CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 21953 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 19:13:52 +00:00
parent a5775d5d25
commit e01ed26af2
11 changed files with 3610 additions and 3037 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -61,6 +61,25 @@
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-21T19:37:12.447446+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-09-21T19:37:12.447446+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "mini_k3",
"sourceModelIds": [
"nkkbr/Mini-K3-1H-attnres-block6-v1_C"
],
"sourceTaskIds": [
"5006364"
],
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation"
},
"ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:muse_glimmer": { "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:muse_glimmer": {
"architectureSignature": "model_type:muse_glimmer", "architectureSignature": "model_type:muse_glimmer",
"architectures": [], "architectures": [],
@@ -2817,12 +2836,12 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-07T18:41:57.358280+00:00", "generatedAt": "2026-10-07T19:02:02.565000+00:00",
"summary": { "summary": {
"activeBlockCount": 142, "activeBlockCount": 143,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 9, "Ascend_910-b3|vllm": 9,
"Ascend_910-b3|vllm_tokenizer_patch": 7, "Ascend_910-b3|vllm_tokenizer_patch": 8,
"Ascend_910-b4|vllm": 10, "Ascend_910-b4|vllm": 10,
"Ascend_910-b4|vllm_tokenizer_patch": 7, "Ascend_910-b4|vllm_tokenizer_patch": 7,
"Biren_166m|vllm": 3, "Biren_166m|vllm": 3,

296
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-10-07T18:49:24.762308+00:00", "communityAttemptedAt": "2026-10-07T19:06:20.402129+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-10-07T18:49:24.762308+00:00", "communityUpdatedAt": "2026-10-07T19:06:20.402129+00:00",
"frameworkAttemptedAt": "2026-10-07T14:52:53.254460+00:00", "frameworkAttemptedAt": "2026-10-07T14:52:53.254460+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -434,121 +434,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-07T18:58:08.044886+00:00", "generatedAt": "2026-10-07T19:06:20.402129+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1034.2641509433963, "backlogHours": 1007.9263803680981,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b3", "gpu": "Ascend_910-b3",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 1.2194086164724065, "qualityFactor": 1.288938594572344,
"queueFactor": 0.9978424875333087, "queueFactor": 1.0018938730251956,
"queueWeight": 0.9978424875333087, "queueWeight": 1.0018938730251956,
"recentSuccess": 44, "recentSuccess": 45,
"recentSuccessRate": 0.27672955974842767, "recentSuccessRate": 0.27607361963190186,
"recentTerminal": 159, "recentTerminal": 163,
"recentWilsonLowerBound": 0.21308016641771516, "recentWilsonLowerBound": 0.21319744025496024,
"running": 10, "running": 8,
"selectionWeight": 1.2167777271803766, "selectionWeight": 1.291379680607738,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.5, "throughputPerHour": 27.166666666666668,
"waiting": 27408 "waiting": 27382
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1100.3190184049079, "backlogHours": 1164.3506493506493,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b4", "gpu": "Ascend_910-b4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 2.0415014031757712, "qualityFactor": 1.9238418980605791,
"queueFactor": 0.9886189249257661, "queueFactor": 0.9804455373220654,
"queueWeight": 0.9886189249257661, "queueWeight": 0.9804455373220654,
"recentSuccess": 55, "recentSuccess": 50,
"recentSuccessRate": 0.3374233128834356, "recentSuccessRate": 0.3246753246753247,
"recentTerminal": 163, "recentTerminal": 154,
"recentWilsonLowerBound": 0.26932116996770256, "recentWilsonLowerBound": 0.255766892716209,
"running": 8, "running": 8,
"selectionWeight": 2.018266922442074, "selectionWeight": 1.8862222034667067,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 27.166666666666668, "throughputPerHour": 25.666666666666668,
"waiting": 29892 "waiting": 29885
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 140.50267379679144, "backlogHours": 141.85945945945946,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.36992665566335803, "qualityFactor": 0.4001160835715028,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 32, "recentSuccess": 32,
"recentSuccessRate": 0.1711229946524064, "recentSuccessRate": 0.17297297297297298,
"recentTerminal": 187, "recentTerminal": 185,
"recentWilsonLowerBound": 0.1239005385256487, "recentWilsonLowerBound": 0.12527138719559175,
"running": 9, "running": 8,
"selectionWeight": 0.48090465236236546, "selectionWeight": 0.5201509086429537,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 31.166666666666668, "throughputPerHour": 30.833333333333332,
"waiting": 4379 "waiting": 4374
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1044.061224489796, "backlogHours": 1033.5151515151515,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x4", "gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.24672845833144288, "qualityFactor": 0.21282420828790807,
"queueFactor": 0.9964323475047329, "queueFactor": 0.9981332321725974,
"queueWeight": 0.9964323475047329, "queueWeight": 0.9981332321725974,
"recentSuccess": 16, "recentSuccess": 15,
"recentSuccessRate": 0.16326530612244897, "recentSuccessRate": 0.15151515151515152,
"recentTerminal": 98, "recentTerminal": 99,
"recentWilsonLowerBound": 0.10306715625004181, "recentWilsonLowerBound": 0.09402242321177301,
"running": 7, "running": 7,
"selectionWeight": 0.2458482169314233, "selectionWeight": 0.2124269149029838,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.333333333333332, "throughputPerHour": 16.5,
"waiting": 17053 "waiting": 17053
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 415.5111111111111, "backlogHours": 438.140625,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x8", "gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.6521931792776154, "qualityFactor": 0.6474397397738088,
"queueFactor": 1.1441140437295805, "queueFactor": 1.1352565440896367,
"queueWeight": 1.1441140437295805, "queueWeight": 1.1352565440896367,
"recentSuccess": 30, "recentSuccess": 28,
"recentSuccessRate": 0.2222222222222222, "recentSuccessRate": 0.21875,
"recentTerminal": 135, "recentTerminal": 128,
"recentWilsonLowerBound": 0.1603281725224173, "recentWilsonLowerBound": 0.1559042491230976,
"running": 8, "running": 7,
"selectionWeight": 0.7461833756361639, "selectionWeight": 0.7350102014819079,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.5, "throughputPerHour": 21.333333333333332,
"waiting": 9349 "waiting": 9347
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 90.24657534246575, "backlogHours": 114.10404624277457,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -558,196 +558,196 @@
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 8, "recentSuccess": 8,
"recentSuccessRate": 0.0365296803652968, "recentSuccessRate": 0.046242774566473986,
"recentTerminal": 219, "recentTerminal": 173,
"recentWilsonLowerBound": 0.01862407328502234, "recentWilsonLowerBound": 0.023615152637950033,
"running": 27, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 36.5, "throughputPerHour": 28.833333333333332,
"waiting": 3294 "waiting": 3290
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 179.1627906976744, "backlogHours": 230.5868263473054,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-150", "gpu": "Iluvatar_bi-150",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 50, "maxConcurrentTasks": 50,
"qualityFactor": 0.2703605772835014, "qualityFactor": 0.3892589582470699,
"queueFactor": 1.2979846005368254, "queueFactor": 1.2500024630207098,
"queueWeight": 1.2979846005368254, "queueWeight": 1.2500024630207098,
"recentSuccess": 32, "recentSuccess": 29,
"recentSuccessRate": 0.14883720930232558, "recentSuccessRate": 0.17365269461077845,
"recentTerminal": 215, "recentTerminal": 167,
"recentWilsonLowerBound": 0.10744265007546998, "recentWilsonLowerBound": 0.12371468491228088,
"running": 2, "running": 6,
"selectionWeight": 0.35092386590623104, "selectionWeight": 0.48657465656171306,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 35.833333333333336, "throughputPerHour": 27.833333333333332,
"waiting": 6420 "waiting": 6418
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2736.705882352941, "backlogHours": 2735.8235294117644,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_mrv-100", "gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 1.2421473353964052, "qualityFactor": 1.3113854816370532,
"queueFactor": 0.8623280117525993, "queueFactor": 0.8625272614690882,
"queueWeight": 0.8623280117525993, "queueWeight": 0.8625272614690882,
"recentSuccess": 12, "recentSuccess": 12,
"recentSuccessRate": 0.35294117647058826, "recentSuccessRate": 0.35294117647058826,
"recentTerminal": 34, "recentTerminal": 34,
"recentWilsonLowerBound": 0.2148771489529607, "recentWilsonLowerBound": 0.2148771489529607,
"running": 2, "running": 2,
"selectionWeight": 1.0711384420361711, "selectionWeight": 1.1311057282067287,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 5.666666666666667, "throughputPerHour": 5.666666666666667,
"waiting": 15508 "waiting": 15503
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 384.9166666666667, "backlogHours": 398.71942446043164,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.5152331984677884, "qualityFactor": 0.5370651246434119,
"queueFactor": 1.1573153284447588, "queueFactor": 1.1514257390723857,
"queueWeight": 1.1573153284447588, "queueWeight": 1.1514257390723857,
"recentSuccess": 29, "recentSuccess": 28,
"recentSuccessRate": 0.2013888888888889, "recentSuccessRate": 0.2014388489208633,
"recentTerminal": 144, "recentTerminal": 139,
"recentWilsonLowerBound": 0.144037948396581, "recentWilsonLowerBound": 0.1432060631755529,
"running": 10, "running": 8,
"selectionWeight": 0.5962872783103921, "selectionWeight": 0.6183906080725435,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.0, "throughputPerHour": 23.166666666666668,
"waiting": 9238 "waiting": 9237
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 636.5825242718446, "backlogHours": 636.5242718446601,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "MetaX_c-500", "gpu": "MetaX_c-500",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 0.5939733819153186, "qualityFactor": 0.7032459212447805,
"queueFactor": 1.0731946671700847, "queueFactor": 1.0734054530522665,
"queueWeight": 1.0731946671700847, "queueWeight": 1.0734054530522665,
"recentSuccess": 23, "recentSuccess": 24,
"recentSuccessRate": 0.22330097087378642, "recentSuccessRate": 0.23300970873786409,
"recentTerminal": 103, "recentTerminal": 103,
"recentWilsonLowerBound": 0.1536565519868537, "recentWilsonLowerBound": 0.16187497360880485,
"running": 4, "running": 4,
"selectionWeight": 0.6374490659125, "selectionWeight": 0.7548680067009121,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.166666666666668, "throughputPerHour": 17.166666666666668,
"waiting": 10928 "waiting": 10927
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1554.642857142857, "backlogHours": 1573.6626506024095,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Mthreads_s4000", "gpu": "Mthreads_s4000",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.9386682263589574, "queueFactor": 0.9371288259940411,
"queueWeight": 0.9386682263589574, "queueWeight": 0.9371288259940411,
"recentSuccess": 33, "recentSuccess": 32,
"recentSuccessRate": 0.39285714285714285, "recentSuccessRate": 0.3855421686746988,
"recentTerminal": 84, "recentTerminal": 83,
"recentWilsonLowerBound": 0.2953018006281275, "recentWilsonLowerBound": 0.2881099453171214,
"running": 4, "running": 4,
