state: generation 27805 (intent)

This commit is contained in:
2026-10-21 21:17:43 +00:00
parent b9ff44e955
commit 6631c3abed
10 changed files with 2013 additions and 1571 deletions

View File

@@ -2,53 +2,53 @@
"accounts": {
"116321aaaa71977e436a": {
"accountIndex": 5,
"knownCap": 2
"knownCap": 100
},
"203cf600e31a19e36522": {
"accountIndex": 4,
"knownCap": 2
"knownCap": 100
},
"23b36a0498728a5497ec": {
"accountIndex": 10,
"knownCap": 1
"knownCap": 100
},
"5d7e48ccd4ba2b34e49f": {
"accountIndex": 7,
"knownCap": 2
"knownCap": 100
},
"72046eb8a2d9d386504e": {
"accountIndex": 11,
"knownCap": 3
"knownCap": 100
},
"730c876d2910041553c8": {
"accountIndex": 9,
"knownCap": 2
"knownCap": 100
},
"b940824e4299693749aa": {
"accountIndex": 6,
"knownCap": 4
"knownCap": 100
},
"bc10735ccf9c93d0bc23": {
"accountIndex": 12,
"knownCap": 2
"knownCap": 100
},
"c5217a5fe9b938618a85": {
"accountIndex": 3,
"knownCap": 3
"knownCap": 100
},
"cef6a28aba11a67c2a45": {
"accountIndex": 2,
"knownCap": 2
"knownCap": 100
},
"efca47eed826bada0502": {
"accountIndex": 1,
"knownCap": 13
"knownCap": 100
},
"f0b5423ecb0841256040": {
"accountIndex": 8,
"knownCap": 8
"knownCap": 100
}
},
"updatedAt": "2026-10-21T20:54:31.481688+00:00",
"updatedAt": "2026-10-21T21:16:28.397588+00:00",
"version": 1
}

View File

@@ -491,7 +491,7 @@
"metax_c-500|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 3,
"evidenceCount": 2,
"expiresAt": "2026-11-05T08:52:25.882518+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-10-06T08:52:25.882518+00:00",
@@ -500,13 +500,11 @@
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
"mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
"primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8"
"mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B"
],
"sourceTaskIds": [
"5319960",
"5319943",
"5319932"
"5319943"
],
"targetGpu": "MetaX_c-500",
"taskType": "text-generation"
@@ -530,6 +528,25 @@
"targetGpu": "MetaX_c-500",
"taskType": "text-generation"
},
"metax_c-500|vllm|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-11-20T21:15:43+00:00",
"framework": "vllm",
"latestFailureAt": "2026-10-21T21:15:43+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"cyankiwi/Ornith-1.0-35B-AWQ-INT4"
],
"sourceTaskIds": [
"5684052"
],
"targetGpu": "MetaX_c-500",
"taskType": "text-generation"
},
"mthreads_s4000|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
@@ -611,9 +628,9 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-21T21:14:46.753204+00:00",
"generatedAt": "2026-10-21T21:16:24.877566+00:00",
"summary": {
"activeBlockCount": 30,
"activeBlockCount": 31,
"byGpuFramework": {
"Ascend_910-b3|vllm": 1,
"Ascend_910-b3|vllm_tokenizer_patch": 2,
@@ -624,7 +641,7 @@
"Cambricon_mlu-370-x8|vllm-mlu": 2,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
"Iluvatar_mrv-100|vllm": 3,
"MetaX_c-500|vllm": 1,
"MetaX_c-500|vllm": 2,
"MetaX_c-500|vllm_tokenizer_patch": 4,
"Mthreads_s4000|vllm": 2,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 1,

