661727,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.9561300169633641,
|
||||
"selectionWeight": 0.7253644646966857,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.333333333333333,
|
||||
"throughputPerHour": 6.666666666666667,
|
||||
"waiting": 16146
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 487.54545454545456,
|
||||
"backlogHours": 498.6046511627907,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.3505217926647097,
|
||||
"queueFactor": 1.0985718336707055,
|
||||
"queueWeight": 1.0985718336707055,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.18181818181818182,
|
||||
"recentTerminal": 132,
|
||||
"recentWilsonLowerBound": 0.12533423590114975,
|
||||
"qualityFactor": 0.34848835740554857,
|
||||
"queueFactor": 1.0983657865465264,
|
||||
"queueWeight": 1.0983657865465264,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.1937984496124031,
|
||||
"recentTerminal": 129,
|
||||
"recentWilsonLowerBound": 0.13485458233735692,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.385073368509213,
|
||||
"selectionWeight": 0.3827676887840524,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.0,
|
||||
"waiting": 10726
|
||||
"throughputPerHour": 21.5,
|
||||
"waiting": 10720
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 504.40909090909093,
|
||||
"backlogHours": 500.390977443609,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.3909105698028423,
|
||||
"queueFactor": 1.0929827076472585,
|
||||
"queueWeight": 1.0929827076472585,
|
||||
"qualityFactor": 0.3252275824589706,
|
||||
"queueFactor": 1.0977767402454068,
|
||||
"queueWeight": 1.0977767402454068,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.1893939393939394,
|
||||
"recentTerminal": 132,
|
||||
"recentWilsonLowerBound": 0.1317037304939829,
|
||||
"recentSuccessRate": 0.18796992481203006,
|
||||
"recentTerminal": 133,
|
||||
"recentWilsonLowerBound": 0.13068596058578308,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.4272584930310432,
|
||||
"selectionWeight": 0.357027275309703,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.0,
|
||||
"waiting": 11097
|
||||
"throughputPerHour": 22.166666666666668,
|
||||
"waiting": 11092
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2202.8135593220336,
|
||||
"backlogHours": 2363.6727272727276,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8761612980612937,
|
||||
"queueWeight": 0.8761612980612937,
|
||||
"queueFactor": 0.8697057544281359,
|
||||
"queueWeight": 0.8697057544281359,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.423728813559322,
|
||||
"recentTerminal": 59,
|
||||
"recentWilsonLowerBound": 0.3061253228310244,
|
||||
"recentSuccessRate": 0.45454545454545453,
|
||||
"recentTerminal": 55,
|
||||
"recentWilsonLowerBound": 0.330250717464462,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.1904032451532345,
|
||||
"selectionWeight": 2.1742643860703397,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.833333333333334,
|
||||
"waiting": 21661
|
||||
"throughputPerHour": 9.166666666666666,
|
||||
"waiting": 21667
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 3133.0,
|
||||
"backlogHours": 3614.769230769231,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.10790180489267844,
|
||||
"queueFactor": 0.8310682051499603,
|
||||
"queueWeight": 0.8310682051499603,
|
||||
"qualityFactor": 0.12646916570868544,
|
||||
"queueFactor": 0.8160154071110767,
|
||||
"queueWeight": 0.8160154071110767,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.16666666666666666,
|
||||
"recentTerminal": 30,
|
||||
"recentWilsonLowerBound": 0.07336434240351682,
|
||||
"recentSuccessRate": 0.19230769230769232,
|
||||
"recentTerminal": 26,
|
||||
"recentWilsonLowerBound": 0.08506935771788268,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.08967375932459946,
|
||||
"selectionWeight": 0.10320078774277117,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.0,
|
||||
"waiting": 15665
|
||||
"throughputPerHour": 4.333333333333333,
|
||||
"waiting": 15664
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1466.7457627118642,
|
||||
"backlogHours": 1803.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 0.9312740476005069,
|
||||
"queueWeight": 0.9312740476005069,
|
||||
"recentSuccess": 4,
|
||||
"recentSuccessRate": 0.06779661016949153,
|
||||
"recentTerminal": 59,
|
||||
"recentWilsonLowerBound": 0.02667818709839157,
|
||||
"queueFactor": 0.9057557218131672,
|
||||
"queueWeight": 0.9057557218131672,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.10416666666666667,
|
||||
"recentTerminal": 48,
|
||||
"recentWilsonLowerBound": 0.04532105090117825,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.04656370238002535,
|
||||
"selectionWeight": 0.045287786090658366,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 9.833333333333334,
|
||||
"waiting": 14423
|
||||
"throughputPerHour": 8.0,
|
||||
"waiting": 14424
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 883.7222222222222,
|
||||
"backlogHours": 883.7777777777778,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.684616974133644,
|
||||
"queueFactor": 1.0048086389645945,
|
||||
"queueWeight": 1.0048086389645945,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.24074074074074073,
|
||||
"qualityFactor": 0.6408380076104798,
|
||||
"queueFactor": 1.0079964060327424,
|
||||
"queueWeight": 1.0079964060327424,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.25,
|
||||
"recentTerminal": 108,
|
||||
"recentWilsonLowerBound": 0.16991077352557898,
|
||||
"recentWilsonLowerBound": 0.17787718518702555,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.6879090499912858,
|
||||
"selectionWeight": 0.6459624085205469,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.0,
|
||||
"waiting": 15907
|
||||
"waiting": 15908
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-20T21:31:43.948011+00:00",
|
||||
"queueAttemptedAt": "2026-09-20T21:55:44.516119+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-20T21:31:43.948011+00:00",
|
||||
"queueUpdatedAt": "2026-09-20T21:55:44.516119+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Kunlunxin_p-800",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-20T21:33:11.597469+00:00",
|
||||
"lastSyncTime": "2026-09-20T21:33:11.158049+00:00",
|
||||
"generatedAt": "2026-09-20T21:55:44.447564+00:00",
|
||||
"lastSyncTime": "2026-09-20T21:55:44.371069+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -328,6 +328,25 @@