"selectionWeight": 2.3466705658973934, "selectionWeight": 2.3428220649851026,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.0, "throughputPerHour": 13.833333333333334,
"waiting": 21765 "waiting": 21769
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 2632.3076923076924, "backlogHours": 2503.609756097561,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Sunrise_pt-200-x1", "gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.11369779988728158, "qualityFactor": 0.1715756487756158,
"queueFactor": 0.8673736305466752, "queueFactor": 0.8740797264612077,
"queueWeight": 0.8673736305466752, "queueWeight": 0.8740797264612077,
"recentSuccess": 6, "recentSuccess": 7,
"recentSuccessRate": 0.15384615384615385, "recentSuccessRate": 0.17073170731707318,
"recentTerminal": 39, "recentTerminal": 41,
"recentWilsonLowerBound": 0.07247373845051468, "recentWilsonLowerBound": 0.08525143995273898,
"running": 2, "running": 2,
"selectionWeight": 0.09861847347340078, "selectionWeight": 0.1499707961491945,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.5, "throughputPerHour": 6.833333333333333,
"waiting": 17110 "waiting": 17108
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1458.5142857142857, "backlogHours": 1379.1891891891892,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Vastai_va16", "gpu": "Vastai_va16",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 16, "maxConcurrentTasks": 16,
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 0.9476983176284866, "queueFactor": 0.9558559896578388,
"queueWeight": 0.9476983176284866, "queueWeight": 0.9558559896578388,
"recentSuccess": 1, "recentSuccess": 1,
"recentSuccessRate": 0.014285714285714285, "recentSuccessRate": 0.013513513513513514,
"recentTerminal": 70, "recentTerminal": 74,
"recentWilsonLowerBound": 0.002526181403234866, "recentWilsonLowerBound": 0.002389401874939327,
"running": 17, "running": 16,
"selectionWeight": 0.04738491588142433, "selectionWeight": 0.047792799482891946,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 11.666666666666666, "throughputPerHour": 12.333333333333334,
"waiting": 17016 "waiting": 17010
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 1004.6929133858267, "backlogHours": 1037.121951219512,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "hygon_k100-ai", "gpu": "hygon_k100-ai",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 6, "maxConcurrentTasks": 6,
"qualityFactor": 0.414021761527445, "qualityFactor": 0.419233772691239,
"queueFactor": 1.0021938005056028, "queueFactor": 0.9976117796477567,
"queueWeight": 1.0021938005056028, "queueWeight": 0.9976117796477567,
"recentSuccess": 24, "recentSuccess": 23,
"recentSuccessRate": 0.1889763779527559, "recentSuccessRate": 0.18699186991869918,
"recentTerminal": 127, "recentTerminal": 123,
"recentWilsonLowerBound": 0.1304078981380311, "recentWilsonLowerBound": 0.12795746795510443,
"running": 7, "running": 6,
"selectionWeight": 0.4149300426772145, "selectionWeight": 0.41823255006295007,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 21.166666666666668, "throughputPerHour": 20.5,
"waiting": 21266 "waiting": 21261
} }
}, },
"queueAttemptedAt": "2026-10-07T18:49:24.762308+00:00", "queueAttemptedAt": "2026-10-07T19:06:20.402129+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-07T18:49:24.762308+00:00", "queueUpdatedAt": "2026-10-07T19:06:20.402129+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",

1548
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

197
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-07T18:22:59.673964+00:00", "generatedAt": "2026-10-07T19:06:20.299856+00:00",
"lastSyncTime": "2026-10-07T18:22:59.552965+00:00", "lastSyncTime": "2026-10-07T19:06:20.160304+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -65,6 +65,25 @@
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-10-21T19:37:12.447446+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-09-21T19:37:12.447446+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "mini_k3",
"sourceModelIds": [
"nkkbr/Mini-K3-1H-attnres-block6-v1_C"
],
"sourceTaskIds": [
"5006364"
],
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation"
},
"ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:muse_glimmer": { "ascend_910-b3|vllm_tokenizer_patch|text-generation|model_type:muse_glimmer": {
"architectureSignature": "model_type:muse_glimmer", "architectureSignature": "model_type:muse_glimmer",
"architectures": [], "architectures": [],
@@ -2822,10 +2841,10 @@
} }
}, },
"architectureCompatibilitySummary": { "architectureCompatibilitySummary": {
"activeBlockCount": 142, "activeBlockCount": 143,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 9, "Ascend_910-b3|vllm": 9,
"Ascend_910-b3|vllm_tokenizer_patch": 7, "Ascend_910-b3|vllm_tokenizer_patch": 8,
"Ascend_910-b4|vllm": 10, "Ascend_910-b4|vllm": 10,
"Ascend_910-b4|vllm_tokenizer_patch": 7, "Ascend_910-b4|vllm_tokenizer_patch": 7,
"Biren_166m|vllm": 3, "Biren_166m|vllm": 3,
@@ -2942,29 +2961,29 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": { "Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 47, "attributableFailureCount": 48,
"decisionFailureRate": 0.9216, "decisionFailureRate": 0.9231,
"decisionSuccessRate": 0.0784, "decisionSuccessRate": 0.0769,
"decisionTotal": 51, "decisionTotal": 52,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 93, "ambiguous_runtime": 93,
"context_length": 9, "context_length": 9,
"framework_architecture_unsupported": 37, "framework_architecture_unsupported": 38,
"memory_capacity": 1, "memory_capacity": 1,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"参数/模板问题": 8 "参数/模板问题": 8
}, },
"failureCount": 149, "failureCount": 150,
"failureRate": 0.9739, "failureRate": 0.974,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 4, "successCount": 4,
"successRate": 0.0261, "successRate": 0.026,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 153, "total": 154,
"unresolvedFailureCount": 101 "unresolvedFailureCount": 101
}, },
"Ascend_910-b3|vllm|text-generation": { "Ascend_910-b3|vllm|text-generation": {
@@ -5693,15 +5712,15 @@
"unresolvedFailureCount": 387 "unresolvedFailureCount": 387
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"attributableFailureCount": 157, "attributableFailureCount": 158,
"decisionFailureRate": 0.9401, "decisionFailureRate": 0.9405,
"decisionSuccessRate": 0.0599, "decisionSuccessRate": 0.0595,
"decisionTotal": 167, "decisionTotal": 168,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 208, "ambiguous_runtime": 208,
"backend_operator": 15, "backend_operator": 15,
"context_length": 9, "context_length": 9,
"framework_architecture_unsupported": 99, "framework_architecture_unsupported": 100,
"memory_capacity": 2, "memory_capacity": 2,
"model_load": 24, "model_load": 24,
"platform_infrastructure": 3, "platform_infrastructure": 3,
@@ -5710,28 +5729,28 @@
"tokenizer_compatibility": 2, "tokenizer_compatibility": 2,
"参数/模板问题": 49 "参数/模板问题": 49
}, },
"failureCount": 417, "failureCount": 418,
"failureRate": 0.9766, "failureRate": 0.9766,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 3, "platformFailureCount": 3,
"successCount": 10, "successCount": 10,
"successRate": 0.0234, "successRate": 0.0234,
"total": 427, "total": 428,
"unresolvedFailureCount": 257 "unresolvedFailureCount": 257
} }
}, },
"generatedAt": "2026-10-07T18:22:59.655554+00:00", "generatedAt": "2026-10-07T19:06:20.276551+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 119, "attributableFailureCount": 120,
"decisionFailureRate": 0.844, "decisionFailureRate": 0.8451,
"decisionSuccessRate": 0.156, "decisionSuccessRate": 0.1549,
"decisionTotal": 141, "decisionTotal": 142,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 162, "ambiguous_runtime": 162,
"context_length": 9, "context_length": 9,
"framework_architecture_unsupported": 104, "framework_architecture_unsupported": 105,
"memory_capacity": 2, "memory_capacity": 2,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"repository_structure": 1, "repository_structure": 1,
@@ -5740,14 +5759,14 @@
"日志缺失": 3, "日志缺失": 3,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 352, "failureCount": 353,
"failureRate": 0.9412, "failureRate": 0.9413,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 22, "successCount": 22,
"successRate": 0.0588, "successRate": 0.0587,
"total": 374, "total": 375,
"unresolvedFailureCount": 232 "unresolvedFailureCount": 232
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
@@ -6162,7 +6181,7 @@
"hygon_k100-ai": 64.0 "hygon_k100-ai": 64.0
}, },
"pendingRecords": 0, "pendingRecords": 0,
"policyCancelledRecords": 291, "policyCancelledRecords": 315,
"profileCombinationStats": { "profileCombinationStats": {
"Ascend_910-b3|llamacpp|text-generation|smollm3|none": { "Ascend_910-b3|llamacpp|text-generation|smollm3|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -6553,6 +6572,29 @@
"total": 3, "total": 3,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 2
}, },
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mini_k3|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": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none": { "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -25314,18 +25356,18 @@
"unresolvedFailureCount": 3 "unresolvedFailureCount": 3
}, },
"Ascend_910-b3|vllm_tokenizer_patch|text-generation": { "Ascend_910-b3|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 5, "attributableFailureCount": 6,
"consecutiveFailures": 5, "consecutiveFailures": 6,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 5, "decisionTotal": 6,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 14, "ambiguous_runtime": 14,
"context_length": 3, "context_length": 3,
"framework_architecture_unsupported": 2 "framework_architecture_unsupported": 3
}, },
"failureCount": 19, "failureCount": 20,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -25337,7 +25379,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 19, "total": 20,
"unresolvedFailureCount": 14 "unresolvedFailureCount": 14
}, },
"Ascend_910-b3|vllm|text-generation": { "Ascend_910-b3|vllm|text-generation": {
@@ -25452,9 +25494,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 13 "ambiguous_runtime": 12
}, },
"failureCount": 13, "failureCount": 12,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -25466,8 +25508,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 13, "total": 12,
"unresolvedFailureCount": 13 "unresolvedFailureCount": 12
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -26253,6 +26295,31 @@
"total": 8, "total": 8,
"unresolvedFailureCount": 5 "unresolvedFailureCount": 5
}, },
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mini_k3|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": "2026-10-07T19:02:02.168317+00:00",
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": { "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"consecutiveFailures": 0, "consecutiveFailures": 0,
@@ -26710,9 +26777,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 5 "ambiguous_runtime": 4
}, },
"failureCount": 5, "failureCount": 4,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-07T11:42:31.164621+00:00", "lastTerminalAt": "2026-10-07T11:42:31.164621+00:00",
@@ -26725,8 +26792,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 5, "total": 4,
"unresolvedFailureCount": 5 "unresolvedFailureCount": 4
}, },
"Biren_166m|vllm_fix_tokenizer|text-generation|smollm3|none": { "Biren_166m|vllm_fix_tokenizer|text-generation|smollm3|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -30145,6 +30212,30 @@
"total": 2, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mini_k3|none|30": {