View File

@@ -452,121 +452,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-21T21:14:46.874280+00:00",
"generatedAt": "2026-10-21T21:16:40.677149+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1142.3513513513512,
"backlogHours": 1149.9183673469388,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.5453792765860181,
"queueFactor": 0.9689986975435282,
"queueWeight": 0.9689986975435282,
"recentSuccess": 30,
"recentSuccessRate": 0.20270270270270271,
"recentTerminal": 148,
"recentWilsonLowerBound": 0.14583936224518,
"qualityFactor": 0.5744825219196915,
"queueFactor": 0.9680152359890588,
"queueWeight": 0.9680152359890588,
"recentSuccess": 31,
"recentSuccessRate": 0.2108843537414966,
"recentTerminal": 147,
"recentWilsonLowerBound": 0.1527313597425877,
"running": 8,
"selectionWeight": 0.5284718086790832,
"selectionWeight": 0.5561078340276798,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.666666666666668,
"waiting": 28178
"throughputPerHour": 24.5,
"waiting": 28173
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1407.410071942446,
"backlogHours": 1377.4647887323943,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.5,
"queueFactor": 0.9391393763285917,
"queueWeight": 0.9391393763285917,
"recentSuccess": 51,
"recentSuccessRate": 0.3669064748201439,
"recentTerminal": 139,
"recentWilsonLowerBound": 0.29136609862384355,
"queueFactor": 0.9421502520095155,
"queueWeight": 0.9421502520095155,
"recentSuccess": 53,
"recentSuccessRate": 0.3732394366197183,
"recentTerminal": 142,
"recentWilsonLowerBound": 0.2980091971868539,
"running": 8,
"selectionWeight": 2.3478484408214793,
"selectionWeight": 2.3553756300237887,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.166666666666668,
"waiting": 32605
"throughputPerHour": 23.666666666666668,
"waiting": 32600
},
"Biren_166m": {
"available": true,
"backlogHours": 111.50204081632653,
"backlogHours": 110.1532258064516,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.059965790005360106,
"qualityFactor": 0.07170317619797106,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 20,
"recentSuccessRate": 0.08163265306122448,
"recentTerminal": 245,
"recentWilsonLowerBound": 0.053463675811352175,
"recentSuccess": 22,
"recentSuccessRate": 0.08870967741935484,
"recentTerminal": 248,
"recentWilsonLowerBound": 0.05931137938583347,
"running": 8,
"selectionWeight": 0.07795552700696814,
"selectionWeight": 0.09321412905736239,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 40.833333333333336,
"throughputPerHour": 41.333333333333336,
"waiting": 4553
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 983.027027027027,
"backlogHours": 982.8108108108108,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.1324187590208821,
"queueFactor": 0.9910791267957219,
"queueWeight": 0.9910791267957219,
"qualityFactor": 0.1260114724622174,
"queueFactor": 0.9910869457100846,
"queueWeight": 0.9910869457100846,
"recentSuccess": 14,
"recentSuccessRate": 0.12612612612612611,
"recentTerminal": 111,
"recentWilsonLowerBound": 0.07663785470708645,
"running": 7,
"selectionWeight": 0.13123746806178896,
"selectionWeight": 0.12488832536700946,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.5,
"waiting": 18186
"waiting": 18182
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 334.25142857142856,
"backlogHours": 319.672131147541,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.31161042314323656,
"queueFactor": 1.1651508530190853,
"queueWeight": 1.1651508530190853,
"qualityFactor": 0.26818265049216383,
"queueFactor": 1.1729419745197942,
"queueWeight": 1.1729419745197942,
"recentSuccess": 28,
"recentSuccessRate": 0.16,
"recentTerminal": 175,
"recentWilsonLowerBound": 0.11307870395124361,
"recentSuccessRate": 0.15300546448087432,
"recentTerminal": 183,
"recentWilsonLowerBound": 0.10802980904437412,
"running": 7,
"selectionWeight": 0.36307315033498017,
"selectionWeight": 0.3145626876002305,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 29.166666666666668,
"waiting": 9749
"throughputPerHour": 30.5,
"waiting": 9750
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 76.53511705685618,
"backlogHours": 77.45084745762712,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -576,196 +576,196 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 15,
"recentSuccessRate": 0.05016722408026756,
"recentTerminal": 299,
"recentWilsonLowerBound": 0.030634264948042222,
"recentSuccessRate": 0.05084745762711865,
"recentTerminal": 295,
"recentWilsonLowerBound": 0.031052886803117304,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 49.833333333333336,
"waiting": 3814
"throughputPerHour": 49.166666666666664,
"waiting": 3808
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 171.90106007067138,
"backlogHours": 169.58885017421602,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.23472408405733416,
"queueFactor": 1.287364014049041,
"queueWeight": 1.287364014049041,
"recentSuccess": 38,
"recentSuccessRate": 0.13427561837455831,
"recentTerminal": 283,
"recentWilsonLowerBound": 0.0994138834069284,
"running": 5,
"selectionWeight": 0.3021753390460342,
"qualityFactor": 0.20211322485714878,
"queueFactor": 1.289949326761863,
"queueWeight": 1.289949326761863,
"recentSuccess": 37,
"recentSuccessRate": 0.1289198606271777,
"recentTerminal": 287,
"recentWilsonLowerBound": 0.09499682424822424,
"running": 3,
"selectionWeight": 0.2607158183341481,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 47.166666666666664,
"waiting": 8108
"throughputPerHour": 47.833333333333336,
"waiting": 8112
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2549.0526315789475,
"backlogHours": 2618.108108108108,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.5409766923105586,
"queueFactor": 0.8590853792895204,
"queueWeight": 0.8590853792895204,
"qualityFactor": 1.5618362663487857,
"queueFactor": 0.8556262662318102,
"queueWeight": 0.8556262662318102,
"recentSuccess": 14,
"recentSuccessRate": 0.3684210526315789,
"recentTerminal": 38,
"recentWilsonLowerBound": 0.23384013155413794,
"recentSuccessRate": 0.3783783783783784,
"recentTerminal": 37,
"recentWilsonLowerBound": 0.2406378746389103,
"running": 2,
"selectionWeight": 1.323830546189927,
"selectionWeight": 1.3363481330414424,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.333333333333333,
"waiting": 16144
"throughputPerHour": 6.166666666666667,
"waiting": 16145
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 444.046875,
"backlogHours": 447.4015748031496,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.573512885396235,
"queueFactor": 1.1165516702691836,
"queueWeight": 1.1165516702691836,
"recentSuccess": 27,
"recentSuccessRate": 0.2109375,
"recentTerminal": 128,
"recentWilsonLowerBound": 0.1492121185502459,
"qualityFactor": 0.6118665007341005,
"queueFactor": 1.1152638320277928,
"queueWeight": 1.1152638320277928,
"recentSuccess": 28,
"recentSuccessRate": 0.2204724409448819,
"recentTerminal": 127,
"recentWilsonLowerBound": 0.15717143105153952,
"running": 8,
"selectionWeight": 0.6403567701100651,
"selectionWeight": 0.6823925782981493,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.333333333333332,
"waiting": 9473
"throughputPerHour": 21.166666666666668,
"waiting": 9470
},
"MetaX_c-500": {
"available": true,
"backlogHours": 510.9635036496351,
"backlogHours": 492.7183098591549,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.5940789649162524,
"queueFactor": 1.093288213527617,
"queueWeight": 1.093288213527617,
"recentSuccess": 29,
"recentSuccessRate": 0.2116788321167883,
"recentTerminal": 137,
"recentWilsonLowerBound": 0.15162090848199464,
"qualityFactor": 0.5699819584898731,
"queueFactor": 1.0992397870983295,
"queueWeight": 1.0992397870983295,
"recentSuccess": 30,
"recentSuccessRate": 0.2112676056338028,
"recentTerminal": 142,
"recentWilsonLowerBound": 0.15218632238107427,
"running": 4,
"selectionWeight": 0.6494995302476255,
"selectionWeight": 0.6265468467002969,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.833333333333332,
"waiting": 11667
"throughputPerHour": 23.666666666666668,
"waiting": 11661
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 3147.8399999999997,
"backlogHours": 3085.8823529411766,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.22591772089940776,
"queueFactor": 0.8323217637446844,
"queueWeight": 0.8323217637446844,
"qualityFactor": 0.20552761187716748,
"queueFactor": 0.8347863513748297,
"queueWeight": 0.8347863513748297,
"recentSuccess": 9,
"recentSuccessRate": 0.18,
"recentTerminal": 50,
"recentWilsonLowerBound": 0.0977008273245379,
"recentSuccessRate": 0.17647058823529413,
"recentTerminal": 51,
"recentWilsonLowerBound": 0.09572295725809898,
"running": 4,
"selectionWeight": 0.1880362359201744,
"selectionWeight": 0.17157164522572274,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.333333333333334,
"waiting": 26232
"throughputPerHour": 8.5,
"waiting": 26230
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 1501.5405405405404,
"backlogHours": 1501.4594594594594,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.06589970409098739,
"queueFactor": 0.9300634741702558,
"queueWeight": 0.9300634741702558,
"recentSuccess": 8,
"recentSuccessRate": 0.10810810810810811,
"qualityFactor": 0.05,
"queueFactor": 0.9300476569292823,
"queueWeight": 0.9300476569292823,
"recentSuccess": 7,
"recentSuccessRate": 0.0945945945945946,
"recentTerminal": 74,
"recentWilsonLowerBound": 0.055806661696501225,
"recentWilsonLowerBound": 0.046579345930590606,
"running": 2,
"selectionWeight": 0.06129090773365555,
"selectionWeight": 0.046502382846464116,
"stale": false,
"submissionEligible": true,
"submissionEligible": false,
"throughputPerHour": 12.333333333333334,
"waiting": 18519
"waiting": 18518
},
"Vastai_va16": {
"available": true,
"backlogHours": 869.015625,
"backlogHours": 868.921875,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.05,
"queueFactor": 1.0095759829708455,
"queueWeight": 1.0095759829708455,
"recentSuccess": 6,
"recentSuccessRate": 0.046875,
"queueFactor": 1.0095669737544124,
"queueWeight": 1.0095669737544124,
"recentSuccess": 5,
"recentSuccessRate": 0.0390625,
"recentTerminal": 128,
"recentWilsonLowerBound": 0.02165754889327991,
"recentWilsonLowerBound": 0.0167983630559502,
"running": 16,
"selectionWeight": 0.05047879914854228,
"selectionWeight": 0.05047834868772062,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 21.333333333333332,
"waiting": 18539
"waiting": 18537
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 1378.710280373832,
"backlogHours": 1365.6666666666667,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 1.7158334941268696,
"queueFactor": 0.9420461872440877,
"queueWeight": 0.9420461872440877,
"recentSuccess": 35,
"recentSuccessRate": 0.32710280373831774,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.2455482291176742,
"qualityFactor": 1.4805794300632646,
"queueFactor": 0.9433666916973844,
"queueWeight": 0.9433666916973844,
"recentSuccess": 34,
"recentSuccessRate": 0.3148148148148148,
"recentTerminal": 108,
"recentWilsonLowerBound": 0.234864190343351,
"running": 6,
"selectionWeight": 1.6163944010879183,
"selectionWeight": 1.3967293187339809,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.833333333333332,
"waiting": 24587
"throughputPerHour": 18.0,
"waiting": 24582
}
},
"queueAttemptedAt": "2026-10-21T21:04:51.367800+00:00",
"queueAttemptedAt": "2026-10-21T21:16:40.677149+00:00",
"queueError": null,
"queueUpdatedAt": "2026-10-21T21:04:51.367800+00:00",
"queueUpdatedAt": "2026-10-21T21:16:40.677149+00:00",
"supportedGpus": [
"Cambricon_mlu-370-x4",
"Vastai_va16",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-21T21:04:51.145479+00:00",
"lastSyncTime": "2026-10-21T21:04:50.875541+00:00",
"generatedAt": "2026-10-21T21:16:40.576259+00:00",
"lastSyncTime": "2026-10-21T21:16:40.470588+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -495,7 +495,7 @@
"metax_c-500|vllm_tokenizer_patch|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 3,
"evidenceCount": 2,
"expiresAt": "2026-11-05T08:52:25.882518+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-10-06T08:52:25.882518+00:00",
@@ -504,13 +504,11 @@
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"mlx-community/Agents-A1-OptiQ-4bit-REAP-19B",
"mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B",
"primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8"
"mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B"
],
"sourceTaskIds": [
"5319960",
"5319943",
"5319932"
"5319943"
],
"targetGpu": "MetaX_c-500",
"taskType": "text-generation"
@@ -534,6 +532,25 @@
"targetGpu": "MetaX_c-500",
"taskType": "text-generation"
},
"metax_c-500|vllm|text-generation|model_type:qwen3_5_moe": {
"architectureSignature": "model_type:qwen3_5_moe",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-11-20T21:15:43+00:00",
"framework": "vllm",
"latestFailureAt": "2026-10-21T21:15:43+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5_moe",
"sourceModelIds": [
"cyankiwi/Ornith-1.0-35B-AWQ-INT4"
],
"sourceTaskIds": [
"5684052"
],
"targetGpu": "MetaX_c-500",
"taskType": "text-generation"
},
"mthreads_s4000|vllm|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
@@ -616,7 +633,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 30,
"activeBlockCount": 31,
"byGpuFramework": {
"Ascend_910-b3|vllm": 1,
"Ascend_910-b3|vllm_tokenizer_patch": 2,
@@ -627,7 +644,7 @@
"Cambricon_mlu-370-x8|vllm-mlu": 2,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
"Iluvatar_mrv-100|vllm": 3,
"MetaX_c-500|vllm": 1,
"MetaX_c-500|vllm": 2,
"MetaX_c-500|vllm_tokenizer_patch": 4,
"Mthreads_s4000|vllm": 2,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 1,
@@ -1044,11 +1061,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 154,
"ambiguous_runtime": 155,
"memory_capacity": 1,
"参数/模板问题": 5
},
"failureCount": 160,
"failureCount": 161,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -1058,8 +1075,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 160,
"unresolvedFailureCount": 159
"total": 161,
"unresolvedFailureCount": 160
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 50,
@@ -2514,16 +2531,16 @@
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 640,
"attributableFailureCount": 641,
"decisionFailureRate": 0.961,
"decisionSuccessRate": 0.039,
"decisionTotal": 666,
"decisionTotal": 667,
"failureBreakdown": {
"ambiguous_runtime": 135,
"architecture_compatibility": 20,
"backend_operator": 43,
"context_length": 46,
"framework_architecture_unsupported": 203,
"framework_architecture_unsupported": 204,
"memory_capacity": 84,
"model_load": 65,
"platform_infrastructure": 3,
@@ -2532,7 +2549,7 @@
"tokenizer_compatibility": 79,
"参数/模板问题": 11
},
"failureCount": 789,
"failureCount": 790,
"failureRate": 0.9681,
"framework": "vllm",
"pendingCount": 0,
@@ -2542,7 +2559,7 @@
"successRate": 0.0319,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 815,
"total": 816,
"unresolvedFailureCount": 146
},
"MetaX_c-500|vllm|unknown": {
@@ -3337,17 +3354,17 @@
"unresolvedFailureCount": 6552
},
"vllm": {
"attributableFailureCount": 3708,
"attributableFailureCount": 3709,
"decisionFailureRate": 0.9709,
"decisionSuccessRate": 0.0291,
"decisionTotal": 3819,
"decisionTotal": 3820,
"failureBreakdown": {
"ambiguous_runtime": 1608,
"architecture_compatibility": 112,
"attention_backend": 3,
"backend_operator": 98,
"context_length": 161,
"framework_architecture_unsupported": 1418,
"framework_architecture_unsupported": 1419,
"memory_capacity": 725,
"model_load": 230,
"platform_infrastructure": 888,
@@ -3356,14 +3373,14 @@
"tokenizer_compatibility": 425,
"参数/模板问题": 90
},
"failureCount": 6294,
"failureCount": 6295,
"failureRate": 0.9827,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 888,
"successCount": 111,
"successRate": 0.0173,
"total": 6405,
"total": 6406,
"unresolvedFailureCount": 1698
},
"vllm-customized": {
@@ -3466,7 +3483,7 @@
"decisionSuccessRate": 0.0359,
"decisionTotal": 195,
"failureBreakdown": {
"ambiguous_runtime": 432,
"ambiguous_runtime": 433,
"backend_operator": 11,
"framework_architecture_unsupported": 56,
"memory_capacity": 11,
@@ -3475,15 +3492,15 @@
"tokenizer_compatibility": 97,
"参数/模板问题": 30
},
"failureCount": 685,
"failureCount": 686,
"failureRate": 0.9899,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 35,
"successCount": 7,
"successRate": 0.0101,
"total": 692,
"unresolvedFailureCount": 462
"total": 693,
"unresolvedFailureCount": 463
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 172,
@@ -3514,7 +3531,7 @@
"unresolvedFailureCount": 339
}
},
"generatedAt": "2026-10-21T21:04:51.127521+00:00",
"generatedAt": "2026-10-21T21:16:40.520921+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 132,
@@ -3578,7 +3595,7 @@
"decisionSuccessRate": 0.1147,
"decisionTotal": 218,
"failureBreakdown": {
"ambiguous_runtime": 298,
"ambiguous_runtime": 299,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 125,
@@ -3592,15 +3609,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 801,
"failureRate": 0.9697,
"failureCount": 802,
"failureRate": 0.9698,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0303,
"total": 826,
"unresolvedFailureCount": 606
"successRate": 0.0302,
"total": 827,
"unresolvedFailureCount": 607
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 767,
@@ -3790,16 +3807,16 @@
"unresolvedFailureCount": 170
},
"MetaX_c-500": {
"attributableFailureCount": 684,
"decisionFailureRate": 0.8231,
"decisionSuccessRate": 0.1769,
"decisionTotal": 831,
"attributableFailureCount": 685,
"decisionFailureRate": 0.8233,
"decisionSuccessRate": 0.1767,
"decisionTotal": 832,
"failureBreakdown": {
"ambiguous_runtime": 308,
"architecture_compatibility": 21,
"backend_operator": 43,
"context_length": 60,
"framework_architecture_unsupported": 213,
"framework_architecture_unsupported": 214,
"memory_capacity": 85,
"model_load": 67,
"platform_infrastructure": 5,
@@ -3810,14 +3827,14 @@
"日志缺失": 15,
"验证失败": 48
},
"failureCount": 1507,
"failureRate": 0.9111,
"failureCount": 1508,
"failureRate": 0.9112,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 5,
"successCount": 147,
"successRate": 0.0889,
"total": 1654,
"successRate": 0.0888,
"total": 1655,
"unresolvedFailureCount": 818
},
"Mthreads_s4000": {
@@ -3956,7 +3973,7 @@
"hygon_k100-ai": 64.0
},
"pendingRecords": 0,
"policyCancelledRecords": 530,
"policyCancelledRecords": 537,
"profileCombinationStats": {
"Ascend_910-b3|llamacpp|text-generation|smollm3|none": {
"attributableFailureCount": 0,
@@ -7084,6 +7101,29 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|modelopt": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -25188,10 +25228,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 10,
"ambiguous_runtime": 11,
"参数/模板问题": 3
},
"failureCount": 13,
"failureCount": 14,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -25203,8 +25243,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 13
"total": 14,
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -25494,6 +25534,31 @@
"total": 20,
"unresolvedFailureCount": 14
},
"MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-21T21:16:24.481139+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|unknown|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -25778,6 +25843,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|modelopt": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-21T21:16:24.481190+00:00",
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gpt_oss|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -26906,31 +26996,6 @@
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_moe|compressed-tensors": {
"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": "2026-10-07T11:42:31.164571+00:00",
"modelType": "qwen3_5_moe",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm_tokenizer_patch|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 2,
"consecutiveFailures": 2,
@@ -32557,6 +32622,30 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|modelopt|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "gemma4",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "modelopt",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|none|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
@@ -59672,20 +59761,20 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17939,
"totalRecords": 18469,
"terminalRecords": 17941,
"totalRecords": 18478,
"totals": {
"attributableFailureCount": 6347,
"decisionFailureRate": 0.8655,
"decisionSuccessRate": 0.1345,
"decisionTotal": 7333,
"attributableFailureCount": 6348,
"decisionFailureRate": 0.8656,
"decisionSuccessRate": 0.1344,
"decisionTotal": 7334,
"failureBreakdown": {
"ambiguous_runtime": 4662,
"ambiguous_runtime": 4663,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 135,
"context_length": 328,
"framework_architecture_unsupported": 2346,
"framework_architecture_unsupported": 2347,
"memory_capacity": 1207,
"model_load": 577,
"platform_infrastructure": 971,
@@ -59696,15 +59785,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16953,
"failureCount": 16955,
"failureRate": 0.945,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 971,
"successCount": 986,
"successRate": 0.055,
"total": 17939,
"unresolvedFailureCount": 9635
"total": 17941,
"unresolvedFailureCount": 9636
},
"warnings": [
"GPU Biren_166m 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -59767,6 +59856,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 18469,
"summarizedRecords": 18478,
"version": 1
}