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:gemma4_unified": {
|
||||
"architectureSignature": "model_type:gemma4_unified",
|
||||
"architectures": [],
|
||||
"evidenceCount": 1,
|
||||
"expiresAt": "2026-10-20T02:52:43.767336+00:00",
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"latestFailureAt": "2026-09-20T02:52:43.767336+00:00",
|
||||
"latestSuccessfulAt": null,
|
||||
"matchType": "model_type",
|
||||
"modelType": "gemma4_unified",
|
||||
"sourceModelIds": [
|
||||
"mlx-community/gemma-4-12B-it-qat-OptiQ-4bit"
|
||||
],
|
||||
"sourceTaskIds": [
|
||||
"4969004"
|
||||
],
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
"ascend_910-b4|vllm_tokenizer_patch|text-generation|model_type:qwen3_5": {
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectures": [],
|
||||
@@ -2271,12 +2290,12 @@
|
||||
}
|
||||
},
|
||||
"architectureCompatibilitySummary": {
|
||||
"activeBlockCount": 111,
|
||||
"activeBlockCount": 112,
|
||||
"byGpuFramework": {
|
||||
"Ascend_910-b3|vllm": 11,
|
||||
"Ascend_910-b3|vllm_tokenizer_patch": 4,
|
||||
"Ascend_910-b4|vllm": 12,
|
||||
"Ascend_910-b4|vllm_tokenizer_patch": 2,
|
||||
"Ascend_910-b4|vllm_tokenizer_patch": 3,
|
||||
"Biren_166m|vllm": 3,
|
||||
"Cambricon_mlu-370-x8|vllm": 6,
|
||||
"Cambricon_mlu-370-x8|vllm-mlu": 5,
|
||||
@@ -2565,15 +2584,15 @@
|
||||
"unresolvedFailureCount": 17
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 15,
|
||||
"attributableFailureCount": 16,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 15,
|
||||
"decisionTotal": 16,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 25,
|
||||
"framework_architecture_unsupported": 15
|
||||
"framework_architecture_unsupported": 16
|
||||
},
|
||||
"failureCount": 40,
|
||||
"failureCount": 41,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"pendingCount": 0,
|
||||
@@ -2583,7 +2602,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 40,
|
||||
"total": 41,
|
||||
"unresolvedFailureCount": 25
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
@@ -4996,28 +5015,28 @@
|
||||
"unresolvedFailureCount": 137
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
"attributableFailureCount": 43,
|
||||
"decisionFailureRate": 0.9556,
|
||||
"decisionSuccessRate": 0.0444,
|
||||
"decisionTotal": 45,
|
||||
"attributableFailureCount": 44,
|
||||
"decisionFailureRate": 0.9565,
|
||||
"decisionSuccessRate": 0.0435,
|
||||
"decisionTotal": 46,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 37,
|
||||
"framework_architecture_unsupported": 41,
|
||||
"framework_architecture_unsupported": 42,
|
||||
"model_load": 1,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 80,
|
||||
"failureRate": 0.9756,
|
||||
"failureCount": 81,
|
||||
"failureRate": 0.9759,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0244,
|
||||
"total": 82,
|
||||
"successRate": 0.0241,
|
||||
"total": 83,
|
||||
"unresolvedFailureCount": 37
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-20T21:33:11.588812+00:00",
|
||||
"generatedAt": "2026-09-20T21:55:44.436706+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 81,
|
||||
@@ -5045,14 +5064,14 @@
|
||||
"unresolvedFailureCount": 117
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 308,
|
||||
"decisionFailureRate": 0.8324,
|
||||
"decisionSuccessRate": 0.1676,
|
||||
"decisionTotal": 370,
|
||||
"attributableFailureCount": 309,
|
||||
"decisionFailureRate": 0.8329,
|
||||
"decisionSuccessRate": 0.1671,
|
||||
"decisionTotal": 371,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 153,
|
||||
"context_length": 1,
|
||||
"framework_architecture_unsupported": 168,
|
||||
"framework_architecture_unsupported": 169,
|
||||
"memory_capacity": 18,
|
||||
"model_load": 85,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -5062,14 +5081,14 @@
|
||||
"日志缺失": 14,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 905,
|
||||
"failureRate": 0.9359,
|
||||
"failureCount": 906,
|
||||
"failureRate": 0.936,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 62,
|
||||
"successRate": 0.0641,
|
||||
"total": 967,
|
||||
"successRate": 0.064,
|
||||
"total": 968,
|
||||
"unresolvedFailureCount": 596
|
||||
},
|
||||
"Biren_166m": {
|
||||
@@ -5447,7 +5466,7 @@
|
||||
"hygon_k100-ai": 64.0
|
||||
},
|
||||
"pendingRecords": 0,
|
||||
"policyCancelledRecords": 155,
|
||||
"policyCancelledRecords": 156,
|
||||
"profileCombinationStats": {
|
||||
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|cohere2|none": {
|
||||
"attributableFailureCount": 0,
|
||||
@@ -5999,6 +6018,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4_unified|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"modelType": "gemma4_unified",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4|none": {
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -12956,17 +12998,17 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"attributableFailureCount": 4,
|
||||
"consecutiveFailures": 4,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 3,
|
||||
"decisionTotal": 4,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 8,
|
||||
"framework_architecture_unsupported": 3
|
||||
"framework_architecture_unsupported": 4
|
||||
},
|
||||
"failureCount": 11,
|
||||
"failureCount": 12,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastPlatformFailureAt": null,
|
||||
@@ -12978,7 +13020,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 11,
|
||||
"total": 12,
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
@@ -13301,18 +13343,18 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 9,
|
||||
"attributableFailureCount": 8,
|
||||
"consecutiveFailures": 1,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.6,
|
||||
"decisionSuccessRate": 0.4,
|
||||
"decisionTotal": 15,
|
||||
"decisionFailureRate": 0.5714,
|
||||
"decisionSuccessRate": 0.4286,
|
||||
"decisionTotal": 14,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 9
|
||||
"framework_architecture_unsupported": 8
|
||||
},
|
||||
"failureCount": 10,
|
||||
"failureRate": 0.625,
|
||||
"failureCount": 9,
|
||||
"failureRate": 0.6,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-18T11:36:11.987002+00:00",
|
||||
@@ -13320,10 +13362,10 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 6,
|
||||
"successRate": 0.375,
|
||||
"successRate": 0.4,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 16,
|
||||