"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": 30,
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Ascend_910-b3",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none|34": { "Ascend_910-b3|vllm_tokenizer_patch|text-generation|mistral3|none|34": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -58608,20 +58699,20 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17420, "terminalRecords": 17421,
"totalRecords": 17711, "totalRecords": 17736,
"totals": { "totals": {
"attributableFailureCount": 6254, "attributableFailureCount": 6255,
"decisionFailureRate": 0.8648, "decisionFailureRate": 0.8648,
"decisionSuccessRate": 0.1352, "decisionSuccessRate": 0.1352,
"decisionTotal": 7232, "decisionTotal": 7233,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4573, "ambiguous_runtime": 4573,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 129, "backend_operator": 129,
"context_length": 327, "context_length": 327,
"framework_architecture_unsupported": 2273, "framework_architecture_unsupported": 2274,
"memory_capacity": 1206, "memory_capacity": 1206,
"model_load": 571, "model_load": 571,
"platform_infrastructure": 954, "platform_infrastructure": 954,
@@ -58632,14 +58723,14 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16442, "failureCount": 16443,
"failureRate": 0.9439, "failureRate": 0.9439,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 954, "platformFailureCount": 954,
"successCount": 978, "successCount": 978,
"successRate": 0.0561, "successRate": 0.0561,
"total": 17420, "total": 17421,
"unresolvedFailureCount": 9234 "unresolvedFailureCount": 9234
}, },
"warnings": [ "warnings": [
@@ -58701,6 +58792,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17711, "summarizedRecords": 17736,
"version": 1 "version": 1
} }

1000
.modelhub_state/queue_cleanup_latest.json
View File

File diff suppressed because it is too large Load Diff

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -105,6 +105,7 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T13:29:11.757302+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:12:49.394711+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006730", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T13:29:11.757302+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:12:49.394711+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006730", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-25T01:41:30.953868+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 4, "model_load": 1}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:49:53.770533+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-25T01:41:30.953868+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 4, "model_load": 1}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:49:53.770533+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164621+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.653471+00:00", "targetGpu": "Biren_166m", "taskId": "5006368", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164621+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.653471+00:00", "targetGpu": "Biren_166m", "taskId": "5006368", "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": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T19:02:02.168317+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.447446+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006364", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T09:53:21.160613+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 3, "consecutiveFailures": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": {"memory_capacity": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-20T12:21:49.901832+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.849661+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006201", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T09:53:21.160613+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 3, "consecutiveFailures": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": {"memory_capacity": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-20T12:21:49.901832+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.849661+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006201", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T13:06:44.750866+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 35256868927}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.848154+00:00", "targetGpu": "Biren_166m", "taskId": "5006202", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T13:06:44.750866+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 35256868927}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.848154+00:00", "targetGpu": "Biren_166m", "taskId": "5006202", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T14:46:46.372736+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35256868927}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:05:50.963205+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006057", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T14:46:46.372736+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35256868927}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:05:50.963205+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006057", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-21T18:39:29.750819+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142065, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-09-20T12:58:28.353096+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 16568142065}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:05:59.142974+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4997663", "taskType": "text-generation", "verifyResult": -1} {"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-21T18:39:29.750819+00:00", "modelId": "RedHatAI/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142065, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-09-20T12:58:28.353096+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 16568142065}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:05:59.142974+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4997663", "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": "2026-09-30T11:55:48.444086+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084014480, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093198689, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093198689}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:02:30.537080+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997592", "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": "2026-09-30T11:55:48.444086+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084014480, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093198689, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093198689}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:02:30.537080+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997592", "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": "2026-09-23T05:26:10.454831+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219876272, "estimatedRequiredGiB": 0.25, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223261617, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223261617}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:02:30.534692+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997591", "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": "2026-09-23T05:26:10.454831+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219876272, "estimatedRequiredGiB": 0.25, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223261617, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223261617}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:02:30.534692+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997591", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T23:26:35.259297+00:00", "modelId": "blue2star/Qwen-Image-2.1-PE-I2I-ComfyUI", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29306922460, "estimatedRequiredGiB": 32.775, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29326959151, "modelscopeLicense": "other", "modelscopeParams": 18821595084, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:prompt-rewriting", "custom_tag:image-editing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29326959151}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:59:28.154388+00:00", "targetGpu": "Biren_166m", "taskId": "4997528", "taskType": "text-generation", "verifyResult": -1}

1496
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2006
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

28
ledger/submissions.jsonl
View File

@@ -216,16 +216,6 @@
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "submitTime": "2026-09-21T19:05:50.750203+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006047", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "submitTime": "2026-09-21T19:05:50.750203+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006047", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "submitTime": "2026-09-21T19:21:51.641656+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006191", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "submitTime": "2026-09-21T19:21:51.641656+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006191", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "submitTime": "2026-09-21T19:21:51.638009+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006194", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "submitTime": "2026-09-21T19:21:51.638009+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006194", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "submitTime": "2026-09-21T19:21:51.651884+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006196", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "submitTime": "2026-09-21T19:21:51.643154+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006186", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "submitTime": "2026-09-21T19:21:51.645382+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006189", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "submitTime": "2026-09-21T19:21:51.649992+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006193", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g64-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g64-v2_B", "submitTime": "2026-09-21T19:21:51.659014+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006195", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "submitTime": "2026-09-21T19:21:51.675420+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006197", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "submitTime": "2026-09-21T19:21:51.846176+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006199", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "submitTime": "2026-09-21T19:21:51.789058+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006198", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "submitTime": "2026-09-21T19:21:51.844977+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006200", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "submitTime": "2026-09-21T19:37:12.451588+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006358", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "submitTime": "2026-09-21T19:37:12.445928+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006361", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "submitTime": "2026-09-21T19:37:12.445928+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006361", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "submitTime": "2026-09-21T19:37:12.453443+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006363", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "submitTime": "2026-09-21T19:37:12.453443+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006363", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "submitTime": "2026-09-21T19:37:12.455102+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006362", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "submitTime": "2026-09-21T19:37:12.455102+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006362", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