View File

@@ -20,7 +20,7 @@
"cleanupDisabled": true,
"reason": "admission_only"
},
"architectureBlockCount": 30,
"architectureBlockCount": 31,
"architectureFrameworkCatalog": {
"ascend_910-b3|text-generation": [
"llamacpp",
@@ -33,21 +33,6 @@
"vllm",
"vllm_tokenizer_patch"
],
"biren_166m|text-generation": [
"vllm",
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"cambricon_mlu-370-x4|text-generation": [
"vllm",
"vllm-customized",
"vllm-mlu"
],
"cambricon_mlu-370-x8|text-generation": [
"vllm",
"vllm-customized",
"vllm-mlu"
],
"hygon_k100-ai|text-generation": [
"llamacpp",
"vllm",
@@ -63,15 +48,6 @@
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"iluvatar_mrv-100|text-generation": [
"transformers",
"vllm"
],
"kunlunxin_p-800|text-generation": [
"vllm",
"vllm_fix_tokenizer",
"vllm_tokenizer_patch"
],
"metax_c-500|text-generation": [
"vllm",
"vllm_tokenizer_patch"
@@ -80,20 +56,161 @@
"llamacpp",
"vllm",
"vllm_tokenizer_patch"
],
"sunrise_pt-200-x1|text-generation": [
"sglang",
"vllm",
"vllm_fix_tokenizer"
],
"vastai_va16|text-generation": [
"vllm",
"vllm_fix_tokenizer"
]
},
"architectureFrameworkCatalogErrors": {},
"architectureIncompatibleCount": 0,
"architectureIncompatibleTasks": [],
"architectureIncompatibleCount": 7,
"architectureIncompatibleTasks": [
{
"accountIndex": 1,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "MetaX_c-500",
"modelId": "ddalcu/Qwen3.6-35B-A3B-MLX-Serve-4bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5381695,
"taskType": "text-generation"
},
{
"accountIndex": 4,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "MetaX_c-500",
"modelId": "StartLuxAI/Qwen3.6-35B-A3B-OptiQ-4bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5536994,
"taskType": "text-generation"
},
{
"accountIndex": 5,
"architectureBlockEvidenceCount": 3,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "all_live_frameworks",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm",
"vllm_tokenizer_patch"
],
"framework": "*",
"gpuType": "MetaX_c-500",
"modelId": "cyankiwi/Ornith-1.0-35B-AWQ-FP8",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5679352,
"taskType": "text-generation"
},
{
"accountIndex": 7,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "MetaX_c-500",
"modelId": "ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5482883,
"taskType": "text-generation"
},
{
"accountIndex": 11,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "MetaX_c-500",
"modelId": "ManniX-ITA/Qwen3.6-27B-A3B-Coder",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5402815,
"taskType": "text-generation"
},
{
"accountIndex": 11,
"architectureBlockEvidenceCount": 3,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "all_live_frameworks",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm",
"vllm_tokenizer_patch"
],
"framework": "*",
"gpuType": "MetaX_c-500",
"modelId": "cyankiwi/Qwen-AgentWorld-35B-A3B-AWQ-FP8",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5679853,
"taskType": "text-generation"
},
{
"accountIndex": 12,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "MetaX_c-500",
"modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5381694,
"taskType": "text-generation"
}
],
"architectureModelConfigErrors": {
"GestaltLabs/Ornstein-3.5-9B-V2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/GestaltLabs/Ornstein-3.5-9B-V2-GGUF/resolve/master/config.json (status=404)",
"LiquidAI/LFM2.5-2.6B-DSpark-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/LiquidAI/LFM2.5-2.6B-DSpark-GGUF/resolve/master/config.json (status=404)",
@@ -114,22 +231,193 @@
"z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
},
"architectureModelConfigsComplete": 27,
"architectureOnly": false,
"architectureOnly": true,
"architecturePolicySkipped": {
"frameworkCatalogUnknown": 0,
"frameworkContextUnknown": 34,
"modelArchitectureUnknown": 216,
"noMatchingBlock": 979,
"partiallyBlockedFrameworkSet": 5,
"noMatchingBlock": 974,
"partiallyBlockedFrameworkSet": 3,
"runningMatchedProtected": 0,
"submissionContextMismatch": 0,
"submissionContextUnknown": 0
},
"cancelledCount": 0,
"cancelledTasks": [],
"cancelledCount": 7,
"cancelledTasks": [
{
"accountIndex": 1,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "MetaX_c-500",
"modelId": "ddalcu/Qwen3.6-35B-A3B-MLX-Serve-4bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5381695,
"taskType": "text-generation"
},
{
"accountIndex": 4,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "MetaX_c-500",
"modelId": "StartLuxAI/Qwen3.6-35B-A3B-OptiQ-4bit",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5536994,
"taskType": "text-generation"
},
{
"accountIndex": 5,
"architectureBlockEvidenceCount": 3,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "all_live_frameworks",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm",
"vllm_tokenizer_patch"
],
"framework": "*",
"gpuType": "MetaX_c-500",
"modelId": "cyankiwi/Ornith-1.0-35B-AWQ-FP8",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5679352,
"taskType": "text-generation"
},
{
"accountIndex": 7,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "MetaX_c-500",
"modelId": "ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5482883,
"taskType": "text-generation"
},
{
"accountIndex": 11,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "MetaX_c-500",
"modelId": "ManniX-ITA/Qwen3.6-27B-A3B-Coder",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5402815,
"taskType": "text-generation"
},
{
"accountIndex": 11,
"architectureBlockEvidenceCount": 3,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "all_live_frameworks",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm",
"vllm_tokenizer_patch"
],
"framework": "*",
"gpuType": "MetaX_c-500",
"modelId": "cyankiwi/Qwen-AgentWorld-35B-A3B-AWQ-FP8",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5679853,
"taskType": "text-generation"
},
{
"accountIndex": 12,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-20T21:15:43+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "model_type",
"architectureSignature": "model_type:qwen3_5_moe",
"architectureSignatures": [
"model_type:qwen3_5_moe"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm"
],
"framework": "vllm",
"gpuType": "MetaX_c-500",
"modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5381694,
"taskType": "text-generation"
}
],
"certainOomCount": 0,
"certainOomTasks": [],
"cleanupCandidateCount": 0,
"cleanupCandidateCount": 7,
"dryRun": false,
"listingErrors": {},
"modelAgeErrors": {},
@@ -154,15 +442,15 @@
],
"oldOverflowCount": 0,
"oldOverflowTasks": [],
"policyCancelledRecorded": 0,
"policyCancelledRecorded": 7,
"policyNoLongerAppliesCount": 0,
"policyNoLongerAppliesTasks": [],
"recentModelDays": 7,
"recentModelReserveSlots": 5,
"repositorySizeErrors": {},
"repositorySizesComplete": 340,
"repositorySizesComplete": 0,
"skipped": {
"fitsKnownCapacity": 1200,
"fitsKnownCapacity": 0,
"gpuCapacityUnknown": 0,
"repositorySizeUnknown": 0
},

