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

state: compacted generation 6801

Browse Source
This commit is contained in:
CoolBoy
2026-09-13 16:14:45 +00:00
commit a051842df5
22 changed files with 20789 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

0
.manifest.json.lock Normal file
View File

0
.modelhub_state/.market_intelligence.json.lock Normal file
View File

0
.modelhub_state/.official_capabilities.json.lock Normal file
View File

0
.modelhub_state/.recent_outcomes.jsonl.lock Normal file
View File

0
.modelhub_state/.worker_crashes.jsonl.lock Normal file
View File

1498
.modelhub_state/architecture_compatibility_blacklist.json Normal file
View File

File diff suppressed because it is too large Load Diff

113
.modelhub_state/architecture_history_backfill.json Normal file
View File

@@ -0,0 +1,113 @@
{
"accounts": {
"0": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 494,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
},
"1": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
},
"10": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
},
"11": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
},
"2": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
},
"3": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
},
"4": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
},
"5": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
},
"6": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
},
"7": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
},
"8": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
},
"9": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 493,
"nextPage": 1,
"recordsScanned": 0,
"uniqueRecords": 0
}
},
"architectureBlocks": 0,
"complete": false,
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0,
"mode": "incremental_decision_only",
"nextAccountIndex": 1,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-13T16:14:45.177807+00:00",
"version": 1
}