@@ -250,7 +240,6 @@
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "submitTime": "2026-09-21T20:37:39.959415+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5007016", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "submitTime": "2026-09-21T20:37:39.959415+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5007016", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "submitTime": "2026-09-21T20:40:49.946575+00:00", "targetGpu": "Biren_166m", "taskId": "5007047", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "submitTime": "2026-09-21T20:40:49.946575+00:00", "targetGpu": "Biren_166m", "taskId": "5007047", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "submitTime": "2026-09-21T20:46:16.651713+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007123", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "submitTime": "2026-09-21T20:46:16.651713+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007123", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "submitTime": "2026-09-21T21:04:43.408226+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5007290", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "submitTime": "2026-09-21T21:06:49.754370+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5007313", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "submitTime": "2026-09-21T21:06:49.754370+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5007313", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "submitTime": "2026-09-21T21:06:49.752998+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5007314", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "submitTime": "2026-09-21T21:06:49.752998+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5007314", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "submitTime": "2026-09-21T21:10:26.048602+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007347", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "submitTime": "2026-09-21T21:10:26.048602+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007347", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
@@ -282,12 +271,10 @@
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "submitTime": "2026-09-21T23:44:30.789761+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009101", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "submitTime": "2026-09-21T23:44:30.789761+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009101", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "submitTime": "2026-09-21T23:46:25.882874+00:00", "targetGpu": "MetaX_c-500", "taskId": "5009122", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "submitTime": "2026-09-21T23:46:25.882874+00:00", "targetGpu": "MetaX_c-500", "taskId": "5009122", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "submitTime": "2026-09-21T23:50:56.149099+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5009164", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "submitTime": "2026-09-21T23:50:56.149099+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5009164", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "submitTime": "2026-09-21T23:50:56.150801+00:00", "targetGpu": "MetaX_c-500", "taskId": "5009165", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "submitTime": "2026-09-21T23:54:44.050989+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009242", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "submitTime": "2026-09-21T23:54:44.050989+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009242", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "submitTime": "2026-09-21T23:58:44.401705+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5009282", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "submitTime": "2026-09-21T23:58:44.401705+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5009282", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "submitTime": "2026-09-22T00:00:45.685170+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5009297", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "submitTime": "2026-09-22T00:00:45.685170+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5009297", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "submitTime": "2026-09-22T00:04:31.388498+00:00", "targetGpu": "Vastai_va16", "taskId": "5009346", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "submitTime": "2026-09-22T00:04:31.388498+00:00", "targetGpu": "Vastai_va16", "taskId": "5009346", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "submitTime": "2026-09-22T00:10:30.409776+00:00", "targetGpu": "MetaX_c-500", "taskId": "5009394", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "submitTime": "2026-09-22T00:12:27.759306+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009429", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "submitTime": "2026-09-22T00:12:27.759306+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009429", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "submitTime": "2026-09-22T00:12:27.760772+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009428", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "submitTime": "2026-09-22T00:12:27.760772+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009428", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "submitTime": "2026-09-22T00:12:27.762342+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009427", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "submitTime": "2026-09-22T00:12:27.762342+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5009427", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
@@ -549,28 +536,18 @@
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-G1k-2.9B-20260930", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "submitTime": "2026-10-03T16:15:48.956404+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5260087", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-G1k-2.9B-20260930", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "submitTime": "2026-10-03T16:15:48.956404+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5260087", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/bench-labs/pulvis-v1", "modelId": "bench-labs/pulvis-v1", "submitTime": "2026-10-03T16:15:48.962708+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260089", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/bench-labs/pulvis-v1", "modelId": "bench-labs/pulvis-v1", "submitTime": "2026-10-03T16:15:48.962708+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260089", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "submitTime": "2026-10-03T16:15:48.954522+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260093", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "submitTime": "2026-10-03T16:15:48.954522+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260093", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "submitTime": "2026-10-03T16:15:48.964174+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260086", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "submitTime": "2026-10-03T16:15:48.958081+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260088", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/BananaMind/TernaryBananaMind-10M", "modelId": "BananaMind/TernaryBananaMind-10M", "submitTime": "2026-10-03T16:15:49.154928+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260094", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/BananaMind/TernaryBananaMind-10M", "modelId": "BananaMind/TernaryBananaMind-10M", "submitTime": "2026-10-03T16:15:49.154928+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260094", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "submitTime": "2026-10-03T16:15:49.244657+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260102", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/groxaxo/Hemmingway-1-AutoRound-W4G128", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "submitTime": "2026-10-03T16:15:49.161002+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260095", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/groxaxo/Hemmingway-1-AutoRound-W4G128", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "submitTime": "2026-10-03T16:15:49.161002+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260095", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "submitTime": "2026-10-03T16:15:49.256275+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260098", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "submitTime": "2026-10-03T16:15:49.265263+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260097", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "submitTime": "2026-10-03T16:15:49.262277+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260096", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Panyuqi/SpikingBrain-2.0-base-8k", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "submitTime": "2026-10-03T16:15:49.351950+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260104", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Panyuqi/SpikingBrain-2.0-base-8k", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "submitTime": "2026-10-03T16:15:49.351950+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260104", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "submitTime": "2026-10-03T16:15:49.252673+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260100", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "submitTime": "2026-10-03T16:15:49.252673+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260100", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "submitTime": "2026-10-03T16:15:49.272455+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260099", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "submitTime": "2026-10-03T16:15:49.272455+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260099", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlabonne/LFM2.5-230M-Chess", "modelId": "mlabonne/LFM2.5-230M-Chess", "submitTime": "2026-10-03T16:15:49.353284+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260101", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlabonne/LFM2.5-230M-Chess", "modelId": "mlabonne/LFM2.5-230M-Chess", "submitTime": "2026-10-03T16:15:49.353284+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260101", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ProCreations/Auto-Reason-3b", "modelId": "ProCreations/Auto-Reason-3b", "submitTime": "2026-10-03T16:15:49.356198+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260103", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ProCreations/Auto-Reason-3b", "modelId": "ProCreations/Auto-Reason-3b", "submitTime": "2026-10-03T16:15:49.356198+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260103", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "submitTime": "2026-10-03T16:15:49.446747+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260107", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "submitTime": "2026-10-03T16:15:49.469061+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