View File

@@ -1,3 +1,4 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-10-21T21:16:24.481139+00:00", "modelId": "cyankiwi/Ornith-1.0-35B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-21T21:15:43+00:00", "targetGpu": "MetaX_c-500", "taskId": "5684052", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "llamacpp", "lastSyncTime": "2026-10-19T02:18:02.861795+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-19T02:17:42+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4332393", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-10-18T23:11:19.047759+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-18T23:07:42+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4376891", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-10-18T20:30:33.153730+00:00", "modelId": "ornith-ai/Ornith-1.0-9B-GGUF", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-10-18T20:15:43+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4353479", "taskType": "text-generation", "verifyResult": -1}
@@ -263,6 +264,7 @@
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164443+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:27.549406+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320020", "taskType": "text-generation", "verifyResult": null}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T03:59:02.973639+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.471074+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320018", "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": "2026-10-10T09:26:43.784451+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409915, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409915}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.159752+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320008", "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": "2026-10-21T21:16:24.481190+00:00", "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.158144+00:00", "targetGpu": "Biren_166m", "taskId": "5320010", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:09:53.041515+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:26.657696+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319990", "taskType": "text-generation", "verifyResult": null}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T06:27:34.062566+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:26.475735+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319987", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:09:53.041505+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:26.456691+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319984", "taskType": "text-generation", "verifyResult": null}
@@ -296,5 +298,3 @@
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:31:58.345538+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:25.546082+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319945", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:31:58.345485+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:25.544511+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319947", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:31:58.345569+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:25.543223+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319942", "taskType": "text-generation", "verifyResult": null}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T11:42:31.164571+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090092835, "modelscopeLicense": "apache-2.0", "modelscopeParams": 21416999792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:fp8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26090092835}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:50:49.358297+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319932", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:09:53.041493+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:50:49.345125+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319936", "taskType": "text-generation", "verifyResult": null}