"total": 15,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Kunlunxin_p-800|unknown|text-generation": {
|
||||
@@ -14044,6 +14086,31 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4_unified|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"consecutiveFailures": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"lastTerminalAt": "2026-09-20T21:55:28.960251+00:00",
|
||||
"modelType": "gemma4_unified",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4|none": {
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
@@ -17408,6 +17475,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4_unified|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "gemma4_unified",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|gemma4|none|32": {
|
||||
"attributableFailureCount": 2,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -27483,20 +27574,20 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"terminalRecords": 15974,
|
||||
"totalRecords": 16129,
|
||||
"terminalRecords": 15975,
|
||||
"totalRecords": 16131,
|
||||
"totals": {
|
||||
"attributableFailureCount": 5805,
|
||||
"attributableFailureCount": 5806,
|
||||
"decisionFailureRate": 0.8617,
|
||||
"decisionSuccessRate": 0.1383,
|
||||
"decisionTotal": 6737,
|
||||
"decisionTotal": 6738,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 3812,
|
||||
"architecture_compatibility": 212,
|
||||
"attention_backend": 1,
|
||||
"backend_operator": 102,
|
||||
"context_length": 318,
|
||||
"framework_architecture_unsupported": 2018,
|
||||
"framework_architecture_unsupported": 2019,
|
||||
"memory_capacity": 1196,
|
||||
"model_load": 484,
|
||||
"platform_infrastructure": 922,
|
||||
@@ -27507,14 +27598,14 @@
|
||||
"日志缺失": 719,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 15042,
|
||||
"failureCount": 15043,
|
||||
"failureRate": 0.9417,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 922,
|
||||
"successCount": 932,
|
||||
"successRate": 0.0583,
|
||||
"total": 15974,
|
||||
"total": 15975,
|
||||
"unresolvedFailureCount": 8315
|
||||
},
|
||||
"warnings": [
|
||||
@@ -27568,6 +27659,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 16129,
|
||||
"summarizedRecords": 16131,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -14,13 +14,13 @@
|
||||
100
|
||||
],
|
||||
"accounts": 12,
|
||||
"activeScanned": 1154,
|
||||
"activeScanned": 1145,
|
||||
"ageCleanupMode": "admission_only",
|
||||
"agePolicySkipped": {
|
||||
"cleanupDisabled": true,
|
||||
"reason": "admission_only"
|
||||
},
|
||||
"architectureBlockCount": 111,
|
||||
"architectureBlockCount": 112,
|
||||
"architectureFrameworkCatalog": {
|
||||
"ascend_910-b3|text-generation": [
|
||||
"llamacpp",
|
||||
@@ -67,153 +67,27 @@
|
||||
]
|
||||
},
|
||||
"architectureFrameworkCatalogErrors": {},
|
||||
"architectureIncompatibleCount": 7,
|
||||
"architectureIncompatibleCount": 1,
|
||||
"architectureIncompatibleTasks": [
|
||||
{
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969016,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4782245,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969005,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.762431+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:gemma4",
|
||||
"architectureSignatures": [
|
||||
"model_type:gemma4"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969017,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 5,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.767336+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:gemma4_unified",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:gemma4_unified"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX",
|
||||
"modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4899358,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 7,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969013,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 8,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4895729,
|
||||
"taskId": 4968995,
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
],
|
||||
@@ -239,125 +113,29 @@
|
||||
"unsloth/LFM2-2.6B-Exp-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/unsloth/LFM2-2.6B-Exp-GGUF/resolve/master/config.json (status=404)",
|
||||
"z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
|
||||
},
|
||||
"architectureModelConfigsComplete": 62,
|
||||
"architectureModelConfigsComplete": 60,
|
||||
"architectureOnly": true,
|
||||
"architecturePolicySkipped": {
|
||||
"frameworkCatalogUnknown": 0,
|
||||
"frameworkContextUnknown": 74,
|
||||
"frameworkContextUnknown": 72,
|
||||
"modelArchitectureUnknown": 134,
|
||||
"noMatchingBlock": 988,
|
||||
"noMatchingBlock": 985,
|
||||
"partiallyBlockedFrameworkSet": 25,
|
||||
"runningMatchedProtected": 0,
|
||||
"submissionContextMismatch": 0,
|
||||
"submissionContextUnknown": 0
|
||||
},
|
||||
"cancelledCount": 7,
|
||||
"cancelledCount": 1,
|
||||
"cancelledTasks": [
|
||||
{
|
||||
"accountIndex": 2,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969016,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4782245,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969005,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 3,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.762431+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:gemma4",
|
||||
"architectureSignatures": [
|
||||
"model_type:gemma4"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "mlx-community/gemma-4-26B-A4B-it-qat-OptiQ-4bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969017,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 5,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.767336+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignature": "model_type:gemma4_unified",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
"model_type:gemma4_unified"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
@@ -367,64 +145,16 @@
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX",
|
||||
"modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4899358,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 7,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4969013,
|
||||
"taskType": "text-generation"
|
||||
},
|
||||
{
|
||||
"accountIndex": 8,
|
||||
"architectureBlockEvidenceCount": 1,
|
||||
"architectureBlockExpiresAt": "2026-10-20T02:52:43.746995+00:00",
|
||||
"architectureMatchScope": "exact_framework",
|
||||
"architectureMatchType": "model_type",