260106", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-610m-fin-instruct", "modelId": "pfnet/plamo-3-610m-fin-instruct", "submitTime": "2026-10-03T16:15:49.464366+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260105", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-610m-fin-instruct", "modelId": "pfnet/plamo-3-610m-fin-instruct", "submitTime": "2026-10-03T16:15:49.464366+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260105", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/juspay/xor-lite", "modelId": "juspay/xor-lite", "submitTime": "2026-10-03T16:15:49.565606+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260116", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/juspay/xor-lite", "modelId": "juspay/xor-lite", "submitTime": "2026-10-03T16:15:49.565606+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260116", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/burtenshaw/nanochat", "modelId": "burtenshaw/nanochat", "submitTime": "2026-10-03T16:15:49.554250+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260109", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/burtenshaw/nanochat", "modelId": "burtenshaw/nanochat", "submitTime": "2026-10-03T16:15:49.554250+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260109", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B-INT4", "modelId": "hcnote/SparkMuse-4B-INT4", "submitTime": "2026-10-03T16:15:49.572421+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260112", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B-INT4", "modelId": "hcnote/SparkMuse-4B-INT4", "submitTime": "2026-10-03T16:15:49.572421+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260112", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "submitTime": "2026-10-03T16:15:49.563992+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260111", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "submitTime": "2026-10-03T16:15:49.563992+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260111", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "submitTime": "2026-10-03T16:15:49.560660+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260110", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "submitTime": "2026-10-03T16:15:49.555638+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260108", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "submitTime": "2026-10-03T16:15:49.674309+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260118", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "submitTime": "2026-10-03T16:15:49.674309+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260118", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/FINAL-Bench/Darwin-27B-RSI", "modelId": "FINAL-Bench/Darwin-27B-RSI", "submitTime": "2026-10-03T16:15:49.664837+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260117", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/FINAL-Bench/Darwin-27B-RSI", "modelId": "FINAL-Bench/Darwin-27B-RSI", "submitTime": "2026-10-03T16:15:49.664837+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260117", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "submitTime": "2026-10-03T16:15:49.651187+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260113", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "submitTime": "2026-10-03T16:15:49.651187+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260113", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
@@ -580,7 +557,6 @@
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/BananaMind/BananaMind-2-assistant2user", "modelId": "BananaMind/BananaMind-2-assistant2user", "submitTime": "2026-10-03T16:15:49.960990+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260120", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/BananaMind/BananaMind-2-assistant2user", "modelId": "BananaMind/BananaMind-2-assistant2user", "submitTime": "2026-10-03T16:15:49.960990+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260120", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "submitTime": "2026-10-03T16:15:49.751457+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260119", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "submitTime": "2026-10-03T16:15:49.751457+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260119", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/bench-labs/tinctura-v1", "modelId": "bench-labs/tinctura-v1", "submitTime": "2026-10-03T16:15:49.752368+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260114", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/bench-labs/tinctura-v1", "modelId": "bench-labs/tinctura-v1", "submitTime": "2026-10-03T16:15:49.752368+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260114", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "submitTime": "2026-10-03T16:15:50.052404+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260121", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/PleIAs/Baguettotron-MoE", "modelId": "PleIAs/Baguettotron-MoE", "submitTime": "2026-10-03T16:15:49.943304+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260126", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/PleIAs/Baguettotron-MoE", "modelId": "PleIAs/Baguettotron-MoE", "submitTime": "2026-10-03T16:15:49.943304+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260126", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/PleIAs/baguettotron-600m", "modelId": "PleIAs/baguettotron-600m", "submitTime": "2026-10-03T16:15:50.046146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260125", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/PleIAs/baguettotron-600m", "modelId": "PleIAs/baguettotron-600m", "submitTime": "2026-10-03T16:15:50.046146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260125", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Akahsizrr/Cyber-Prime-1.1-2.6B", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "submitTime": "2026-10-03T16:15:50.055568+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260122", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Akahsizrr/Cyber-Prime-1.1-2.6B", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "submitTime": "2026-10-03T16:15:50.055568+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260122", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
@@ -694,8 +670,6 @@
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3-Pro", "modelId": "webAI-Official/TwIL-LM3-Pro", "submitTime": "2026-10-06T09:13:59.665332+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320464", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"} {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3-Pro", "modelId": "webAI-Official/TwIL-LM3-Pro", "submitTime": "2026-10-06T09:13:59.665332+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320464", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM2", "modelId": "webAI-Official/TwIL-LM2", "submitTime": "2026-10-06T09:13:59.667635+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320463", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"} {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM2", "modelId": "webAI-Official/TwIL-LM2", "submitTime": "2026-10-06T09:13:59.667635+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320463", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/Hemmingway-1-OptiQ-4bit", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "submitTime": "2026-10-06T09:13:59.672848+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320456", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/Hemmingway-1-OptiQ-4bit", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "submitTime": "2026-10-06T09:13:59.672848+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320456", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "submitTime": "2026-10-06T09:13:59.677111+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320455", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "submitTime": "2026-10-06T09:13:59.676142+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320466", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-4bit-MLX", "modelId": "ukisai/Swift-1.5-4bit-MLX", "submitTime": "2026-10-06T09:13:59.662856+00:00", "targetGpu": "Biren_166m", "taskId": "5320459", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-4bit-MLX", "modelId": "ukisai/Swift-1.5-4bit-MLX", "submitTime": "2026-10-06T09:13:59.662856+00:00", "targetGpu": "Biren_166m", "taskId": "5320459", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "submitTime": "2026-10-06T09:13:59.670629+00:00", "targetGpu": "Biren_166m", "taskId": "5320460", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "submitTime": "2026-10-06T09:13:59.670629+00:00", "targetGpu": "Biren_166m", "taskId": "5320460", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "submitTime": "2026-10-06T09:13:59.674981+00:00", "targetGpu": "Biren_166m", "taskId": "5320465", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "submitTime": "2026-10-06T09:13:59.674981+00:00", "targetGpu": "Biren_166m", "taskId": "5320465", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
@@ -1088,6 +1062,8 @@
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "submitTime": "2026-10-06T08:52:27.549406+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320020", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "submitTime": "2026-10-06T08:52:27.549406+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320020", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-10-06T08:52:27.660895+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320023", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-10-06T08:52:27.660895+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320023", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-10-06T08:52:27.648162+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320021", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-10-06T08:52:27.648162+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320021", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "submitTime": "2026-10-06T09:13:59.677111+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320455", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "submitTime": "2026-10-06T09:13:59.676142+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320466", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-10-06T09:15:22.648982+00:00", "targetGpu": "Biren_166m", "taskId": "5320514", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-10-06T09:15:22.648982+00:00", "targetGpu": "Biren_166m", "taskId": "5320514", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-5bit-MLX", "modelId": "ukisai/Swift-1.5-5bit-MLX", "submitTime": "2026-10-06T09:15:22.761540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320515", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-5bit-MLX", "modelId": "ukisai/Swift-1.5-5bit-MLX", "submitTime": "2026-10-06T09:15:22.761540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320515", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "submitTime": "2026-10-06T09:15:22.866391+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320518", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "submitTime": "2026-10-06T09:15:22.866391+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320518", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}

24
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "a84ac910207151efa689d004207a1ae1b4f3ad6811d8d254a3d8a39a3b3fc87f", ".modelhub_state/architecture_compatibility_blacklist.json": "4f51efb9a0e8d48aaf97bf7acae6c0e5a2e36e4c9f74df721196b7868ac2e804",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "c22855507163c7416953e3a5965879997ecd0b2ce1360ccc9d918f94b60e2ac9", ".modelhub_state/market_intelligence.json": "64929dfeca573f6de625b8c8bb0e91292d9ab999101bdf2e78c619521b1a3a6d",