View File

@@ -3690,6 +3690,106 @@
{"batchId": "9c505c9d159f4f8495bc5e31e8bb24b0", "completedAt": "2026-10-21T18:42:34.650485+00:00", "configFingerprint": "a1180a720dd471c32059d347c8965c5b18df1ca663ca61c609333bb476be5117", "configSource": "modelhub_live", "createdAt": "2026-10-21T18:42:32.111209+00:00", "framework": "llamacpp", "intentId": "f325a603297d4a3e9b0ed6bc55a7280c", "lastModified": "2026-10-21T18:16:46+00:00", "modelAddress": "https://modelscope.cn/models/AtomicChat/Qwen3.5-9B-DFlash-GGUF", "reason": null, "reconciledAt": "2026-10-21T21:14:52.931132+00:00", "repoId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5699676", "taskType": "text-generation"}
{"batchId": "5bb2c5352b644790992acdf3f4f523ff", "completedAt": "2026-10-21T19:49:02.957262+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T19:48:50.055809+00:00", "framework": "vllm_tokenizer_patch", "intentId": "933b46fdd9a54b24a06b04b46a445f54", "lastModified": "2026-10-19T18:03:21+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-21T21:14:52.930627+00:00", "repoId": "cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5700656", "taskType": "text-generation"}
{"batchId": "8cc63beaf5e54bc8bb49ea0a3d28f49f", "completedAt": "2026-10-21T20:17:02.769542+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T20:16:58.974122+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b7b45aff30164d63b1c4cb44486fd379", "lastModified": "2026-10-21T16:46:52+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Seed-OSS-36B-Instruct-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-21T21:14:52.932216+00:00", "repoId": "cyankiwi/Seed-OSS-36B-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5701026", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.991738+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d6e998c18cae4424976f87cd315be803", "lastModified": "2026-10-21T16:31:51+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.991839+00:00", "framework": "vllm_tokenizer_patch", "intentId": "865d627f8cbf4d328798050af434e73c", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.991885+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7fb09d9f57494b6395459ad2c1632b4e", "lastModified": "2026-10-21T19:08:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.991929+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8fbd38cce8b84de885b5fcb2b5b3e912", "lastModified": "2026-10-21T15:33:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-8bit", "repoId": "cyankiwi/GLM-4.7-Flash-REAP-23B-A3B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.991971+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6bc552099f454634ba907f2fe261c8f7", "lastModified": "2026-10-21T17:18:20+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiroThinker-v1.5-30B-AWQ-8bit", "repoId": "cyankiwi/MiroThinker-v1.5-30B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992014+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0662ff0ab1514969859e5bfa986e1641", "lastModified": "2026-10-21T14:24:21+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-4bit", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992056+00:00", "framework": "vllm_tokenizer_patch", "intentId": "295a1632f7ef45fab25ddf82bf9f56ed", "lastModified": "2026-10-21T14:51:04+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nanbeige4.1-3B-AWQ-4bit", "repoId": "cyankiwi/Nanbeige4.1-3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992099+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bdda600303584856a28475a828105128", "lastModified": "2026-10-21T15:09:27+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiroThinker-v1.0-30B-AWQ-8bit", "repoId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992141+00:00", "framework": "vllm_tokenizer_patch", "intentId": "76533964ca1d485393531b2f85930504", "lastModified": "2026-10-21T12:17:17+00:00", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-24B-A2B", "repoId": "LiquidAI/LFM2.5-24B-A2B", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992196+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4e70ab87356e4730909af22f2ccac635", "lastModified": "2026-10-21T19:49:11+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-8bit", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992237+00:00", "framework": "vllm_tokenizer_patch", "intentId": "314b2423a60042bcb8429ae451008927", "lastModified": "2026-10-21T16:02:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4.3-36B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4.3-36B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992279+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8bddc018b8104e378afdbcfae0f84971", "lastModified": "2026-10-21T17:04:56+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992341+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1196b7d7722a4815a3a04b63a30f22f0", "lastModified": "2026-10-21T16:14:40+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992388+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d550399e6d754b21ab47e26402d5c26d", "lastModified": "2026-10-21T15:42:33+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Instruct-AWQ-8bit", "repoId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992429+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cb9792473e3e4bcb833d36ec9b9daa66", "lastModified": "2026-10-21T15:22:00+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Trinity-Mini-AWQ-8bit", "repoId": "cyankiwi/Trinity-Mini-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992471+00:00", "framework": "vllm_tokenizer_patch", "intentId": "95f9ecc9d50c4b5e8c698aa2ee05ac24", "lastModified": "2026-10-21T15:27:56+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Jan-v1-4B-AWQ-4bit", "repoId": "cyankiwi/Jan-v1-4B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992513+00:00", "framework": "vllm_tokenizer_patch", "intentId": "725602cf485e45ceab2198e0738f8544", "lastModified": "2026-10-21T17:08:03+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-8bit", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992555+00:00", "framework": "vllm_tokenizer_patch", "intentId": "684f0576d59c4ba2928714c6e3d1b5ff", "lastModified": "2026-10-21T17:19:37+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-8bit", "repoId": "cyankiwi/KAT-Dev-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "57aceff29ff69c4fb34602873529ff182196395d82e08b39e53f9350ca14eca7", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992597+00:00", "framework": "llamacpp", "intentId": "2c28fe133c2f4acba965ee64e5890553", "lastModified": "2026-10-21T03:15:59+00:00", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.6-4B-GGUF", "repoId": "XHToken/Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "0810a8dbec6a5bb8330373d71363e8e47f5ab88e5ca0b04cee0d7bb4fc33e81f", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992654+00:00", "framework": "llamacpp", "intentId": "007f63c2cc0041589cb606b1243d48a9", "lastModified": "2026-10-20T13:54:35+00:00", "modelAddress": "https://modelscope.cn/models/incoai/Muse-Glimmer-30B-DFlash2-GGUF", "repoId": "incoai/Muse-Glimmer-30B-DFlash2-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "705b8b3614c86a1ac722c97f43e177e84ca20282e9799fffb1b890510d641728", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992711+00:00", "framework": "llamacpp", "intentId": "38543a5df8464c82868f3ce7a04a6c47", "lastModified": "2026-10-21T18:16:46+00:00", "modelAddress": "https://modelscope.cn/models/AtomicChat/Qwen3.5-9B-DFlash-GGUF", "repoId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992762+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0af3286fa18340609e6b18cb7ab4473b", "lastModified": "2026-10-21T16:33:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992814+00:00", "framework": "vllm_tokenizer_patch", "intentId": "95bb5736c5304538916a905fdd1698d2", "lastModified": "2026-10-19T16:59:08+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cpatonn-mirror/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992864+00:00", "framework": "vllm_tokenizer_patch", "intentId": "80b1f65329964a48860d7389f540cd8a", "lastModified": "2026-10-21T14:17:13+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "repoId": "cyankiwi/MiroThinker-v1.0-30B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992913+00:00", "framework": "vllm_tokenizer_patch", "intentId": "8447fc03e3384e78840130f38de0bcb5", "lastModified": "2026-10-21T16:21:36+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.992962+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a11d96da481b40d2acd8dec40f0c0fbd", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993010+00:00", "framework": "vllm_tokenizer_patch", "intentId": "6e6a2b31232e4739bf8b85be6b6771bd", "lastModified": "2026-10-21T16:56:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993058+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ba2e15117fb4474baf0f6f5a4381394f", "lastModified": "2026-10-21T15:04:03+00:00", "modelAddress": "https://modelscope.cn/models/hf/BennyDaBall-Mistral-44B-MoE-Patched-MLX-4bit-G64", "repoId": "hf/BennyDaBall-Mistral-44B-MoE-Patched-MLX-4bit-G64", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993105+00:00", "framework": "vllm_tokenizer_patch", "intentId": "34772fd1ab4f4fc795fc82c4ef3b44b7", "lastModified": "2026-10-19T18:55:19+00:00", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-2.1-FP8-dynamic", "repoId": "shisa-ai/shisa-de-2.1-FP8-dynamic", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993153+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c5f1ade7245a484f83474a90aba3011e", "lastModified": "2026-10-21T13:30:22+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4-14B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4-14B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993213+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a236263787e9401585db3fa9aa7dae59", "lastModified": "2026-10-21T15:53:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993261+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d04d6ce10f814785a76c5dc363fb74be", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993308+00:00", "framework": "vllm_tokenizer_patch", "intentId": "66f8fed8813b4163a5efede689b5b20c", "lastModified": "2026-10-21T13:20:37+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993357+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a934d3d3d5c7455cabe732a650d4df0f", "lastModified": "2026-10-21T16:49:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "repoId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993404+00:00", "framework": "vllm_tokenizer_patch", "intentId": "dade2d9dfe524014a4ad7f759fb11c1d", "lastModified": "2026-10-21T16:31:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993452+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a4b7e21414e8451f947f17b92d862ab7", "lastModified": "2026-10-21T17:00:21+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2-8B-A1B-AWQ-4bit", "repoId": "cyankiwi/LFM2-8B-A1B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993500+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a2ef83b96d6e4a338505a8f8bd9a1e29", "lastModified": "2026-10-19T21:32:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Agents-A1-AWQ-NVFP4", "repoId": "cyankiwi/Agents-A1-AWQ-NVFP4", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993547+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d6c1afd6165f465dbc0a401f43e255fd", "lastModified": "2026-10-21T15:03:47+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-4B-Thinking-AWQ-8bit", "repoId": "cyankiwi/DASD-4B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993595+00:00", "framework": "vllm_tokenizer_patch", "intentId": "25fd18b010054997bd4560df56cee731", "lastModified": "2026-10-21T16:58:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-4bit", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993643+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b883e3935da24952b1cc632efb14afaa", "lastModified": "2026-10-21T17:09:55+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993691+00:00", "framework": "vllm_tokenizer_patch", "intentId": "02bdaf0b5084474f890305c500638070", "lastModified": "2026-10-21T16:41:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993739+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d960894c735e43a983867cf5c6798933", "lastModified": "2026-10-21T12:34:41+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.7-Flash-AWQ-8bit", "repoId": "cyankiwi/GLM-4.7-Flash-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993777+00:00", "framework": "vllm_tokenizer_patch", "intentId": "15f401f2e56143e88e0bb266ef79ee92", "lastModified": "2026-10-19T17:58:37+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-4bit", "repoId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993813+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3f8dfd046781479ea736c8fd6c1541df", "lastModified": "2026-10-20T13:37:13+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.0-35B-AWQ-INT4", "repoId": "cyankiwi/Ornith-1.0-35B-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993849+00:00", "framework": "vllm_tokenizer_patch", "intentId": "48fb41feeb834df7a5e25abbb78542d6", "lastModified": "2026-10-20T13:32:09+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Agents-A1-AWQ-INT4", "repoId": "cyankiwi/Agents-A1-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993884+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b3a0946fac7845fe924cb74a33fdbd1a", "lastModified": "2026-10-21T15:40:49+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-4bit-MLX", "repoId": "ukisai/Swift-1.5-4bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993920+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2a595798c9db4e9b80e4fa7ccf93b664", "lastModified": "2026-10-19T17:03:22+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-30B-A3B-Instruct-2507-AWQ-8bit", "repoId": "cpatonn-mirror/Qwen3-30B-A3B-Instruct-2507-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993956+00:00", "framework": "vllm_tokenizer_patch", "intentId": "62c9e03776ce40249bd7b7a9f02548fa", "lastModified": "2026-10-21T13:51:06+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/LFM2-24B-A2B-AWQ-8bit", "repoId": "cyankiwi/LFM2-24B-A2B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.993992+00:00", "framework": "vllm_tokenizer_patch", "intentId": "90fc14b7f9314ed6b29c3dc8f64ebb77", "lastModified": "2026-10-21T17:21:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "repoId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994028+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c37e04d86ed84060bb0a1ed35aa50ccf", "lastModified": "2026-10-21T15:32:58+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-BF16-INT4", "repoId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994063+00:00", "framework": "vllm_tokenizer_patch", "intentId": "05b4332ce9d54949b8f92c4cc950e549", "lastModified": "2026-10-21T16:19:52+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994100+00:00", "framework": "vllm_tokenizer_patch", "intentId": "05c0d1193e1141a8ab874116a13575f8", "lastModified": "2026-10-21T16:24:38+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