|
||||
"architectureSignature": "model_type:qwen3_5",
|
||||
"architectureSignatures": [
|
||||
"model_type:qwen3_5"
|
||||
],
|
||||
"cleanupReasons": [
|
||||
"known_framework_architecture_incompatible"
|
||||
],
|
||||
"evaluatedFrameworks": [
|
||||
"vllm_tokenizer_patch"
|
||||
],
|
||||
"framework": "vllm_tokenizer_patch",
|
||||
"gpuType": "Ascend_910-b4",
|
||||
"modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit",
|
||||
"reason": "known_framework_architecture_incompatible",
|
||||
"status": "waiting",
|
||||
"taskId": 4895729,
|
||||
"taskId": 4968995,
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
],
|
||||
"certainOomCount": 0,
|
||||
"certainOomTasks": [],
|
||||
"cleanupCandidateCount": 7,
|
||||
"cleanupCandidateCount": 1,
|
||||
"dryRun": false,
|
||||
"listingErrors": {},
|
||||
"modelAgeErrors": {},
|
||||
@@ -449,7 +179,7 @@
|
||||
],
|
||||
"oldOverflowCount": 0,
|
||||
"oldOverflowTasks": [],
|
||||
"policyCancelledRecorded": 7,
|
||||
"policyCancelledRecorded": 1,
|
||||
"policyNoLongerAppliesCount": 0,
|
||||
"policyNoLongerAppliesTasks": [],
|
||||
"recentModelDays": 7,
|
||||
@@ -462,5 +192,5 @@
|
||||
"repositorySizeUnknown": 0
|
||||
},
|
||||
"stopErrors": [],
|
||||
"uniqueModels": 338
|
||||
"uniqueModels": 334
|
||||
}
|
||||
|
||||
@@ -168,6 +168,7 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:33:11.158049+00:00", "modelId": "Arain119/Sophia", "modelProfile": {"architectures": ["SophiaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2226652224, "estimatedRequiredGiB": 7.28, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sophia_hybrid", "modelscopeFileSize": 6513869659, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 1113293776, "modelscopeTags": ["license:Apache License 2.0", "model_type:sophia_hybrid", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6513869659}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.893989+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969012", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:06:45.850250+00:00", "modelId": "aisingapore/Qwen-SEA-LION-v4-32B-IT-4BIT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19935028960, "estimatedRequiredGiB": 22.299, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 19953127685, "modelscopeLicense": "mit", "modelscopeParams": 32762123264, "modelscopeTags": ["license:mit", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19953127685}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:50.839341+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969006", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:49:19.683277+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2340697867, "estimatedRequiredGiB": 2.621, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 2345554722, "modelscopeLicense": "other", "modelscopeParams": 1170340608, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2345554722}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:43.837507+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969003", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["gemma4_unified"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:55:28.960251+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "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": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:43.767336+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969004", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["gemma4"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:33:11.157994+00:00", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:43.765788+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4968997", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:33:11.158033+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "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", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:43.764080+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969001", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["gemma4"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T20:49:19.683300+00:00", "modelId": "mlx-community/gemma-4-e4b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7486327132, "estimatedRequiredGiB": 8.403, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 7518908360, "modelscopeLicense": "gemma", "modelscopeParams": 2227418442, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7518908360}, "outcome": "failed", "status": "success", "submitTime": "2026-09-20T02:52:43.762431+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4968999", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T09:34:12.938151+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4594446", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-15T09:34:12.938183+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4590565", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-15T09:23:51.409303+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:17:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4595432", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T09:13:01.342842+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4585989", "taskType": "text-generation", "verifyResult": -1}
|
||||
|
||||
@@ -1846,6 +1846,62 @@
|
||||
{"batchId": "f153c23218ff4247ba8eae298865975f", "completedAt": "2026-09-20T21:49:54.153922+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:37:27.998776+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2edb869422514d3989f45532266f31ba", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "reason": null, "reconciledAt": "2026-09-20T21:55:25.927754+00:00", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4988063", "taskType": "text-generation"}
|
||||
{"batchId": "f153c23218ff4247ba8eae298865975f", "completedAt": "2026-09-20T21:49:54.154012+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:37:28.000165+00:00", "framework": "vllm_fix_tokenizer", "intentId": "773922009bfe4a7fb352998c5b25eb4b", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "reason": null, "reconciledAt": "2026-09-20T21:55:25.929434+00:00", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Biren_166m", "taskId": "4988230", "taskType": "text-generation"}
|
||||