".modelhub_state/official_capabilities.json": "611c5b47b742b28867222be5f78f7e10820113e672f7bc02b8490e1660bc562a", ".modelhub_state/official_capabilities.json": "61099ca2d2c6762d668af923cc5ea7bf1ec9e9ea148556a3cffe9752c89dab3a",
".modelhub_state/outcome_checkpoint.json": "a5fccfea856345f346a45b534890585ea2c18a70aca187e5ced0d8f9faa85a48", ".modelhub_state/outcome_checkpoint.json": "84bc1e19e67ac71152d482c1764b7c89a8502087430dbf79f324be027349d2cf",
".modelhub_state/queue_cleanup_latest.json": "159f6df0b5b371fa1dddd726670836470a936ad493a4d7241524d02584c428b7", ".modelhub_state/queue_cleanup_latest.json": "1965ac91ebc1403dee7dc08c6d9877e352f2f6e7e00804a98b96ec767dd0d0aa",
".modelhub_state/recent_outcomes.jsonl": "ccbed4e3e9a8ccfca56856b049a43ea7a271d026cd0125a697aba416165ef37a", ".modelhub_state/recent_outcomes.jsonl": "6ab8cf8e8bcbaff143ddf33f66e6a462d62b24f52251469599f837b7ec461e14",
".modelhub_state/recovery_active_tasks.jsonl": "cce09047cae263d728375c1dc67b9af7891b8f9a9dd8409d9c5cef1b58788836", ".modelhub_state/recovery_active_tasks.jsonl": "7e3cb439aa55ded9dc5613f91fc576398c184daf70c23b46ec02e68fc76589d4",
".modelhub_state/recovery_intents.jsonl": "57ab24b0fac74028270c8a5e84b792d42e6433a1234aa698e96760a7f91383bf", ".modelhub_state/recovery_intents.jsonl": "207ad27490943d3f35220d538183302589f6b6e055512dfca7596e1174c36594",
".modelhub_state/routing_intelligence.json": "67aba6b23f7c9186cbd2cc1a757cfe1c1474348cdfa8f4efed9b37720353994f", ".modelhub_state/routing_intelligence.json": "67aba6b23f7c9186cbd2cc1a757cfe1c1474348cdfa8f4efed9b37720353994f",
".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b", ".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f", ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "27e6b7173d107476b2155e7e4d8f23010c81f9b98e7dff5173e8e7f1055e287b", "ledger/submissions.jsonl": "20e126af4d210ea76bfbe329bda2d725ef45ba223e3ba8ea7521ca4527ec034d",
"outcomes/submissions.jsonl": "90878c940257ec81a58fe2cb19b1bb215dd7cbc3d263ff7749406c5e9a0569e9" "outcomes/submissions.jsonl": "a0a69f43a6d5f2e824b89f2bc047e1097cf15537b933007e4d322f89753a26d2"
}, },
"generation": 21952, "generation": 21953,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-07T19:00:58.980580+00:00", "updatedAt": "2026-10-07T19:13:52.566137+00:00",
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2" "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
} }

25
outcomes/submissions.jsonl
View File

@@ -229,21 +229,10 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057509+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.583521+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006188", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057509+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.583521+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006188", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057389+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.641656+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006191", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057389+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.641656+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006191", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057480+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.26, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2022478516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.638009+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006194", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057480+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.26, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2022478516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.638009+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006194", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057413+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042625829}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.651884+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006196", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057469+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030685704, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039047610}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.643154+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006186", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057498+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031556216, "estimatedRequiredGiB": 2.28, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039918195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.645382+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006189", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057428+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030769952, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039132310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.649992+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006193", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057504+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g64-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2032454776, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2040816815}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.659014+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006195", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057421+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2038896936, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042511760}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.675420+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006197", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057475+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034915504, "estimatedRequiredGiB": 2.278, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2038530279}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.846176+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006199", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057515+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.789058+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006198", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057487+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.844977+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006200", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600642+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.447446+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006364", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600714+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.388268+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006357", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600714+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.388268+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006357", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600703+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.384898+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006356", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600703+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.384898+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006356", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600656+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.459191+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006360", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600656+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039076183}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.459191+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006360", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600649+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.449585+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006359", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600649+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.449585+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006359", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600690+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.26, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2022478516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.451588+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006358", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T03:37:52.600620+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042625829}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.445928+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006361", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T03:37:52.600620+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block2-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042625829}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.445928+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006361", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T03:37:52.600663+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030685704, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039047610}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.453443+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006363", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T03:37:52.600663+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030685704, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039047610}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.453443+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006363", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T03:37:52.600683+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031556216, "estimatedRequiredGiB": 2.28, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039918195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.455102+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006362", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T03:37:52.600683+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031556216, "estimatedRequiredGiB": 2.28, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039918195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.455102+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006362", "taskType": "text-generation", "verifyResult": null}