-5bit-MLX", "repoId": "ukisai/Swift-1.5-5bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994135+00:00", "framework": "vllm_tokenizer_patch", "intentId": "437a61c276bf447b822422955f5b4eba", "lastModified": "2026-10-19T17:56:37+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Coder-V2.5-Dev-AWQ-INT4", "repoId": "cyankiwi/KAT-Coder-V2.5-Dev-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994171+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ad0ab5de71914bb9b771c89d8bddf54f", "lastModified": "2026-10-19T17:49:37+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nex-N2-mini-AWQ-INT4", "repoId": "cyankiwi/Nex-N2-mini-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994216+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7b852c7939724dd79419dc76f039a85e", "lastModified": "2026-10-21T15:31:37+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Sage-A1.5-FP8", "repoId": "InternScience/Sage-A1.5-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994252+00:00", "framework": "vllm_tokenizer_patch", "intentId": "85355f79ab2c4875a18392748e726962", "lastModified": "2026-10-20T14:01:12+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.0-35B-AWQ-FP8", "repoId": "cyankiwi/Ornith-1.0-35B-AWQ-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994288+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2cde89ff92824a6a9a298f55000d2561", "lastModified": "2026-10-21T16:43:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Dev-72B-AWQ-4bit", "repoId": "cyankiwi/Kimi-Dev-72B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994324+00:00", "framework": "vllm_tokenizer_patch", "intentId": "feb2b4bdd95f407b8a59bc2091ab50ea", "lastModified": "2026-10-21T17:15:17+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4-70B-AWQ-4bit", "repoId": "cyankiwi/Hermes-4-70B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994360+00:00", "framework": "vllm_tokenizer_patch", "intentId": "ac4a14a1d58a49268a4de0d71682ec4d", "lastModified": "2026-10-20T13:33:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen-AgentWorld-35B-A3B-AWQ-FP8", "repoId": "cyankiwi/Qwen-AgentWorld-35B-A3B-AWQ-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994396+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1e189a49eccb462ebf866ddbd424190a", "lastModified": "2026-10-21T15:51:34+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/granite-4.0-h-tiny-AWQ-8bit", "repoId": "cyankiwi/granite-4.0-h-tiny-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994432+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f9968517bf6143459b37986cc8b6424c", "lastModified": "2026-10-19T18:19:51+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit", "repoId": "cpatonn-mirror/Qwen3-Next-80B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994474+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bcdf0c3be5e34cd98b5af4fa25851072", "lastModified": "2026-10-19T18:17:12+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "repoId": "cpatonn-mirror/Qwen3-4B-Instruct-2507-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994516+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bdb7e149917a4da69436431933c42fae", "lastModified": "2026-10-19T17:47:47+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-Coder-30B-A3B-Instruct-AWQ", "repoId": "cpatonn-mirror/Qwen3-Coder-30B-A3B-Instruct-AWQ", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994557+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9e659e9961d84ba58aa8f93045e4d22a", "lastModified": "2026-10-19T17:00:47+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-Next-80B-A3B-Thinking-AWQ-8bit", "repoId": "cpatonn-mirror/Qwen3-Next-80B-A3B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994626+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a559ddf894c44270b4a6676491473e09", "lastModified": "2026-10-21T19:51:23+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-3-Super-120B-A12B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994670+00:00", "framework": "vllm_fix_tokenizer", "intentId": "33ce835e5686467a885d43eff70fb3d6", "lastModified": "2026-10-21T17:12:30+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniMax-M2.5-REAP-139B-A10B-AWQ-4bit", "repoId": "cyankiwi/MiniMax-M2.5-REAP-139B-A10B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994728+00:00", "framework": "vllm_fix_tokenizer", "intentId": "9a4239a47be746a4879c234ae67d73de", "lastModified": "2026-10-20T14:24:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen-AgentWorld-35B-A3B-AWQ-INT4", "repoId": "cyankiwi/Qwen-AgentWorld-35B-A3B-AWQ-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994770+00:00", "framework": "vllm_fix_tokenizer", "intentId": "35b53c8766ae4d5bb1c8715c21f762c7", "lastModified": "2026-10-19T17:09:46+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "repoId": "cpatonn-mirror/Qwen3-4B-Thinking-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994811+00:00", "framework": "vllm_fix_tokenizer", "intentId": "752e1fee37694138bfe1bf3cd0646f06", "lastModified": "2026-10-21T14:41:08+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-4bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994853+00:00", "framework": "vllm_fix_tokenizer", "intentId": "6a56918390a84000b9de3e8f7d1ac48e", "lastModified": "2026-10-19T16:53:59+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Jan-v1-4B-AWQ-4bit", "repoId": "cpatonn-mirror/Jan-v1-4B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994895+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ba4242878aa94c28b1574d0991f75d08", "lastModified": "2026-10-19T18:03:45+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "repoId": "cpatonn-mirror/Seed-OSS-36B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994936+00:00", "framework": "vllm_fix_tokenizer", "intentId": "5748f5e5297e473193f191cc54278707", "lastModified": "2026-10-20T08:50:37+00:00", "modelAddress": "https://modelscope.cn/models/Haodong07/Qwen3-32B-TwinQuant-W4A4", "repoId": "Haodong07/Qwen3-32B-TwinQuant-W4A4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.994978+00:00", "framework": "vllm_fix_tokenizer", "intentId": "31b617ee3c5c47c8b6cd5a4ffa6b59bc", "lastModified": "2026-10-21T15:40:57+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995019+00:00", "framework": "vllm_fix_tokenizer", "intentId": "a264a446a06b4ab7bd5a4f8a1f4f70d1", "lastModified": "2026-10-21T16:06:54+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/GLM-4.5-Air-Derestricted-AWQ-4bit", "repoId": "cyankiwi/GLM-4.5-Air-Derestricted-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995060+00:00", "framework": "vllm_fix_tokenizer", "intentId": "17c41ec5eef4434f9162d61520c418f2", "lastModified": "2026-10-19T17:25:36+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Hermes-4-70B-AWQ-8bit", "repoId": "cpatonn-mirror/Hermes-4-70B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995102+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ce16757c362745fbabe916766294fb3e", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995143+00:00", "framework": "vllm_fix_tokenizer", "intentId": "0f7ad623290648cd9bb923eb9d0dcee8", "lastModified": "2026-10-19T16:44:42+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/Jan-v1-2509-AWQ-4bit", "repoId": "cpatonn-mirror/Jan-v1-2509-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995196+00:00", "framework": "vllm_fix_tokenizer", "intentId": "966f65d60df5441ab3cd2a33c5cd0ed9", "lastModified": "2026-10-19T17:23:16+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "repoId": "cpatonn-mirror/granite-4.0-h-small-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995237+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e3d1b26064a641b8bcc1289f3a41d609", "lastModified": "2026-10-19T17:33:23+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-micro-AWQ-8bit", "repoId": "cpatonn-mirror/granite-4.0-h-micro-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995278+00:00", "framework": "vllm_fix_tokenizer", "intentId": "4eaebc86b9e44d18b1aa4489af38c508", "lastModified": "2026-10-19T18:03:21+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "repoId": "cpatonn-mirror/granite-4.0-h-tiny-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995320+00:00", "framework": "vllm_fix_tokenizer", "intentId": "c0d39fdb75e44e9694c9d1290dc35078", "lastModified": "2026-10-20T14:17:21+00:00", "modelAddress": "https://modelscope.cn/models/hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "repoId": "hf/esatapedico-MiniCPM-V-4.7-35B-A3B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995361+00:00", "framework": "vllm_fix_tokenizer", "intentId": "7412dd304e9045299992a1e5608d477b", "lastModified": "2026-10-21T13:48:58+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-Next-80B-A3B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Qwen3-Next-80B-A3B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995402+00:00", "framework": "vllm_fix_tokenizer", "intentId": "38abd91062194da2ae02387b1739fd8b", "lastModified": "2026-10-21T15:39:54+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Dev-72B-AWQ-8bit", "repoId": "cyankiwi/Kimi-Dev-72B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995444+00:00", "framework": "vllm_fix_tokenizer", "intentId": "f85171932fc14cd5bd6bf9b0f19920b9", "lastModified": "2026-10-21T16:25:01+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "repoId": "cyankiwi/MiniMax-M2.1-REAP-139B-A10B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995485+00:00", "framework": "vllm_fix_tokenizer", "intentId": "85f7d0e978ff404ab36b8c092f799f1d", "lastModified": "2026-10-21T14:18:30+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Orchestrator-8B-AWQ-8bit", "repoId": "cyankiwi/Orchestrator-8B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995526+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ac5ee7b78311410c8e67126ebe01c0c7", "lastModified": "2026-10-20T12:49:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.0-9B-AWQ-FP8", "repoId": "cyankiwi/Ornith-1.0-9B-AWQ-FP8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995567+00:00", "framework": "vllm_fix_tokenizer", "intentId": "b963e5f0182b4c2f8c0df742c825d8fd", "lastModified": "2026-10-21T15:29:56+00:00", "modelAddress": "https://modelscope.cn/models/InternScience/Sage-A1.5", "repoId": "InternScience/Sage-A1.5", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995608+00:00", "framework": "vllm_fix_tokenizer", "intentId": "25c620324cb04817b9d5ceb7cbc0f277", "lastModified": "2026-10-19T22:18:56+00:00", "modelAddress": "https://modelscope.cn/models/cpatonn-mirror/granite-4.0-h-micro-AWQ-4bit", "repoId": "cpatonn-mirror/granite-4.0-h-micro-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995650+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cc85153b7fb54815931795d6a31630bc", "lastModified": "2026-10-21T15:59:12+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995691+00:00", "framework": "vllm_fix_tokenizer", "intentId": "cff17ce8e9ce4b5bb90ef1559dfe0f73", "lastModified": "2026-10-21T14:42:38+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Jan-v1-4B-AWQ-8bit", "repoId": "cyankiwi/Jan-v1-4B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995732+00:00", "framework": "vllm_fix_tokenizer", "intentId": "3afa6a3d6c7b461b8463f107098299c3", "lastModified": "2026-10-21T17:24:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Orchestrator-8B-AWQ-4bit", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995773+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bb9e08cd004e4b1ba964d1611170e39b", "lastModified": "2026-10-21T14:56:09+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Trinity-Mini-AWQ-4bit", "repoId": "cyankiwi/Trinity-Mini-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995815+00:00", "framework": "vllm_fix_tokenizer", "intentId": "70bb8c25958746efb08cafb71cf13d40", "lastModified": "2026-10-21T17:21:32+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Solar-Open-100B-AWQ-4bit", "repoId": "cyankiwi/Solar-Open-100B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995857+00:00", "framework": "vllm_fix_tokenizer", "intentId": "ddc4fb031abc49d7845d7a1ec03952b2", "lastModified": "2026-10-21T16:52:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Hermes-4-70B-AWQ-8bit", "repoId": "cyankiwi/Hermes-4-70B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995898+00:00", "framework": "vllm_fix_tokenizer", "intentId": "586c75bcc87d4f858b5c9eb14bece21e", "lastModified": "2026-10-21T17:02:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995939+00:00", "framework": "vllm_fix_tokenizer", "intentId": "47d2b133088d4a30ac14f785b8341f57", "lastModified": "2026-10-20T12:54:20+00:00", "modelAddress": "https://modelscope.cn/models/Aleph-Alpha/Kolibri-1", "repoId": "Aleph-Alpha/Kolibri-1", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.995981+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2d56b18cec3e4fb6b0d244e9607b7dc0", "lastModified": "2026-10-21T17:00:11+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/command-a-reasoning-08-2025-AWQ-4bit", "repoId": "cyankiwi/command-a-reasoning-08-2025-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.996022+00:00", "framework": "vllm-patch-tokenizer", "intentId": "887686c28d0747a3bddb4333e08899f9", "lastModified": "2026-10-21T15:19:39+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit", "repoId": "cyankiwi/Qwen3-Next-80B-A3B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.996063+00:00", "framework": "vllm-patch-tokenizer", "intentId": "c24ff11e2c9f4df992da7c8093f17a8e", "lastModified": "2026-10-21T16:25:00+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-4B-Thinking-AWQ-4bit", "repoId": "cyankiwi/DASD-4B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "94b1b8777304415f842d6e7d6fb32728", "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:17:42.996104+00:00", "framework": "vllm-patch-tokenizer", "intentId": "3dbd779799f34dea8f4b53aeba90abca", "lastModified": "2026-10-21T13:46:58+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-8bit", "repoId": "cyankiwi/Qwen3-Coder-30B-A3B-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "133a4291c5f74fd39752cdcf194307f9", "completedAt": "2026-10-21T21:14:50.234152+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:14:47.554811+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0ea455edb553416e954d5635b014a879", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
{"batchId": "133a4291c5f74fd39752cdcf194307f9", "completedAt": "2026-10-21T21:14:50.234150+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:14:47.554769+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a56d884c61d348829bfb1cbb1c634a51", "repoId": "cyankiwi/Olmo-3.1-32B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}
{"batchId": "133a4291c5f74fd39752cdcf194307f9", "completedAt": "2026-10-21T21:14:50.234147+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-21T21:14:47.554727+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f4e1b6aa8db049369cd7aa10bff0120e", "repoId": "cyankiwi/Hermes-4.3-36B-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "MetaX_c-500", "taskId": null, "taskType": "text-generation"}