754
.modelhub_state/market_intelligence.json Normal file
View File

@@ -0,0 +1,754 @@
{
"communityAttemptedAt": "2026-09-13T16:12:47.349932+00:00",
"communityError": null,
"communitySample": {},
"communityUpdatedAt": "2026-09-13T16:12:47.349932+00:00",
"frameworkAttemptedAt": "2026-09-13T12:45:47.364313+00:00",
"frameworkError": null,
"frameworkStats": {
"text-generation": {
"Ascend_910-b3": {
"llamacpp": {
"framework": "llamacpp",
"modelCount": 38776,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 18600,
"successRate": 0.4796781514338766,
"wilsonLowerBound": 0.4747077870644458
},
"vllm": {
"framework": "vllm",
"modelCount": 51329,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 14469,
"successRate": 0.2818874320559528,
"wilsonLowerBound": 0.27801154412310947
},
"vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch",
"modelCount": 2066,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 549,
"successRate": 0.26573088092933206,
"wilsonLowerBound": 0.24713083000635674
}
},
"Ascend_910-b4": {
"llamacpp": {
"framework": "llamacpp",
"modelCount": 31922,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 13858,
"successRate": 0.43412066913100683,
"wilsonLowerBound": 0.42869168181785944
},
"vllm": {
"framework": "vllm",
"modelCount": 36971,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 10547,
"successRate": 0.28527765005003924,
"wilsonLowerBound": 0.2806972814723312
},
"vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch",
"modelCount": 7622,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 3374,
"successRate": 0.4426659669378116,
"wilsonLowerBound": 0.4315465279998519
}
},
"Biren_166m": {
"vllm": {
"framework": "vllm",
"modelCount": 63837,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 12065,
"successRate": 0.18899697667496906,
"wilsonLowerBound": 0.18597862901674025
},
"vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer",
"modelCount": 15463,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 3118,
"successRate": 0.2016426307960939,
"wilsonLowerBound": 0.19539298243335687
},
"vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch",
"modelCount": 5478,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 45,
"successRate": 0.008214676889375685,
"wilsonLowerBound": 0.006145143024973394
}
},
"Cambricon_mlu-370-x4": {
"vllm": {
"framework": "vllm",
"modelCount": 26032,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 3198,
"successRate": 0.12284880147510756,
"wilsonLowerBound": 0.11891663308981092
},
"vllm-customized": {
"framework": "vllm-customized",
"modelCount": 16457,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 1672,
"successRate": 0.10159810415020963,
"wilsonLowerBound": 0.09707475831962524
},
"vllm-mlu": {
"framework": "vllm-mlu",
"modelCount": 10010,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 4299,
"successRate": 0.4294705294705295,
"wilsonLowerBound": 0.4198022447157606
}
},
"Cambricon_mlu-370-x8": {
"vllm": {
"framework": "vllm",
"modelCount": 24070,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 3777,
"successRate": 0.15691732447029497,
"wilsonLowerBound": 0.15237708044032894
},
"vllm-customized": {
"framework": "vllm-customized",
"modelCount": 8066,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 544,
"successRate": 0.0674435903793702,
"wilsonLowerBound": 0.0621738174048722
},
"vllm-mlu": {
"framework": "vllm-mlu",
"modelCount": 40629,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 10251,
"successRate": 0.2523074651111275,
"wilsonLowerBound": 0.24810759476921498
}
},
"Iluvatar_bi-100": {
"transformers": {
"framework": "transformers",
"modelCount": 22984,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 3035,
"successRate": 0.13204838148277062,
"wilsonLowerBound": 0.1277329965860188
},
"vllm": {
"framework": "vllm",
"modelCount": 86521,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 9762,
"successRate": 0.1128280995365287,
"wilsonLowerBound": 0.11073708553293825
},
"vllm-patch-tokenizer": {
"framework": "vllm-patch-tokenizer",
"modelCount": 39116,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 4801,
"successRate": 0.12273749872175069,
"wilsonLowerBound": 0.11952263161825838
},
"vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer",
"modelCount": 27920,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 3300,
"successRate": 0.11819484240687679,
"wilsonLowerBound": 0.11446036420870193
}
},
"Iluvatar_bi-150": {
"llamacpp": {
"framework": "llamacpp",
"modelCount": 87754,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 20509,
"successRate": 0.23371014426692802,
"wilsonLowerBound": 0.23092183877771638
},
"transformers": {
"framework": "transformers",
"modelCount": 5092,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 562,
"successRate": 0.11036920659858601,
"wilsonLowerBound": 0.10205438887492263
},
"vllm": {
"framework": "vllm",
"modelCount": 112456,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 16504,
"successRate": 0.14675962154086933,
"wilsonLowerBound": 0.14470343487009737
},
"vllm_0_17_0_corex_4_4_0": {
"framework": "vllm_0_17_0_corex_4_4_0",
"modelCount": 15897,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 3257,
"successRate": 0.20488142416808203,
"wilsonLowerBound": 0.19867877038801196
},
"vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer",
"modelCount": 42646,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 5546,
"successRate": 0.13004736669324204,
"wilsonLowerBound": 0.12688827251420284
},
"vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch",
"modelCount": 6225,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 486,
"successRate": 0.0780722891566265,
"wilsonLowerBound": 0.07166474517615269
}
},
"Iluvatar_mrv-100": {
"transformers": {
"framework": "transformers",
"modelCount": 198,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 36,
"successRate": 0.18181818181818182,
"wilsonLowerBound": 0.1343204258911728
},
"vllm": {
"framework": "vllm",
"modelCount": 30321,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 5252,
"successRate": 0.1732132845222783,
"wilsonLowerBound": 0.16899512321688287
}
},
"Kunlunxin_p-800": {
"vllm": {
"framework": "vllm",
"modelCount": 60768,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 12379,
"successRate": 0.20370918904686677,
"wilsonLowerBound": 0.2005256816798767
},
"vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer",
"modelCount": 6518,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 1930,
"successRate": 0.2961030991101565,
"wilsonLowerBound": 0.28514236738560983
},
"vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch",
"modelCount": 12032,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 3150,
"successRate": 0.26180186170212766,
"wilsonLowerBound": 0.2540235257765174
}
},
"MetaX_c-500": {
"vllm": {
"framework": "vllm",
"modelCount": 59160,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 16107,
"successRate": 0.27226166328600404,
"wilsonLowerBound": 0.26868960698459193
}
},
"Mthreads_s4000": {
"llamacpp": {
"framework": "llamacpp",
"modelCount": 46085,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 20045,
"successRate": 0.4349571444070739,
"wilsonLowerBound": 0.43043648389347655
},
"vllm": {
"framework": "vllm",
"modelCount": 35758,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 3122,
"successRate": 0.08730913362044856,
"wilsonLowerBound": 0.08442737563289227
},
"vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch",
"modelCount": 288,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 0,
"successRate": 0.0,
"wilsonLowerBound": 0.0
}
},
"Sunrise_pt-200-x1": {
"sglang": {
"framework": "sglang",
"modelCount": 6275,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 192,
"successRate": 0.03059760956175299,
"wilsonLowerBound": 0.026615110833495575
},
"vllm": {
"framework": "vllm",
"modelCount": 10007,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 733,
"successRate": 0.07324872589187569,
"wilsonLowerBound": 0.06830595957327275
},
"vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer",
"modelCount": 5576,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 2345,
"successRate": 0.42055236728837875,