@@ -277,7 +266,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T04:42:12.054487+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2038896936, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042511760}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:40:49.946575+00:00", "targetGpu": "Biren_166m", "taskId": "5007047", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T04:42:12.054487+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2038896936, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042511760}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:40:49.946575+00:00", "targetGpu": "Biren_166m", "taskId": "5007047", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T04:42:12.054464+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:40:49.952519+00:00", "targetGpu": "Biren_166m", "taskId": "5007048", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T04:42:12.054464+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:40:49.952519+00:00", "targetGpu": "Biren_166m", "taskId": "5007048", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T04:46:21.254208+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:46:16.651713+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007123", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T04:46:21.254208+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:46:16.651713+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007123", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T05:04:53.763790+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2044205392, "estimatedRequiredGiB": 2.469, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2209448692, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2209448692}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T21:04:43.408226+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5007290", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T05:07:34.967687+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T21:06:49.754370+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5007313", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T05:07:34.967687+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T21:06:49.754370+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5007313", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T05:07:34.967708+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T21:06:49.752998+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5007314", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T05:07:34.967708+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T21:06:49.752998+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5007314", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T05:10:38.965428+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T21:10:26.048602+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007347", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T05:10:38.965428+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T21:10:26.048602+00:00", "targetGpu": "MetaX_c-500", "taskId": "5007347", "taskType": "text-generation", "verifyResult": null}
@@ -585,28 +573,18 @@
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-04T00:18:23.253336+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:48.956404+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5260087", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-04T00:18:23.253336+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:48.956404+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5260087", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253503+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "0a1dbeb37891c11a4d439b0dc783c89f1ca6323ea07398122fc1d7f8cfe8d96f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:48.962708+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260089", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253503+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "0a1dbeb37891c11a4d439b0dc783c89f1ca6323ea07398122fc1d7f8cfe8d96f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:48.962708+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260089", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253696+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169537087, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 33169537087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:48.954522+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260093", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253696+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B-FP8", "modelProfile": {"architectures": ["Xing4_0ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33165728400, "estimatedRequiredGiB": 37.07, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "xing4_0", "modelscopeFileSize": 33169537087, "modelscopeLicense": null, "modelscopeParams": 31215031088, "modelscopeTags": ["model_type:xing4_0", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 33169537087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:48.954522+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260093", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253537+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:48.964174+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260086", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253426+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:48.958081+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260088", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253639+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.154928+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260094", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253639+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.154928+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260094", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253568+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.244657+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260102", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253471+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.161002+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260095", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253471+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.161002+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260095", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253690+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199119539}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.256275+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260098", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253420+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.265263+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260097", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253330+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.262277+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260096", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253530+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.351950+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260104", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253530+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.351950+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260104", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253282+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "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": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.252673+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260100", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253282+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "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": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.252673+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260100", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253498+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.272455+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260099", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253498+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.272455+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260099", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253379+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.353284+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260101", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253379+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.353284+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260101", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253604+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.356198+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260103", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253604+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.356198+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260103", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253634+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-full-sublayer-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199612614, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199612614}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.446747+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260107", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253562+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block1-v1_D", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251904, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199622478, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199622478}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.469061+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260106", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253465+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.464366+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260105", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253465+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.464366+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260105", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253493+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.565606+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260116", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253493+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.565606+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260116", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253273+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.554250+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260109", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253273+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.554250+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260109", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253524+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "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": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.572421+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260112", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253524+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "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": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.572421+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260112", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253414+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.563992+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260111", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253414+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6737, "estimatedRequiredGiB": 2.427, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2171252206, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1080632832, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:ms-swift", "custom_tag:LoRA"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2171252206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.563992+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260111", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253323+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.560660+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260110", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253685+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g4-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871536, "estimatedRequiredGiB": 2.