View File

@@ -1,25 +1,25 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/account_capacity.json": "116f071976d3b7ab4ba369fd339b060b453ed3209a300c29c3841bc9621add27",
".modelhub_state/architecture_compatibility_blacklist.json": "689b8220cde89525b386e2fe52006ce01f3b2fadcb6bb3c9b9f42f50e4d6aea2",
".modelhub_state/account_capacity.json": "e2960b50c753610dd6d74bf7ae42fe64e6191ebe6b626afc56c50e9e35a0b1e8",
".modelhub_state/architecture_compatibility_blacklist.json": "df284d30a072354f690809a950f506a5f7338ba8720eea2c3a16967540507941",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "54c897dcf8148f0de984f7ce63ab51e78bf738d2dc9bc75d1712c2c0e389c247",
".modelhub_state/official_capabilities.json": "175ba6c3390647dfc165c961bc8ce8bf42b988fd3a82f12c1077d28c1d932727",
".modelhub_state/outcome_checkpoint.json": "1dbb2df8b900924819852db215df30d5a01fc629237643d2fe09a1a333098e4c",
".modelhub_state/queue_cleanup_latest.json": "23cfeef48bc7431e8361d3b0c33331cfd06e3fb441f938693ff0c82387ec231e",
".modelhub_state/recent_outcomes.jsonl": "6a0403b1b4a9a9c26e6518199fc6077c3b4d9175d71ca278de8d340a67d88656",
".modelhub_state/market_intelligence.json": "20754957c137862a4b68aec9fd6a4c82432a5afc42afe8f40a766755ad9d776a",
".modelhub_state/official_capabilities.json": "daf06f84a794ca9310da9d0a351e6b2f75e8ce581aaee28084a64e5528b95908",
".modelhub_state/outcome_checkpoint.json": "87ab5eb8fb75e4c51b90739c5e2afc35a64a45902edf1356e8398e143a08fe6b",
".modelhub_state/queue_cleanup_latest.json": "b67fc6e71b665b469c0b8f1060489f9a4576a19360fe903b851afb4d73ba1292",
".modelhub_state/recent_outcomes.jsonl": "560ef09c7ac0e403e5196c3da85a6a3e4d6221a7a03bd8a2c00da647bb7d1c6c",
".modelhub_state/recovery_active_tasks.jsonl": "d11ba13df2b8f347a4b304bf1ac179650e4e51ec38ce1942713320e6ae77855a",
".modelhub_state/recovery_intents.jsonl": "535ee47aadc764f18c57c432c7256f8656e3fe1b66b19205bb9814699b620fe9",
".modelhub_state/recovery_intents.jsonl": "b55344ea714a808f2aad52e2b4a8f3377ee8de60eab633d43fbec78b6fbfb924",
".modelhub_state/routing_intelligence.json": "5589e1908ceb1f969ecae089cad7abe5072be7a812c6608d24dc9068c32ff2cb",
".modelhub_state/submission_exclusions.jsonl": "e2677e09d968a0c44c65d7c030b9c8ea2c9d39dc378ce302c2a309ab54d600d9",
".modelhub_state/worker_crashes.jsonl": "7ec5c580696be9e252968d3b24d3fe50028c3bb63d0549fafeb5a34732dade21",
"ledger/submissions.jsonl": "3114431f61c96a0f603c7847f36c67cfc3e81102d44a6beb8276200e5da4d169",
"outcomes/submissions.jsonl": "a1d2696283c3a865ca349450b690bb3fb061b10295bd1622a6be0952532f3ea5"
"outcomes/submissions.jsonl": "bf2e7b18a445480170a199431e1ef7a2e5491b3b8eebba63b4ad3d16afa8dd42"
},
"generation": 27804,
"phase": "cycle",
"generation": 27805,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-10-21T21:14:53.138243+00:00",
"updatedAt": "2026-10-21T21:17:43.212782+00:00",
"writerId": "d3d6980b05264495beb8a7e113a1076c"
}