"wilsonLowerBound": 0.4076541911130345
}
},
"Vastai_va16": {
"vllm": {
"framework": "vllm",
"modelCount": 7367,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 235,
"successRate": 0.0318990090946111,
"wilsonLowerBound": 0.02812370043844604
},
"vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer",
"modelCount": 10616,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 3627,
"successRate": 0.34165410700828935,
"wilsonLowerBound": 0.33269097842653206
}
},
"hygon_k100-ai": {
"llamacpp": {
"framework": "llamacpp",
"modelCount": 25997,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 13139,
"successRate": 0.5054044697465092,
"wilsonLowerBound": 0.49932642259994464
},
"vllm": {
"framework": "vllm",
"modelCount": 60824,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 5947,
"successRate": 0.0977739050374852,
"wilsonLowerBound": 0.09543883390793778
},
"vllm-patch-tokenizer": {
"framework": "vllm-patch-tokenizer",
"modelCount": 12224,
"officialConfigError": null,
"officialConfigValid": true,
"successCount": 1722,
"successRate": 0.14087041884816753,
"wilsonLowerBound": 0.13481597404972345
}
}
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-13T16:12:47.349932+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1024.2043795620439,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.2167713942907779,
"queueFactor": 0.9826931162695574,
"queueWeight": 0.9826931162695574,
"recentSuccess": 51,
"recentSuccessRate": 0.3722627737226277,
"recentTerminal": 137,
"recentWilsonLowerBound": 0.2958339238729821,
"running": 8,
"selectionWeight": 1.1957128732432587,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.833333333333332,
"waiting": 23386
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1033.05,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.7729397387491526,
"queueFactor": 0.9814263337087059,
"queueWeight": 0.9814263337087059,
"recentSuccess": 68,
"recentSuccessRate": 0.425,
"recentTerminal": 160,
"recentWilsonLowerBound": 0.35104220189233704,
"running": 8,
"selectionWeight": 1.7400097476870517,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 26.666666666666668,
"waiting": 27548
},
"Biren_166m": {
"available": true,
"backlogHours": 148.10526315789474,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.18748423700390524,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 33,
"recentSuccessRate": 0.1736842105263158,
"recentTerminal": 190,
"recentWilsonLowerBound": 0.12642881010746768,
"running": 8,
"selectionWeight": 0.24372950810507682,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 31.666666666666668,
"waiting": 4690
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1708.6153846153848,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.952734546594375,
"queueFactor": 0.9100793522267958,
"queueWeight": 0.9100793522267958,
"recentSuccess": 20,
"recentSuccessRate": 0.38461538461538464,
"recentTerminal": 52,
"recentWilsonLowerBound": 0.26470271334885215,
"running": 7,
"selectionWeight": 0.8670640390086988,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.666666666666666,
"waiting": 14808
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 515.7142857142857,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.27561995931219274,
"queueFactor": 1.0892173081278982,
"queueWeight": 1.0892173081278982,
"recentSuccess": 23,
"recentSuccessRate": 0.21904761904761905,
"recentTerminal": 105,
"recentWilsonLowerBound": 0.15063031032976165,
"running": 7,
"selectionWeight": 0.3002100301483474,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.5,
"waiting": 9025
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 41.06842105263158,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 24,
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 7,
"recentSuccessRate": 0.018421052631578946,
"recentTerminal": 380,
"recentWilsonLowerBound": 0.008951068343728514,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 63.333333333333336,
"waiting": 2601
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 153.6727272727273,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 14,
"recentSuccessRate": 0.08484848484848485,
"recentTerminal": 165,
"recentWilsonLowerBound": 0.05121353901536126,
"running": 1,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 27.5,
"waiting": 4226
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2402.6153846153848,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.8321523546909206,
"queueFactor": 0.8647155524084364,
"queueWeight": 0.8647155524084364,
"recentSuccess": 15,
"recentSuccessRate": 0.38461538461538464,
"recentTerminal": 39,
"recentWilsonLowerBound": 0.24891162547007062,
"running": 2,
"selectionWeight": 0.7195750830745405,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 6.5,
"waiting": 15617
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 799.1428571428571,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.40677391311231403,
"queueFactor": 1.0199578970122474,
"queueWeight": 1.0199578970122474,
"recentSuccess": 22,
"recentSuccessRate": 0.2619047619047619,
"recentTerminal": 84,
"recentWilsonLowerBound": 0.1797835031577335,
"running": 7,
"selectionWeight": 0.41489226497747844,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.0,
"waiting": 11188
},
"MetaX_c-500": {
"available": true,
"backlogHours": 670.6601941747572,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.53577521379662,
"queueFactor": 1.0471298225124224,
"queueWeight": 1.0471298225124224,
"recentSuccess": 29,
"recentSuccessRate": 0.2815533980582524,
"recentTerminal": 103,
"recentWilsonLowerBound": 0.20376373626988126,
"running": 4,
"selectionWeight": 0.5610262045294098,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.166666666666668,
"waiting": 11513
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1927.9130434782608,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.0101136547691718,
"queueFactor": 0.893743285148956,
"queueWeight": 0.893743285148956,
"recentSuccess": 26,
"recentSuccessRate": 0.37681159420289856,
"recentTerminal": 69,
"recentWilsonLowerBound": 0.2718335694978672,
"running": 4,
"selectionWeight": 0.902782296187218,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.5,
"waiting": 22171
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 4610.21052631579,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 2.5,
"queueFactor": 0.7841836703781249,
"queueWeight": 0.7841836703781249,
"recentSuccess": 12,
"recentSuccessRate": 0.631578947368421,
"recentTerminal": 19,
"recentWilsonLowerBound": 0.41039157498156714,
"running": 2,
"selectionWeight": 1.9604591759453123,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 3.1666666666666665,
"waiting": 14599
},
"Vastai_va16": {
"available": true,
"backlogHours": 1075.4117647058822,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.38091814310029976,
"queueFactor": 0.9755278909256485,
"queueWeight": 0.9755278909256485,
"recentSuccess": 18,
"recentSuccessRate": 0.2647058823529412,
"recentTerminal": 68,
"recentWilsonLowerBound": 0.17449602975254203,
"running": 16,
"selectionWeight": 0.3715962727539498,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.333333333333334,
"waiting": 12188
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 686.5882352941177,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 1.0444350930141186,
"queueFactor": 1.0434495461730109,
"queueWeight": 1.0434495461730109,
"recentSuccess": 37,
"recentSuccessRate": 0.3627450980392157,
"recentTerminal": 102,
"recentWilsonLowerBound": 0.275993652652253,
"running": 6,
"selectionWeight": 1.0898153238127486,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.0,
"waiting": 11672
}
},
"queueAttemptedAt": "2026-09-13T16:04:11.081766+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-13T16:04:11.081766+00:00",
"supportedGpus": [
"Vastai_va16",
"Iluvatar_mrv-100",
"Kunlunxin_p-800",
"Cambricon_mlu-370-x4",
"Iluvatar_bi-150",
"Ascend_910-b4",
"hygon_k100-ai",
"Ascend_910-b3",
"MetaX_c-500",
"Sunrise_pt-200-x1",
"Iluvatar_bi-100",
"Biren_166m",
"Cambricon_mlu-370-x8",
"Mthreads_s4000"
],
"taskTypes": [
"text-generation"
],
"throughputWindowHours": 6,
"version": 3
}