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2163952661, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2163952661}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.555638+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260108", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253459+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 30361724387, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.674309+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260118", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253459+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 30361724387, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.674309+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260118", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253629+00:00", "modelId": "FINAL-Bench/Darwin-27B-RSI", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53792110192, "estimatedRequiredGiB": 60.14, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 53812206708, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:darwin", "custom_tag:darwin-rsi", "custom_tag:recursive-self-improvement", "custom_tag:model-level-rsi", "custom_tag:rsi", "custom_tag:self-improvement", "custom_tag:self-improving-ai", "custom_tag:self-evolving", "custom_tag:no-human-labels", "custom_tag:label-free", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:chain-of-thought", "custom_tag:gpqa", "custom_tag:supergpqa", "custom_tag:decision-index", "custom_tag:typed-decisions", "custom_tag:jev", "custom_tag:system-2", "custom_tag:qwen3.5", "custom_tag:27b", "custom_tag:vidraft", "custom_tag:final-bench"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53812206708}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.664837+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260117", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253629+00:00", "modelId": "FINAL-Bench/Darwin-27B-RSI", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53792110192, "estimatedRequiredGiB": 60.14, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 53812206708, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:darwin", "custom_tag:darwin-rsi", "custom_tag:recursive-self-improvement", "custom_tag:model-level-rsi", "custom_tag:rsi", "custom_tag:self-improvement", "custom_tag:self-improving-ai", "custom_tag:self-evolving", "custom_tag:no-human-labels", "custom_tag:label-free", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:chain-of-thought", "custom_tag:gpqa", "custom_tag:supergpqa", "custom_tag:decision-index", "custom_tag:typed-decisions", "custom_tag:jev", "custom_tag:system-2", "custom_tag:qwen3.5", "custom_tag:27b", "custom_tag:vidraft", "custom_tag:final-bench"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53812206708}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.664837+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260117", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253599+00:00", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "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": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.651187+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260113", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253599+00:00", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "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": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.651187+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260113", "taskType": "text-generation", "verifyResult": null}
@@ -616,7 +594,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253487+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "91724ec8af3438608025fceb041a914813953b73f7cf5dbbf3b18a807d4b354f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.960990+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260120", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253487+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "91724ec8af3438608025fceb041a914813953b73f7cf5dbbf3b18a807d4b354f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.960990+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260120", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253679+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.751457+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260119", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253679+00:00", "modelId": "ProCreations/BetterWright-K2-Horizon-7B-Uno", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19395158128, "estimatedRequiredGiB": 21.699, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 19416072650, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4022513664, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:betterwright", "custom_tag:browser-agent", "custom_tag:web-agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:diffusion-language-model", "custom_tag:uno", "custom_tag:k2-horizon", "custom_tag:full-finetune"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19416072650}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.751457+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260119", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253316+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.752368+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260114", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253316+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.752368+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260114", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253371+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960168568, "estimatedRequiredGiB": 2.344, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2097293495, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2097293495}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.052404+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260121", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253408+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": 26586426092, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.943304+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260126", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253408+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26581256560, "estimatedRequiredGiB": 29.713, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "baguettotron_moe", "modelscopeFileSize": 26586426092, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:baguettotron_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:moe", "custom_tag:mixtral", "custom_tag:reasoning", "custom_tag:synthetic-data", "custom_tag:custom_code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26586426092}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:49.943304+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260126", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253519+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.046146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260125", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253519+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1216600244, "estimatedRequiredGiB": 1.365, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1221756819, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:transformers", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1221756819}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.046146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260125", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253594+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.055568+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260122", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-04T00:18:23.253594+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-03T16:15:50.055568+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5260122", "taskType": "text-generation", "verifyResult": null}
@@ -730,8 +707,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-06T18:06:36.953120+00:00", "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "70fc30548c2dc36d2dafb257d0a9af9499f0b4ee78e93bb3669e56774e585794", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3892651456, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 26407018955, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.665332+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320464", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-06T18:06:36.953120+00:00", "modelId": "webAI-Official/TwIL-LM3-Pro", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "70fc30548c2dc36d2dafb257d0a9af9499f0b4ee78e93bb3669e56774e585794", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3892651456, "estimatedRequiredGiB": 29.512, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 26407018955, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26407018955}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.665332+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320464", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-06T18:06:36.953001+00:00", "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "cb5d151b2dc44f0b470d106dee740b8a04dd01ff392c2d2ce69e974ff0e2c0fb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2694119616, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.667635+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320463", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-06T18:06:36.953001+00:00", "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "cb5d151b2dc44f0b470d106dee740b8a04dd01ff392c2d2ce69e974ff0e2c0fb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2694119616, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.667635+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5320463", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T18:06:36.952007+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.672848+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320456", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T18:06:36.952007+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.672848+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320456", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T18:06:36.953006+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2152567281, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.677111+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320455", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T18:06:36.952454+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.676142+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320466", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952893+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.662856+00:00", "targetGpu": "Biren_166m", "taskId": "5320459", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952893+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.662856+00:00", "targetGpu": "Biren_166m", "taskId": "5320459", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953125+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.670629+00:00", "targetGpu": "Biren_166m", "taskId": "5320460", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953125+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.670629+00:00", "targetGpu": "Biren_166m", "taskId": "5320460", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952117+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.674981+00:00", "targetGpu": "Biren_166m", "taskId": "5320465", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952117+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:13:59.674981+00:00", "targetGpu": "Biren_166m", "taskId": "5320465", "taskType": "text-generation", "verifyResult": null}