View File

@@ -385,7 +385,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.348070+00:00", "modelId": "theGAI/MiniCPM5-1B-FullSFT-swift-mixture", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-10-06T08:52:27.070041+00:00", "targetGpu": "Biren_166m", "taskId": "5320000", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347826+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "2026-10-06T08:52:27.149663+00:00", "targetGpu": "Biren_166m", "taskId": "5320006", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.348016+00:00", "modelId": "juspay/Xor-26B-A4B", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51612008428, "estimatedRequiredGiB": 57.717, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 51644378597, "modelscopeLicense": "apache-2.0", "modelscopeParams": 25805936206, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 51644378597}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.148128+00:00", "targetGpu": "Biren_166m", "taskId": "5320005", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347884+00:00", "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.158144+00:00", "targetGpu": "Biren_166m", "taskId": "5320010", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347970+00:00", "modelId": "PleIAs/Baguettotron-MoE", "modelProfile": {"architectures": ["BaguettotronMoeForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "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": "2026-10-06T08:52:27.255211+00:00", "targetGpu": "Biren_166m", "taskId": "5320013", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347654+00:00", "modelId": "PleIAs/baguettotron-600m", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "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": "2026-10-06T08:52:27.261925+00:00", "targetGpu": "Biren_166m", "taskId": "5320012", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T16:58:45.347576+00:00", "modelId": "Altworld/Hemmingway-1", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54641496528, "estimatedRequiredGiB": 61.09, "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": 54662159810, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:chat", "custom_tag:creative-writing", "custom_tag:altworld"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54662159810}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:27.253624+00:00", "targetGpu": "Biren_166m", "taskId": "5320011", "taskType": "text-generation", "verifyResult": null}
@@ -716,8 +715,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T18:58:03.557051+00:00", "modelId": "ConwayResearch/Underdog-Woof-2B-1.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "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:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426023876}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T10:54:26.451820+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5378609", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T19:08:51.946595+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20321390048, "estimatedRequiredGiB": 22.734, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20341996128, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "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"], "publishedSizeBytes": 20341996128, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 20341996128, "repositoryOnDiskBytes": 20341996128}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T11:06:58.758797+00:00", "targetGpu": "Biren_166m", "taskId": "5378774", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T21:09:25.152940+00:00", "modelId": "ddalcu/Qwen3.6-35B-A3B-MLX-Serve-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20877335295, "estimatedRequiredGiB": 23.362, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20904301636, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5_moe", "custom_tag:moe", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20904301636, "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-08T11:54:51.560590+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "recursiveRepositoryBytes": 20904301636, "repositoryOnDiskBytes": 20904301636}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T13:03:07.592706+00:00", "targetGpu": "Biren_166m", "taskId": "5380968", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T21:56:59.879198+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20321390048, "estimatedRequiredGiB": 22.734, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20341996128, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "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"], "publishedSizeBytes": 20341996128, "quantizationMethod": "compressed-tensors", "recursiveRepositoryBytes": 20341996128, "repositoryOnDiskBytes": 20341996128}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T13:51:49.669029+00:00", "targetGpu": "MetaX_c-500", "taskId": "5381694", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T21:56:59.879220+00:00", "modelId": "ddalcu/Qwen3.6-35B-A3B-MLX-Serve-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20877335295, "estimatedRequiredGiB": 23.362, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20904301636, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5_moe", "custom_tag:moe", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 20904301636, "quantizationMethod": null, "recursiveRepositoryBytes": 20904301636, "repositoryOnDiskBytes": 20904301636}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T13:51:49.654533+00:00", "targetGpu": "MetaX_c-500", "taskId": "5381695", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T22:16:16.258101+00:00", "modelId": "hf/jialinyyzz-humanizer", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23919549408, "estimatedRequiredGiB": 97.901, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 87598084350, "modelscopeLicense": "apache-2.0", "modelscopeParams": 11959730224, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:transformer", "library:gguf", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:humanizer", "custom_tag:transformers", "custom_tag:safetensors", "custom_tag:text-rewriting", "custom_tag:rewriting", "custom_tag:paraphrase", "custom_tag:style-transfer", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:gemma4", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 87598084350, "quantizationMethod": null, "recursiveRepositoryBytes": 87599899966, "repositoryOnDiskBytes": 87599899966}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T14:08:30.851629+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5381855", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-09T10:55:20.060371+00:00", "modelId": "oneday88/sirl-qwen2-5-32b-gurobi", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65527841584, "estimatedRequiredGiB": 73.251, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "published_repository_upper_bound", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 65543798189, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 32763876352, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 65543798189, "quantizationMethod": null, "recursiveRepositoryBytes": 65543797688, "repositoryOnDiskBytes": 65543798189}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T02:50:47.550486+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5392923", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-09T10:55:20.060351+00:00", "modelId": "oneday88/sirl-qwen2-5-7b-copt", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30462543808, "estimatedRequiredGiB": 34.08, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "published_repository_upper_bound", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 30494374461, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:", "task:text-generation"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 30494374461, "quantizationMethod": null, "recursiveRepositoryBytes": 30494374007, "repositoryOnDiskBytes": 30494374461}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T02:50:47.558273+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5392924", "taskType": "text-generation", "verifyResult": null}
@@ -734,7 +731,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-09T18:56:56.464950+00:00", "modelId": "ManniX-ITA/Qwen3.6-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429184344, "estimatedRequiredGiB": 58.619, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe_text", "modelscopeFileSize": 52451782841, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26213016704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:expert-pruning", "custom_tag:code", "custom_tag:mtp", "custom_tag:omnimergekit"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 52451782841, "quantizationMethod": null, "recursiveRepositoryBytes": 52451782841, "repositoryOnDiskBytes": 52451782841}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T10:52:17.252232+00:00", "targetGpu": "Biren_166m", "taskId": "5399158", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-09T20:54:47.764094+00:00", "modelId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6627366288, "estimatedRequiredGiB": 7.43, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1727664128, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "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:tool-use", "custom_tag:finance", "custom_tag:k2_horizon", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 6648353931, "repositoryOnDiskBytes": 6648353931}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T12:52:30.765636+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5401020", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-09T21:13:02.549148+00:00", "modelId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6627366288, "estimatedRequiredGiB": 7.43, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6648353931, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1727664128, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "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:tool-use", "custom_tag:finance", "custom_tag:k2_horizon", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 6648353931, "quantizationMethod": null, "recursiveRepositoryBytes": 6648353931, "repositoryOnDiskBytes": 6648353931}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T13:09:30.759470+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5401458", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-09T22:05:56.970146+00:00", "modelId": "ManniX-ITA/Qwen3.6-27B-A3B-Coder", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53319307872, "estimatedRequiredGiB": 59.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 53342531046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26659587952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:code", "custom_tag:expert-pruning", "custom_tag:qwen3.6"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 53342531046, "quantizationMethod": null, "recursiveRepositoryBytes": 53342531046, "repositoryOnDiskBytes": 53342531046}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T14:03:53.551952+00:00", "targetGpu": "MetaX_c-500", "taskId": "5402815", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-10T03:15:33.370635+00:00", "modelId": "lightonai/colgrep-agent-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "05ede70cae27525d29b4c44e2be02476a5362f2e8a93365f5c82cd3c918aa123", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1490355392, "estimatedRequiredGiB": 22.003, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 2516756480, "modelscopeTags": ["library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:code", "custom_tag:code-search", "custom_tag:colgrep", "custom_tag:agent", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": null, "quantizationMethod": null, "recursiveRepositoryBytes": 19687833658, "repositoryOnDiskBytes": 19687833658}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T19:02:12.450314+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5407638", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-10T03:31:27.249354+00:00", "modelId": "lightonai/colgrep-agent-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "3b82836fb5958ba363655971ed1f15d8109ab96526648b59a9c28586a1d7b2d6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1490355392, "estimatedRequiredGiB": 22.003, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 19687833658, "modelscopeLicense": null, "modelscopeParams": 2516756480, "modelscopeTags": ["library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:code", "custom_tag:code-search", "custom_tag:colgrep", "custom_tag:agent", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 19687833658, "quantizationMethod": null, "recursiveRepositoryBytes": 19687833658, "repositoryOnDiskBytes": 19687833658}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T19:18:44.203926+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5407882", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-10T06:22:55.444978+00:00", "modelId": "IQuestLab/SAIL", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70214494200, "estimatedRequiredGiB": 78.495, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 70236310573, "modelscopeLicense": "apache-2.0", "modelscopeParams": 19327352832, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sail", "custom_tag:science", "custom_tag:scientific-reasoning", "custom_tag:scientific-coding", "custom_tag:tool-use", "custom_tag:mixture-of-experts", "custom_tag:reinforcement-learning"], "modelscopeTasks": ["text-generation"], "publishedSizeBytes": 70236310573, "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-08T16:33:00.970365+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "recursiveRepositoryBytes": 70236310573, "repositoryOnDiskBytes": 70236310573}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-09T22:09:51.953595+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5410223", "taskType": "text-generation", "verifyResult": null}
@@ -806,7 +802,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-12T14:43:14.054431+00:00", "modelId": "h2oai/h2o-lightning-4b-nemotron-nano", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7947142672, "estimatedRequiredGiB": 8.901, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 7964754709, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-making", "custom_tag:calibration", "custom_tag:jevbench", "custom_tag:nemotron"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7964754709}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T06:32:52.848996+00:00", "targetGpu": "MetaX_c-500", "taskId": "5482888", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-12T14:43:14.054468+00:00", "modelId": "oneday88/sirl-qwen2-5-7b-copt", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30462543808, "estimatedRequiredGiB": 34.08, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 30494374461, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30494374461}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T06:32:52.754086+00:00", "targetGpu": "MetaX_c-500", "taskId": "5482884", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-12T14:43:14.054481+00:00", "modelId": "JetBrains/Mellum2.1-12B-A2.5B-Thinking", "modelProfile": {"architectures": ["MellumForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24300538808, "estimatedRequiredGiB": 27.167, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mellum", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:mellum", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24308363631}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T06:32:52.759633+00:00", "targetGpu": "MetaX_c-500", "taskId": "5482878", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-12T14:43:14.054499+00:00", "modelId": "ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24604826824, "estimatedRequiredGiB": 27.524, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 24628378755, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20349011824, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:ascend", "custom_tag:ascend310p", "custom_tag:w4a8", "custom_tag:mtp", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24628378853}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T06:32:52.752815+00:00", "targetGpu": "MetaX_c-500", "taskId": "5482883", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-12T14:43:14.054493+00:00", "modelId": "ConwayResearch/woof-1.0-4B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3034300817, "estimatedRequiredGiB": 3.421, "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": 3061126882, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:underdog", "custom_tag:browser-agent", "custom_tag:on-device"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3061126882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T06:32:52.847917+00:00", "targetGpu": "MetaX_c-500", "taskId": "5482885", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-12T14:43:14.054461+00:00", "modelId": "ConwayResearch/Underdog-Woof-4B-1.1", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2367237149, "estimatedRequiredGiB": 2.668, "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": 2387334789, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2387334789}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T06:32:52.842916+00:00", "targetGpu": "MetaX_c-500", "taskId": "5482882", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-12T14:43:14.054475+00:00", "modelId": "tsinghua-sigs-robot-lab/VeriLoop-E2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 55655301924, "estimatedRequiredGiB": 62.227, "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": 55679383091, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27872753616, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "task:text-generation", "custom_tag:conversational", "custom_tag:veriloop", "custom_tag:post-training", "custom_tag:coding-agent", "custom_tag:software-engineering", "custom_tag:mathematical-reasoning", "custom_tag:scientific-reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:safetensors", "custom_tag:vllm", "custom_tag:apache-2.0"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 55679383091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T06:32:52.762120+00:00", "targetGpu": "MetaX_c-500", "taskId": "5482881", "taskType": "text-generation", "verifyResult": null}
@@ -1019,7 +1014,6 @@
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-14T21:11:41.559932+00:00", "modelId": "OsaurusAI/LFM2.5-24B-A2B-JANG_4M", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15911910672, "estimatedRequiredGiB": 17.803, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 15930009890, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jang-4m", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:lfm2", "custom_tag:lfm2_moe", "custom_tag:moe", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-use", "custom_tag:agent", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15930009890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-14T13:02:57.162589+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5535636", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-14T21:11:41.559957+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-4bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13567294335, "estimatedRequiredGiB": 15.183, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 13585304925, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13585304925}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-14T13:02:57.155863+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5535634", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-14T22:37:47.741162+00:00", "modelId": "StartLuxAI/Qwen3.6-35B-A3B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24673571763, "estimatedRequiredGiB": 27.598, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6522539888, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "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:qwen3.6"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"参数/模板问题": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-12T18:40:58.271114+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 24693956069}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-14T14:20:21.643226+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5536730", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T22:37:47.741196+00:00", "modelId": "StartLuxAI/Qwen3.6-35B-A3B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24673571763, "estimatedRequiredGiB": 27.598, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6522539888, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "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:qwen3.6"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24693956069}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-14T14:36:16.300431+00:00", "targetGpu": "MetaX_c-500", "taskId": "5536994", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-14T23:36:11.477879+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-4bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13567294335, "estimatedRequiredGiB": 15.183, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 13585304925, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13585304925}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-14T15:32:04.363220+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5539021", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-14T23:36:11.477897+00:00", "modelId": "StartLuxAI/Qwen3.6-35B-A3B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24673571763, "estimatedRequiredGiB": 27.598, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6522539888, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "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:qwen3.6"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"参数/模板问题": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_0_17_0_corex_4_4_0", "lastTerminalAt": "2026-10-12T18:40:58.271099+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 24693956069}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-14T15:32:04.355811+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5539022", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-15T00:16:58.740648+00:00", "modelId": "LiquidAI/LFM2.5-24B-A2B-MLX-4bit", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13567294335, "estimatedRequiredGiB": 15.183, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 13585304925, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:moe", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13585304925}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-14T16:07:40.271573+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5539800", "taskType": "text-generation", "verifyResult": null}