6766
.modelhub_state/official_capabilities.json Normal file
View File

File diff suppressed because it is too large Load Diff

7527
.modelhub_state/outcome_checkpoint.json Normal file
View File

File diff suppressed because it is too large Load Diff

172
.modelhub_state/queue_cleanup_latest.json Normal file
View File

@@ -0,0 +1,172 @@
{
"accountCapacityLimits": [
100,
100,
100,
100,
100,
100,
100,
100,
100,
100,
100,
100
],
"accounts": 12,
"activeScanned": 1015,
"ageCleanupMode": "admission_only",
"agePolicySkipped": {
"cleanupDisabled": true,
"reason": "admission_only"
},
"architectureBlockCount": 74,
"architectureFrameworkCatalog": {
"ascend_910-b3|text-generation": [
"llamacpp",
"vllm",
"vllm_tokenizer_patch"
],
"ascend_910-b4|text-generation": [
"llamacpp",
"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",
"vllm-patch-tokenizer"
],
"iluvatar_bi-150|text-generation": [
"llamacpp",
"transformers",
"vllm",
"vllm_0_17_0_corex_4_4_0",
"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"
],
"mthreads_s4000|text-generation": [
"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": [],
"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)",
"LiquidAI/LFM2.5-230M-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/LiquidAI/LFM2.5-230M-GGUF/resolve/master/config.json (status=404)",
"b77968543/Spark-X2.5-4B-Q8_0": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/b77968543/Spark-X2.5-4B-Q8_0/resolve/master/config.json (status=404)",
"cgisky/Ai00-X": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/cgisky/Ai00-X/resolve/master/config.json (status=404)",
"empero-ai/Qwen3.8-2B-Distill-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/empero-ai/Qwen3.8-2B-Distill-GGUF/resolve/master/config.json (status=404)",
"empero-ai/Qwen3.8-4B-Distill-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill-GGUF/resolve/master/config.json (status=404)",
"empero-ai/Qwen3.8-9B-Distill-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill-GGUF/resolve/master/config.json (status=404)",
"empero-ai/Qwen3.8-9B-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/empero-ai/Qwen3.8-9B-GGUF/resolve/master/config.json (status=404)",
"ewinregirgojr/Qwen3.8-14B-Instruct-Turbo-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo-GGUF/resolve/master/config.json (status=404)",
"fengxiaohong/Qwen3.8-27B-Q8_0_GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/fengxiaohong/Qwen3.8-27B-Q8_0_GGUF/resolve/master/config.json (status=404)",
"guaidao2/XuanmuSec-2.6B": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/guaidao2/XuanmuSec-2.6B/resolve/master/config.json (status=404)",
"hf/douyamv-Qwen3.8-27B-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/hf/douyamv-Qwen3.8-27B-GGUF/resolve/master/config.json (status=404)",
"inclusionAI/Ling-3.0-tiny-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny-GGUF/resolve/master/config.json (status=404)",
"incoai/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/incoai/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)",
"ornith-ai/Ornith-1.0-9B-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/ornith-ai/Ornith-1.0-9B-GGUF/resolve/master/config.json (status=404)",
"ornith-ai/Ornith-1.5-9B-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-GGUF/resolve/master/config.json (status=404)",
"prithivMLmods/CogEvol-4B-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/prithivMLmods/CogEvol-4B-GGUF/resolve/master/config.json (status=404)",
"unsloth/LFM2-2.6B-Exp-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/unsloth/LFM2-2.6B-Exp-GGUF/resolve/master/config.json (status=404)",
"z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
},
"architectureModelConfigsComplete": 99,
"architectureOnly": false,
"architecturePolicySkipped": {
"frameworkCatalogUnknown": 0,
"frameworkContextUnknown": 282,
"modelArchitectureUnknown": 149,
"noMatchingBlock": 780,
"partiallyBlockedFrameworkSet": 86,
"runningMatchedProtected": 0,
"submissionContextMismatch": 0,
"submissionContextUnknown": 0
},
"cancelledCount": 0,
"cancelledTasks": [],
"certainOomCount": 0,
"certainOomTasks": [],
"cleanupCandidateCount": 0,
"dryRun": false,
"listingErrors": {},
"modelAgeErrors": {},
"modelAgeMetadataComplete": 0,
"noLongerActiveCount": 0,
"officialCapabilityCatalogError": null,
"officialCapabilityInvalidCount": 0,
"officialCapabilityInvalidTasks": [],
"oldModelQueueThresholds": [
95,
95,
95,
95,
95,
95,
95,
95,
95,
95,
95,
95
],
"oldOverflowCount": 0,
"oldOverflowTasks": [],
"policyCancelledRecorded": 0,
"policyNoLongerAppliesCount": 0,
"policyNoLongerAppliesTasks": [],
"recentModelDays": 7,
"recentModelReserveSlots": 5,
"repositorySizeErrors": {
"empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete"
},
"repositorySizesComplete": 244,
"skipped": {
"fitsKnownCapacity": 1013,
"gpuCapacityUnknown": 0,
"repositorySizeUnknown": 2
},
"stopErrors": [],
"uniqueModels": 245
}