{"batchId": "f153c23218ff4247ba8eae298865975f", "completedAt": "2026-09-20T21:49:54.154045+00:00", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:37:28.000651+00:00", "framework": "vllm-patch-tokenizer", "intentId": "b89432be93924d6393611e350c973d7f", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "reason": null, "reconciledAt": "2026-09-20T21:55:25.927751+00:00", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4988291", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.570798+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b9057a72a819402a83f389f215adaf5c", "lastModified": "2026-08-24T20:05:18+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "repoId": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.570920+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c946c063861d4c4e9da8c5d8e348f6bc", "lastModified": "2026-08-24T19:59:13+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "repoId": "RedHatAI/starcoder2-7b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.570992+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5b8e5f37e4f543ea87ffe23b38a65bd7", "lastModified": "2026-08-24T19:51:52+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571059+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cf9260fa2e774625ba58295aacde97d1", "lastModified": "2026-08-24T20:02:01+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "repoId": "RedHatAI/gemma-2-2b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571127+00:00", "framework": "vllm-mlu", "intentId": "a5018ac5d0ca4543b695b01e0d6c420c", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-FP8", "repoId": "RedHatAI/starcoder2-15b-FP8", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571247+00:00", "framework": "vllm", "intentId": "9a0918825a15471ca078af3e2eec427c", "lastModified": "2026-08-24T20:17:00+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "repoId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571354+00:00", "framework": "vllm", "intentId": "786a70da19a840ec8e24a287d9941dca", "lastModified": "2026-08-24T20:06:34+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a8", "repoId": "RedHatAI/starcoder2-3b-quantized.w8a8", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571457+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f50b25c733764355bae28e0d7fd98c52", "lastModified": "2026-09-04T12:06:20+00:00", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "repoId": "inclusionAI/Ling-3.0-tiny", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571534+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9ffedea7bc044fe99e29884589b1707f", "lastModified": "2026-08-24T20:31:44+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571611+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e0c6c5b21636468bb141cccbd1b834a7", "lastModified": "2026-08-24T20:20:16+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-FP8", "repoId": "neuralmagic/starcoder2-15b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571696+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ca2484634874410b8bec28b7e2ea1026", "lastModified": "2026-08-26T17:18:42+00:00", "modelAddress": "https://modelscope.cn/models/nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "repoId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571773+00:00", "framework": "vllm_fix_tokenizer", "intentId": "beba8a02a4c74fdd826aed861f2c6d15", "lastModified": "2026-09-08T03:51:51+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "repoId": "XHToken/Spark-X2.5-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571849+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e209051f0cf34cb7832bde96a049c29e", "lastModified": "2026-09-12T12:32:06+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "repoId": "OpenBMB/MiniCPM5-2B-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.571925+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7cd832a8bff449ce9d271f617c2f00f7", "lastModified": "2026-08-31T14:27:40+00:00", "modelAddress": "https://modelscope.cn/models/sbintuitions/sarashina2.2-3b-instruct-v0.1", "repoId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572002+00:00", "framework": "vllm_fix_tokenizer", "intentId": "18eee6aa3a0a4f639e13f7fd82b195a7", "lastModified": "2026-09-10T07:52:22+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "repoId": "TokenRhythm/NeoHorse-1-4B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572078+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8f52e8792a4240d0b5e9451c956b6d13", "lastModified": "2026-08-26T12:24:21+00:00", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "repoId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572154+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3bed056b221646d298a1d1acd1c8d693", "lastModified": "2026-08-25T12:06:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B", "repoId": "LiquidAI/LFM2.5-8B-A1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572230+00:00", "framework": "vllm_fix_tokenizer", "intentId": "101a3b1653634fc0bfc411872eb5c772", "lastModified": "2026-09-03T13:37:32+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "repoId": "XHToken/Spark-X2.5-1.7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572307+00:00", "framework": "vllm_fix_tokenizer", "intentId": "06b8dca798aa49e69ec7ffde32b5179c", "lastModified": "2026-08-26T16:41:11+00:00", "modelAddress": "https://modelscope.cn/models/apodex/Apodex-1.1-mini-GPTQ-Int4", "repoId": "apodex/Apodex-1.1-mini-GPTQ-Int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572384+00:00", "framework": "vllm_fix_tokenizer", "intentId": "71c7ee413baa4164b6c860276f7e6d88", "lastModified": "2026-08-26T12:23:32+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572460+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0f4a5616db2e43bf8f0ab560fc43f1c1", "lastModified": "2026-08-26T17:23:58+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572565+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5de6f58110d34692aa3a9939e35594ee", "lastModified": "2026-08-26T20:28:29+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572641+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b228725fe20a418aa477a1f547548de5", "lastModified": "2026-08-31T14:36:00+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572725+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2e1045afb6c24dff9a2c0ae54778a911", "lastModified": "2026-08-24T20:33:29+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "repoId": "RedHatAI/starcoder2-3b-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572801+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f57e12c2e7874a9ca299d1a71c7