300
.modelhub_state/recent_outcomes.jsonl Normal file
View File

@@ -0,0 +1,300 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "", "lastSyncTime": "2026-09-13T16:07:00.124635+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T16:01:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4595685", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-13T15:06:31.804323+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T14:59:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493602", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T13:43:30.144198+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T13:43:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332459", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-13T13:17:31.149556+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T13:11:21+00:00", "targetGpu": "Biren_166m", "taskId": "4349465", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T10:05:37.717736+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T09:59:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560059", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T09:40:23.641563+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T09:33:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4557415", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-13T08:31:12.943798+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T08:23:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4609080", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "", "lastSyncTime": "2026-09-13T06:31:13.105179+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T06:27:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610370", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-13T05:58:35.516166+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T05:53:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4558021", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-13T05:49:53.509642+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T05:47:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549640", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-13T05:03:23.648954+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4585193", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T04:23:07.613289+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:17:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4557614", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T04:05:56.910845+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T04:05:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4332432", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T04:05:56.910823+00:00", "modelId": "whcl412/mlx-LycheeAI-coder-1.7b", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T03:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458813", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T03:22:02.529658+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T03:21:22+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4558358", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-13T03:22:02.529638+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-13T03:15:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523217", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-13T03:12:57.550578+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T03:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549641", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-13T02:55:29.910704+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-13T02:51:53+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4133475", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-13T02:55:29.910734+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-13T02:51:53+00:00", "targetGpu": "MetaX_c-500", "taskId": "4133144", "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", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T02:55:29.910747+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:47:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4557197", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-13T02:47:03.906686+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549639", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-13T02:20:50.802489+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:13:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4549809", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-13T02:12:14.114155+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:09:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4543931", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-13T02:12:14.114179+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T02:05:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4543902", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-13T01:11:40.231412+00:00", "modelId": "XHToken/Spark-X2.5-1.7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T01:11:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4557834", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["gemma4"], "framework": "vllm", "lastSyncTime": "2026-09-13T00:10:37.716599+00:00", "modelId": "nv-community/Gemma-4-31B-IT-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T00:07:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079956", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-12T23:26:15.638604+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T23:23:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4582844", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T23:26:15.638629+00:00", "modelId": "nv-community/Gemma-4-31B-IT-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T23:21:21+00:00", "targetGpu": "Biren_166m", "taskId": "4186791", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T23:00:13.841305+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T22:55:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560062", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-12T22:34:15.509071+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T22:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4543802", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-12T21:39:57.012261+00:00", "modelId": "QuantTrio/KAT-Dev-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T21:29:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079182", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-12T21:28:41.303467+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T21:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523212", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-12T21:28:41.303490+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-12T21:25:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549638", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T20:49:10.452723+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T20:41:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4549113", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T20:28:29.094162+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T20:23:21+00:00", "targetGpu": "Biren_166m", "taskId": "4111539", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-12T19:23:45.302791+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T19:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4583368", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-12T18:59:53.316516+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T18:53:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4549470", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T17:16:49.913530+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T17:15:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4543650", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T17:06:34.916681+00:00", "modelId": "amd/Qwen2-7B-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T16:57:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079249", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-12T16:46:42.939263+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T16:43:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4610337", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T16:46:42.939235+00:00", "modelId": "amd/Qwen2-7B-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T16:39:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079071", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-12T16:46:42.939278+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T16:39:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4548919", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-12T16:02:54.728775+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T15:57:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4549114", "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": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-12T15:08:42.332272+00:00", "modelId": "QuantTrio/KAT-Dev-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T15:01:21+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4079960", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-12T14:41:33.434355+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T14:35:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4543632", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T14:12:46.256625+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T14:11:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4543480", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T13:37:49.606306+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T13:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4546528", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T13:02:08.318677+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T12:55:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560063", "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": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T12:17:17.415709+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-Apollo-V0.1-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T12:13:22+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079266", "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": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T11:41:06.016003+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Lite-Preview-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T11:37:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079092", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-12T11:23:23.155704+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T11:17:22+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4543768", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-12T10:56:57.011705+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T10:55:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4554931", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-12T10:30:27.007152+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T10:25:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610388", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-12T10:03:18.508491+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T10:01:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4543481", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T09:54:24.312986+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T09:53:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4505132", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-12T09:44:49.014208+00:00", "modelId": "AI-ModelScope/bitnet-b1.58-2B-4T-bf16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T09:43:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079172", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-12T09:44:49.014179+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-Apollo-V0.1-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T09:41:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079149", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T09:16:13.411459+00:00", "modelId": "amd/Qwen2-7B-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T09:11:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079981", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T09:06:13.895768+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:57:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560058", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T08:56:30.820631+00:00", "modelId": "amd/Qwen-2.5-1.5B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:55:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079114", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-12T08:47:44.834299+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523323", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-12T08:38:57.213433+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:35:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523313", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-12T08:20:40.114700+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-12T08:17:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523325", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T08:20:40.114654+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:13:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4547659", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T08:20:40.114686+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:13:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4543517", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-12T08:11:37.402305+00:00", "modelId": "LLM-Research/Phi-4-mini-flash-reasoning", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:09:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079966", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T08:11:37.402333+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:09:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4549394", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T08:02:48.507658+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T07:53:22+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4549467", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "", "lastSyncTime": "2026-09-12T07:44:40.913717+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T07:39:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610364", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T07:35:30.412992+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T07:33:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4547660", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-12T06:59:46.603354+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Lite-Preview-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:55:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079259", "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": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T06:34:23.913239+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:29:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079116", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T06:34:23.913264+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:27:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457993", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-12T06:25:49.409819+00:00", "modelId": "LLM-Research/Phi-4-mini-flash-reasoning", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:25:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079173", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-12T06:25:49.409784+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:23:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4550765", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T06:25:49.409808+00:00", "modelId": "amd/Qwen2-7B-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:21:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080124", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T06:09:22.250742+00:00", "modelId": "amd/Qwen-2.5-1.5B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T06:03:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079245", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-12T05:51:39.310788+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Lite-Preview-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T05:43:21+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4079926", "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": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T05:24:45.924629+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Lite-Preview-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T05:21:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080073", "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": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T04:58:37.211377+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T04:55:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080069", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-12T04:58:37.211400+00:00", "modelId": "AI-ModelScope/bitnet-b1.58-2B-4T-bf16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T04:55:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079952", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T04:41:36.246914+00:00", "modelId": "LLM-Research/Phi-4-mini-flash-reasoning", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T04:35:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080064", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "repository_structure", "failureAction": "require_framework_specific_root_files", "failureCategory": "repository_structure", "failureClassificationReason": "structured_missing_files", "failureCode": "MODEL_FILE_NOT_FOUND", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model", "framework": "vllm", "lastSyncTime": "2026-09-12T03:32:35.805010+00:00", "modelId": "AI-ModelScope/bitnet-b1.58-2B-4T-bf16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T03:27:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080052", "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": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T03:05:47.937930+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-Apollo-V0.1-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T03:05:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080040", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T03:05:47.937901+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:57:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4578245", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T02:56:54.384007+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:53:23+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079108", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:56:54.383989+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:51:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134178", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:48:11.158114+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:43:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458009", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:39:29.219599+00:00", "modelId": "RedHatAI/Qwen2.5-3B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:39:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4100876", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T02:39:29.219629+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Thinking", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:35:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152611", "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": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T02:30:20.417896+00:00", "modelId": "nightmedia/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill-Heretic-qx86-hi-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T02:27:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079970", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T01:25:57.322124+00:00", "modelId": "amd/Qwen-2.5-1.5B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T01:25:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079965", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-12T01:25:57.322172+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T01:25:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523213", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-12T00:52:00.210542+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-12T00:49:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523319", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T23:52:34.207568+00:00", "modelId": "r0b0tlab/Agents-A1-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T23:47:53+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079945", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T23:52:34.207605+00:00", "modelId": "r0b0tlab/Agents-A1-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T23:47:53+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079258", "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", "framework": "vllm", "lastSyncTime": "2026-09-11T21:18:30.415792+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T21:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080096", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-11T20:14:35.600665+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T20:07:21+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4080034", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-11T20:03:23.495341+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T19:59:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079943", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-11T18:23:30.509203+00:00", "modelId": "LiquidAI/LFM2-2.6B-Transcript-GGUF", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-11T18:21:22+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079227", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-11T17:04:58.435558+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T16:55:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523307", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-11T14:13:29.151029+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T14:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523303", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-11T13:55:08.941364+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-11T13:53:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523314", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-11T13:55:08.941340+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:47:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332898", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-11T13:46:06.650683+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:43:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523302", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-11T13:18:33.951636+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523312", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-11T13:09:08.149747+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:07:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523311", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-11T12:59:52.253401+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T12:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4531547", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-11T12:50:33.752023+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T12:47:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523324", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm", "lastSyncTime": "2026-09-11T11:19:08.306651+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:13:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4578314", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-11T11:19:08.306628+00:00", "modelId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457980", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-11T11:08:14.809954+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T11:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457994", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-11T07:43:04.407471+00:00", "modelId": "deepreinforce-ai/Ornith-1.0-35B-FP8", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-11T07:38:33+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4079996", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-11T07:33:47.206168+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T07:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523220", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-11T07:24:30.143494+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T07:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4505135", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-11T07:05:27.006934+00:00", "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T06:57:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523318", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-11T05:08:00.009961+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T05:05:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477832", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-11T03:33:48.898214+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497066", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-11T03:25:05.807699+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T03:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497054", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T23:52:39.100972+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T23:51:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477786", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T23:36:16.447910+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T23:33:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497061", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T23:36:16.447873+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T23:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497074", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T23:11:46.109095+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T23:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523218", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T22:39:21.821546+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T22:33:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532025", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T22:32:18.404515+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T22:25:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4583642", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T21:23:30.606595+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T21:17:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532126", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T21:23:30.606628+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T21:17:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532125", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T20:06:18.925896+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T20:01:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523216", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T19:56:51.309666+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:49:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477723", "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, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T19:56:51.309700+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:49:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523214", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T19:48:09.995356+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:45:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477833", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_mtp"], "framework": "", "lastSyncTime": "2026-09-10T19:38:05.602511+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-8bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332704", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T19:27:42.923434+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:25:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523215", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T19:17:56.906562+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:09:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523222", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T19:08:02.004176+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:01:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523301", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T19:08:02.004199+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T19:01:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493684", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T18:58:50.012593+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:57:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532026", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T18:58:50.012601+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:57:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532024", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T18:58:50.012543+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:53:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4573325", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T18:58:50.012571+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:49:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493679", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T18:58:50.012583+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:49:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532127", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "platform_io_transient", "failureCode": "STORAGE_ERROR", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T18:38:45.206121+00:00", "modelId": "nm-testing/Qwen2-1.5B-Instruct-FP8W8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:33:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523310", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T17:40:38.407692+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:31:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497059", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T17:30:55.344638+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497068", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T17:03:45.496007+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:01:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497067", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T17:03:45.496018+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T17:01:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496941", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T17:03:45.495985+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497055", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T16:54:17.206907+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:49:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497075", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T16:54:17.206935+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:45:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532021", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T16:37:38.117587+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:33:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505124", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T16:37:38.117560+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T16:31:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505123", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T16:05:31.804335+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T15:59:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457978", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T16:05:31.804365+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T15:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477834", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T15:48:17.745912+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T15:43:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471922", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T15:48:17.745945+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T15:43:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471921", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T13:55:40.785120+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:47:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610380", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T13:30:05.632388+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496944", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T13:23:06.708419+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T13:19:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496965", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T12:40:42.405633+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523210", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T12:32:29.847014+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:27:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477841", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T12:23:25.501701+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:23:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471971", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T12:23:25.501713+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:19:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471969", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "runtime_memory", "failureAction": "lower_memory_risk_or_reject_combination", "failureCategory": "runtime_memory", "failureClassificationReason": "structured_device_oom", "failureCode": "DEVICE_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-10T12:23:25.501677+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493612", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T12:23:25.501722+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493610", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T12:23:25.501730+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:15:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471967", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-10T12:15:14.346623+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:09:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4463766", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T12:06:09.109223+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:05:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523306", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T12:06:09.109198+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:03:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490278", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T11:57:54.623286+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:53:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610381", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T11:48:57.307255+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:45:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458000", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T11:40:52.603333+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:39:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505113", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T11:40:52.603356+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2-asym", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:39:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505112", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T11:40:52.603367+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505111", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T11:31:55.305639+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:25:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471913", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T11:14:50.402520+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134179", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T11:06:41.315652+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134097", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T11:06:41.315686+00:00", "modelId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:01:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4457998", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "no_idle_device", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T11:06:41.315698+00:00", "modelId": "EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T11:01:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4134356", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T10:57:49.001753+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:49:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532027", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T10:46:39.406893+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:43:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4107002", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T10:30:02.547307+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:27:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471919", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T10:30:02.547284+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:23:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471918", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T10:21:30.006897+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493599", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T10:12:25.704447+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T10:11:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477783", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T09:47:33.262404+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:47:22+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493608", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T09:47:33.262382+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:43:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477720", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-10T09:29:56.132283+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:27:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532020", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T09:20:50.207436+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:19:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505117", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T09:20:50.207399+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:17:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610375", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T09:20:50.207423+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T09:17:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610372", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T08:54:23.346315+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:49:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471916", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454624+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:41:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493673", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454539+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:39:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493671", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454585+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:37:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532019", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218218+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:27:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493670", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T08:19:33.742658+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T08:17:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481727", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:53:10.699377+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:51:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481723", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:53:10.699435+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:51:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481716", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:53:10.699425+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:47:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481724", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:29:02.941680+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:23:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496943", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:21:04.730363+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:19:23+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497058", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T07:04:57.311815+00:00", "modelId": "nm-testing/nonuniform", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:03:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493609", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T07:04:57.311825+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T07:03:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493601", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T07:04:57.311794+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:59:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497056", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T06:56:22.046014+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496936", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:56:22.046035+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477785", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:40:56.094753+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:35:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505108", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:33:34.200730+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:33:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505109", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:33:34.200752+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:29:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505107", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:33:34.200761+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:29:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505106", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T06:11:26.144205+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:09:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610359", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T06:11:26.144180+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:05:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610355", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:03:48.106911+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471974", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:03:48.106939+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:57:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493605", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T05:56:10.303668+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477782", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T05:49:48.500487+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:45:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471903", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T05:49:48.500463+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:43:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471905", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T05:27:18.447582+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:19:22+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481721", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-10T05:18:58.697108+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:13:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4609099", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T05:18:58.697138+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:13:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610360", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T04:54:16.213427+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:51:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493600", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T04:54:16.213455+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:51:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505116", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T04:54:16.213468+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:49:22+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505115", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T04:45:49.293187+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:43:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493603", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T04:27:58.701433+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:25:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471917", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T04:27:58.701482+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:23:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471910", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T04:27:58.701457+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:21:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471915", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-10T04:09:13.117076+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T04:01:22+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4609102", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-10T04:00:09.998782+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T03:57:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532022", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T02:50:12.317776+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:43:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493607", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "", "lastSyncTime": "2026-09-10T02:50:12.317748+00:00", "modelId": "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4271675", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943952+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-10T02:37:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483083", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943965+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483082", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943974+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:35:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496938", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943909+00:00", "modelId": "neuralmagic/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:33:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4505137", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T02:32:07.501704+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496940", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T02:32:07.501688+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:25:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505091", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-10T02:23:37.132500+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:19:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483081", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T02:15:07.106855+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:11:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4497062", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T01:59:31.241099+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:55:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481728", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T01:59:31.241082+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:53:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481717", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T01:50:54.936003+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:49:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481654", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T01:50:54.936024+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:43:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4596146", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T01:42:34.770281+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:37:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481718", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T01:16:26.008857+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505087", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T01:16:26.008867+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505110", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T01:16:26.008832+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:11:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505076", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T01:08:07.916865+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T01:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471909", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T00:51:37.399566+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T00:51:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477721", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T00:20:21.332930+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T00:17:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610357", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T00:20:21.332898+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T00:15:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477714", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T00:20:21.332920+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T00:13:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477718", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T00:11:47.209836+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T00:11:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4596065", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T00:11:47.209848+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T00:11:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4596229", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T00:11:47.209812+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T00:09:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477715", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T00:11:47.209857+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T00:07:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477717", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T23:55:17.200912+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T23:51:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505073", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-09T23:14:19.142084+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T23:07:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481651", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T22:57:38.803923+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:49:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471911", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T22:49:15.213951+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:47:23+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471912", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T22:49:15.213972+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:47:23+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471906", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T22:06:26.296264+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:01:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493490", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T21:47:28.214740+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:41:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610342", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T21:37:50.501060+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:29:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505065", "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": "2026-09-10T18:58:50.012615+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293473597, "estimatedRequiredGiB": 18.233, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16314183099, "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:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:chat"], "modelscopeTasks": ["text-generation"], "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": "2026-09-09T14:21:21.949441+00:00", "modelType": "qwen3_5", "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": 16314183099}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:08:22.097030+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746441", "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": "2026-09-12T23:53:22.743813+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896238160, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898265436, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2948065280, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898265436}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:08:22.094532+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746447", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T21:11:06.904677+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:05:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493675", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T20:45:50.636960+00:00", "modelId": "nm-testing/SmolLM-135M-Instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4505136", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_mtp"], "framework": "", "lastSyncTime": "2026-09-09T20:34:13.525512+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:25:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332982", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T20:34:13.525546+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:25:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505092", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T20:23:37.101867+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:21:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505089", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T20:23:37.101902+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:21:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523211", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T20:23:37.101893+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:19:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4458013", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T20:13:30.044170+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:11:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610353", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-09T20:13:30.044156+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:07:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610356", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-09T20:13:30.044178+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:05:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481655", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-09T20:05:01.109344+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T20:01:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481647", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-09T20:05:01.109364+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:59:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4577671", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-09T19:47:41.999095+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:41:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481653", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-09T19:47:41.999072+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:39:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481659", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T19:37:31.704748+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:35:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4458014", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T19:29:30.333824+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:23:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471908", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T19:18:48.711721+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:17:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4458012", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T19:18:48.711664+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:11:22+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4477955", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T19:08:24.911910+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:05:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493488", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T19:08:24.911937+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T19:01:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493487", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-09T18:37:50.109612+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:31:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4579389", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T18:37:50.109633+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:31:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505090", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-09T18:28:27.522346+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:21:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610358", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-09T18:09:45.834676+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592383", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T18:09:45.834698+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471904", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T18:09:45.834707+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471907", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "", "lastSyncTime": "2026-09-09T17:42:15.798661+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T17:39:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610396", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-09T17:24:58.529030+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-09T17:23:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458425", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T17:24:58.529069+00:00", "modelId": "neuralmagic/Mistral-7B-Instruct-v0.3-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T17:21:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4107009", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "no_idle_device", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-09T17:24:58.529055+00:00", "modelId": "mlx-community/Qwen3.6-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T17:17:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490281", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T16:50:57.940039+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T16:41:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610347", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-09T16:11:26.734386+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T16:05:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4477958", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-09T16:03:52.328406+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T15:55:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493674", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-09T15:39:07.233616+00:00", "modelId": "mlx-community/Ornith-1.0-9B-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T15:33:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079339", "taskType": "text-generation", "verifyResult": -1}