b8136", "lastModified": "2026-09-04T12:06:11+00:00", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "repoId": "sapientinc/HRM-Text-1B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572877+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3c6d840046034efb91d8a4d399840cd0", "lastModified": "2026-09-10T07:49:50+00:00", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "repoId": "TokenRhythm/NeoHorse-1-9B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.572953+00:00", "framework": "vllm_fix_tokenizer", "intentId": "d559358d64b24926a79a8aa03a45716b", "lastModified": "2026-08-31T23:02:41+00:00", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "repoId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573029+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ebaf0cb0afa442d6a37c550fb542e0ee", "lastModified": "2026-09-04T07:05:43+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "repoId": "XHToken/Spark-X2.5-4B-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573106+00:00", "framework": "vllm_fix_tokenizer", "intentId": "05787cfef3f0423397703de6ac1019bd", "lastModified": "2026-09-09T06:31:08+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "repoId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573182+00:00", "framework": "vllm_fix_tokenizer", "intentId": "649d8938aae640c78120b67498733ee1", "lastModified": "2026-09-02T05:56:49+00:00", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "repoId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573258+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3bc238a5d29840ab8681b9900f7692ed", "lastModified": "2026-08-26T13:13:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "repoId": "aisingapore/Gemma-SEA-LION-v4-27B-IT-FP8-Dynamic", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573334+00:00", "framework": "vllm_fix_tokenizer", "intentId": "05f994607b3d4503b2563f88769ffafb", "lastModified": "2026-09-03T06:52:45+00:00", "modelAddress": "https://modelscope.cn/models/bharatgenai/Param2-17B-A2.4B-Thinking", "repoId": "bharatgenai/Param2-17B-A2.4B-Thinking", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573410+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a3ed89d789114995868824f372d3f03c", "lastModified": "2026-08-28T09:38:42+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573485+00:00", "framework": "vllm_fix_tokenizer", "intentId": "074bab56cf2445ca967dc29ecb1a950f", "lastModified": "2026-09-08T15:45:26+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "repoId": "JANGQ-AI/AppleScript-8B-JANG_4M", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573562+00:00", "framework": "vllm_fix_tokenizer", "intentId": "27b6a82417ba43a8ae7f71d0bdd0dd29", "lastModified": "2026-09-08T15:40:32+00:00", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "repoId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573638+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e215f38604ce47be88d735f367a6a237", "lastModified": "2026-08-26T20:08:51+00:00", "modelAddress": "https://modelscope.cn/models/VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "repoId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573724+00:00", "framework": "vllm_fix_tokenizer", "intentId": "82753e5e572f4e53ba21b7d67b3f0da5", "lastModified": "2026-08-26T15:57:06+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "repoId": "aisingapore/Llama-SEA-LION-v3.5-70B-R-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573800+00:00", "framework": "vllm_fix_tokenizer", "intentId": "df6a4d7b4fb243e99b4ba23c22d10133", "lastModified": "2026-09-09T06:27:24+00:00", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "repoId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573876+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0cc62b6e6b9c4171a6b9f35887ae2fe7", "lastModified": "2026-08-28T05:30:04+00:00", "modelAddress": "https://modelscope.cn/models/whcl412/mlx-LycheeAI-coder-1.7b", "repoId": "whcl412/mlx-LycheeAI-coder-1.7b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.573952+00:00", "framework": "vllm_fix_tokenizer", "intentId": "05b3a9de7f3447059e570d70c261ff3f", "lastModified": "2026-08-29T01:07:23+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "repoId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574029+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7f7f77c0e3dc467ab54ea697e66b5679", "lastModified": "2026-09-03T07:00:50+00:00", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "repoId": "EschaLabs/Qwen3.8-27B-Escha-W2", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574105+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a17145aba75148aa833ec4c409cae1c8", "lastModified": "2026-08-26T17:29:18+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B", "repoId": "aisingapore/SEA-LION-v1-7B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574181+00:00", "framework": "vllm_fix_tokenizer", "intentId": "96d3fd4622d94eb6a782191a435f5fcc", "lastModified": "2026-08-26T19:32:38+00:00", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "repoId": "pfnet/plamo-3-nict-8b-base", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574256+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b8f8e960dadd4a968171626dac80f876", "lastModified": "2026-08-26T19:43:40+00:00", "modelAddress": "https://modelscope.cn/models/inceptionai/Jais-2-8B-Chat", "repoId": "inceptionai/Jais-2-8B-Chat", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574332+00:00", "framework": "vllm", "intentId": "840ab00c44d7431e917d5c1cc4b3584f", "lastModified": "2026-08-24T20:29:58+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "repoId": "RedHatAI/starcoder2-7b-quantized.w8a16", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "pending", "targetGpu": "Biren_166m", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574429+00:00", "framework": "vllm", "intentId": "1798b1cf8e364a23b35324cb3398ec16", "lastModified": "2026-08-24T19:46:26+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a8", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_mrv-100", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574518+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0ddeddb5f4af4f6a8f246d57678ae622", "lastModified": "2026-08-24T20:22:00+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-2b-it-quantized.w8a16", "repoId": "neuralmagic/gemma-2-2b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574595+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c5c91bd87fdd4b72a81abf4b3e498008", "lastModified": "2026-08-24T20:26:53+00:00", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "repoId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574681+00:00", "framework": "vllm_fix_tokenizer", "intentId": "8b425364ee49484fa0510a371f214f6e", "lastModified": "2026-08-26T14:51:55+00:00", "modelAddress": "https://modelscope.cn/models/aisingapore/SEA-LION-v1-7B-IT-GPTQ", "repoId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "4d80215b8854e486ecf078eda8f5db649838852684b9429ab6d7b0d91bb411cf", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574758+00:00", "framework": "vllm-patch-tokenizer", "intentId": "5b5b32e68fc442d1a53f114162710bfb", "lastModified": "2026-08-24T20:04:01+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "repoId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574834+00:00", "framework": "vllm-patch-tokenizer", "intentId": "fa32416258e94eba80a0f9aa856d3621", "lastModified": "2026-08-24T19:53:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "repoId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574909+00:00", "framework": "vllm-patch-tokenizer", "intentId": "e3eb71c7659d4fde98af10fcd348fa0b", "lastModified": "2026-08-24T20:09:59+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-2-7b-chat-quantized.w8a8", "repoId": "neuralmagic/Llama-2-7b-chat-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.574984+00:00", "framework": "vllm-patch-tokenizer", "intentId": "d779bd751c65450c8d7c0d1a3595a201", "lastModified": "2026-08-24T20:01:20+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "repoId": "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.575059+00:00", "framework": "vllm-patch-tokenizer", "intentId": "d0d3ccc563b74f1fb175b20e90802245", "lastModified": "2026-08-24T20:10:58+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "repoId": "neuralmagic/Meta-Llama-3.1-8B-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.575133+00:00", "framework": "vllm-patch-tokenizer", "intentId": "629abb01e40e4b87998e08b94961e332", "lastModified": "2026-08-24T20:22:06+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "repoId": "neuralmagic/starcoder2-15b-quantized.w8a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "67a81b105def48f8a969ca85668e5231", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:57:31.575208+00:00", "framework": "vllm-patch-tokenizer", "intentId": "9c01e97a0c3647b99f745074850fffa6", "lastModified": "2026-08-24T20:14:53+00:00", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w4a16", "repoId": "neuralmagic/gemma-2-9b-it-quantized.w4a16", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
|
||||
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268918+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670785+00:00", "framework": "vllm_fix_tokenizer", "intentId": "157e9942a18f48e483882f1df3f63e0c", "repoId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268915+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670730+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2dc6833c4bbf4be9befa6f9639bfe7c8", "repoId": "aisingapore/Llama-SEA-LION-v3-8B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
||||
{"batchId": "d0b54aed500a4a4aa2ac0619a84d4c95", "completedAt": "2026-09-20T21:55:24.268913+00:00", "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configSource": "modelhub_live", "createdAt": "2026-09-20T21:49:55.670676+00:00", "framework": "vllm_fix_tokenizer", "intentId": "480abb8f7bd342c096c3270e01d123d9", "repoId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-bf16", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Sunrise_pt-200-x1", "taskId": null, "taskType": "text-generation"}
|
||||
|
||||
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.20.2",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "341c4c14f80db8a73751efc3ee9ace03e16121e1d71093584150a8f6b7c46920",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "d9231cd52f33dbe483d29005cb241a54b9246424af0cad5e57c1d1f644990fe4",
|
||||
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
|
||||
".modelhub_state/market_intelligence.json": "8e9e8ca54bff8decb2ffd27d4f751787c88b55c53bbdeab17ec36ca649fc476e",
|
||||
".modelhub_state/official_capabilities.json": "c1a6cd53672471e8d38e212fc189c6a6fba531af684f67e92fdce39fab08163a",
|
||||
".modelhub_state/outcome_checkpoint.json": "c6279287ea33d10bc1444d62e01a6bbbdc72b6a2c636e38947c238ab52a09cc2",
|
||||
".modelhub_state/queue_cleanup_latest.json": "1f1e66dec2bd0f5cb8c9814b5cd984748f1c731476a4db5a0546c0671766809d",
|
||||
".modelhub_state/recent_outcomes.jsonl": "e99fa0a2754f761f473a4e9a2172876aa8970850adf7acbd75179341aed18bd0",
|
||||
".modelhub_state/market_intelligence.json": "299395048a959bb38b0b77509437a4a27b86c62ce305ac9a2f52d92fb0fc5105",
|
||||
".modelhub_state/official_capabilities.json": "36ac98d996879f442e5cfd572949a114936cff0d760c3f5ec1c9b349074e3f8c",
|
||||
".modelhub_state/outcome_checkpoint.json": "316ec09ef49eba67ab800323b7098f564abdcc5b047fe0459cd1220df82738a3",
|
||||
".modelhub_state/queue_cleanup_latest.json": "acef5f83c30f7eb3ffae08f106b386239fe407d64362fb7038dd02f4f9164a98",
|
||||
".modelhub_state/recent_outcomes.jsonl": "f99ab670874d94e52bc68ef13a7aa0866101b1ed607f1c4b6128bb4b7da22eb3",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "3f0443fc49a5c692cce608ec6ff4b36da8947b6e0676ba065c73fa14f73c5583",
|
||||
".modelhub_state/recovery_intents.jsonl": "bdbaebdd37505be4731db9518def0db08fb33b3cdb218a6621b77313ba82f0aa",
|
||||
".modelhub_state/recovery_intents.jsonl": "0e962ae792aba2fa5458bbe56c48f2b103509dbc99fae0118398d95211256485",
|
||||
".modelhub_state/routing_intelligence.json": "0a8a7243e0bc4eecdaefff700cf8a1dbbb6209a3bd0122776990bebd546d767e",
|
||||
".modelhub_state/submission_exclusions.jsonl": "80315f370e9cc3cdadaf390e12573ef887794214779379c50b7b37b7631e8989",
|
||||
".modelhub_state/worker_crashes.jsonl": "a494412048eca6dce83e7284303a6b4b56a445c1274ac201ab8723c739a14f23",
|
||||
"ledger/submissions.jsonl": "bc557895dd81f01e317101d6ce5ab19f0c4d11fe60240413c31aa49cc3bbb016",
|
||||
"outcomes/submissions.jsonl": "043912e49caefc7799a9b5e0633504b7be402761b5ee20a557594c317226abdf"
|
||||
"outcomes/submissions.jsonl": "406c903f9a6a8ddf2874682dec576d84122aab589b9ba39148cbfd208819d91e"
|
||||
},
|
||||
"generation": 10930,
|
||||
"phase": "cycle",
|
||||
"generation": 10931,
|
||||
"phase": "intent",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-20T21:55:26.094042+00:00",
|
||||
"updatedAt": "2026-09-20T21:57:31.753159+00:00",
|
||||
"writerId": "fc715c06e24c4db2ae3e425e435db996"
|
||||
}
|
||||
|
||||
@@ -417,9 +417,7 @@
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T02:19:35.596180+00:00", "modelId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3040272206, "estimatedRequiredGiB": 3.409, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3050595322, "modelscopeLicense": "apache-2.0", "modelscopeParams": 824389120, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:spark2_5", "custom_tag:long-context"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3050595322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T18:15:01.430761+00:00", "targetGpu": "Biren_166m", "taskId": "4961485", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-20T11:00:25.647717+00:00", "modelId": "chenqi2026/7a-8elite", "modelProfile": {"architectures": [], "configFingerprint": "48d3a9b2a54c7767b8326d72b3ed023e1469b86b36badd5ea46d40b3b79e65cd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 89208224, "estimatedRequiredGiB": 3.907, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3496327232, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 79009792, "modelscopeTags": ["license:Apache License 2.0", "library:gguf", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3496327232}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:43.741402+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4968996", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647569+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:43.745571+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969000", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647722+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "2026-09-20T02:52:43.738452+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4968995", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647473+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:43.835992+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969002", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647799+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "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": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:43.767336+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969004", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647845+00:00", "modelId": "SyonLi/Qwen3-4B-Instruct-2507-Segmenter", "modelProfile": {"architectures": ["Qwen3ForCut"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8046243744, "estimatedRequiredGiB": 9.01, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8062181376, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4023098880, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8062181376}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.837922+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969007", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647704+00:00", "modelId": "mlx-community/KAT-Coder-V2.5-Dev-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21930054875, "estimatedRequiredGiB": 24.532, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21950415614, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6024588416, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21950415614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.869403+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969009", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647374+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:50.900575+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969014", "taskType": "text-generation", "verifyResult": null}
|
||||
@@ -937,7 +935,7 @@
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T21:33:11.158023+00:00", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161034, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "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", "repositoryOnDiskBytes": 4404161034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:19:23.910185+00:00", "targetGpu": "Vastai_va16", "taskId": "4979588", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "RedHatAI/starcoder2-7b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "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": "pending", "submitTime": "2026-09-20T13:22:06.962643+00:00", "targetGpu": "Biren_166m", "taskId": "4979624", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T21:33:11.158043+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "6db01b5037d5ed2db74875d2113f8582c97f34bd825637161e54174c9f2cabed", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:23:33.095200+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4979625", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504988}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T13:36:07.724905+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4979835", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T21:55:28.960225+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504988, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504988}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:36:07.724905+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4979835", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "pending", "submitTime": "2026-09-20T14:01:30.719848+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980119", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "neuralmagic/gemma-2-2b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3403624536, "estimatedRequiredGiB": 3.828, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 3425449487, "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": 3425449487}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:22:01.079527+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4980340", "taskType": "text-generation", "verifyResult": null}
|
||||
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1232060880, "estimatedRequiredGiB": 1.379, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233909203, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233909203}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-20T14:22:13.035851+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4980360", "taskType": "text-generation", "verifyResult": null}
|
||||
|
||||
Reference in New Issue
Block a user