1004
.modelhub_state/recovery_active_tasks.jsonl Normal file
View File

File diff suppressed because it is too large Load Diff

1022
.modelhub_state/recovery_intents.jsonl Normal file
View File

File diff suppressed because it is too large Load Diff

33
.modelhub_state/routing_intelligence.json Normal file
View File

@@ -0,0 +1,33 @@
{
"acceptedByCategory": {
"unified_success_first": 855
},
"acceptedByRoute": {
"text-generation|Ascend_910-b3|llamacpp": 12,
"text-generation|Ascend_910-b3|vllm": 16,
"text-generation|Ascend_910-b3|vllm_tokenizer_patch": 24,
"text-generation|Ascend_910-b4|llamacpp": 9,
"text-generation|Ascend_910-b4|vllm_tokenizer_patch": 33,
"text-generation|Biren_166m|vllm": 55,
"text-generation|Cambricon_mlu-370-x4|vllm-mlu": 31,
"text-generation|Cambricon_mlu-370-x8|vllm": 13,
"text-generation|Cambricon_mlu-370-x8|vllm-customized": 2,
"text-generation|Cambricon_mlu-370-x8|vllm-mlu": 68,
"text-generation|Iluvatar_bi-150|llamacpp": 12,
"text-generation|Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 66,
"text-generation|Iluvatar_mrv-100|vllm": 40,
"text-generation|Kunlunxin_p-800|vllm_fix_tokenizer": 102,
"text-generation|MetaX_c-500|vllm": 90,
"text-generation|Mthreads_s4000|llamacpp": 12,
"text-generation|Mthreads_s4000|vllm": 64,
"text-generation|Sunrise_pt-200-x1|vllm": 57,
"text-generation|Sunrise_pt-200-x1|vllm_fix_tokenizer": 50,
"text-generation|Vastai_va16|vllm_fix_tokenizer": 39,
"text-generation|hygon_k100-ai|llamacpp": 12,
"text-generation|hygon_k100-ai|vllm-patch-tokenizer": 48
},
"acceptedSinceRefresh": 855,
"acceptedTotal": 855,
"generatedAt": "2026-09-13T14:24:15.458879+00:00",
"version": 1
}

130
.modelhub_state/submission_exclusions.jsonl Normal file
View File

@@ -0,0 +1,130 @@
{"firstSeenAt": "2026-09-04T03:57:23.797048+00:00", "lastSeenAt": "2026-09-04T03:57:23.797048+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-04T03:57:29.674890+00:00", "lastSeenAt": "2026-09-04T03:57:29.674890+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
{"firstSeenAt": "2026-09-04T03:57:35.573847+00:00", "lastSeenAt": "2026-09-04T03:57:35.573847+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
{"firstSeenAt": "2026-09-04T03:57:49.185347+00:00", "lastSeenAt": "2026-09-04T03:57:49.185347+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-04T03:57:54.410921+00:00", "lastSeenAt": "2026-09-04T03:57:54.410921+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-04T03:57:59.490195+00:00", "lastSeenAt": "2026-09-04T03:57:59.490195+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-04T04:29:16.979261+00:00", "lastSeenAt": "2026-09-04T04:29:16.979261+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
{"firstSeenAt": "2026-09-04T04:40:16.591240+00:00", "lastSeenAt": "2026-09-04T04:40:16.591240+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-04T06:49:06.281179+00:00", "lastSeenAt": "2026-09-04T06:49:06.281179+00:00", "modelId": "voconly/Qwen3-ASR-1.7B-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-04T07:00:32.615126+00:00", "lastSeenAt": "2026-09-04T07:00:32.615126+00:00", "modelId": "voconly/whisper-large-v3-turbo-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-04T07:00:32.616924+00:00", "lastSeenAt": "2026-09-04T07:00:32.616924+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-04T07:09:19.413394+00:00", "lastSeenAt": "2026-09-04T07:09:19.413394+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-04T07:16:43.841046+00:00", "lastSeenAt": "2026-09-04T07:16:43.841046+00:00", "modelId": "ggml-org/gpt-oss-20b-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-04T08:11:10.291594+00:00", "lastSeenAt": "2026-09-04T08:11:10.291594+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
{"firstSeenAt": "2026-09-04T09:45:23.171369+00:00", "lastSeenAt": "2026-09-04T09:45:23.171369+00:00", "modelId": "voconly/whisper-large-v3-turbo-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-04T10:14:22.495811+00:00", "lastSeenAt": "2026-09-04T10:14:22.495811+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-04T11:55:25.074530+00:00", "lastSeenAt": "2026-09-04T11:55:25.074530+00:00", "modelId": "ggml-org/gpt-oss-20b-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-04T11:55:25.076100+00:00", "lastSeenAt": "2026-09-04T11:55:25.076100+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-04T12:57:48.331515+00:00", "lastSeenAt": "2026-09-04T12:57:48.331515+00:00", "modelId": "voconly/Qwen3-ASR-1.7B-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-04T12:57:48.333103+00:00", "lastSeenAt": "2026-09-04T12:57:48.333103+00:00", "modelId": "ggml-org/gpt-oss-20b-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-04T13:21:50.254157+00:00", "lastSeenAt": "2026-09-04T13:21:50.254157+00:00", "modelId": "voconly/Qwen3-ASR-1.7B-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-04T13:40:36.168451+00:00", "lastSeenAt": "2026-09-04T13:40:36.168451+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-04T14:13:43.429448+00:00", "lastSeenAt": "2026-09-04T14:13:43.429448+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
{"firstSeenAt": "2026-09-04T16:30:38.120052+00:00", "lastSeenAt": "2026-09-04T16:30:38.120052+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-04T16:49:34.985609+00:00", "lastSeenAt": "2026-09-04T16:49:34.985609+00:00", "modelId": "voconly/whisper-large-v3-turbo-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-04T16:59:32.121822+00:00", "lastSeenAt": "2026-09-04T16:59:32.121822+00:00", "modelId": "voconly/Qwen3-ASR-1.7B-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-04T17:30:31.477117+00:00", "lastSeenAt": "2026-09-04T17:30:31.477117+00:00", "modelId": "voconly/whisper-large-v3-turbo-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-04T18:10:12.844722+00:00", "lastSeenAt": "2026-09-04T18:10:12.844722+00:00", "modelId": "ggml-org/gpt-oss-20b-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-04T18:10:12.846446+00:00", "lastSeenAt": "2026-09-04T18:10:12.846446+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-04T18:31:29.728507+00:00", "lastSeenAt": "2026-09-04T18:31:29.728507+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
{"firstSeenAt": "2026-09-04T20:37:43.057350+00:00", "lastSeenAt": "2026-09-04T20:37:43.057350+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-04T20:46:08.566927+00:00", "lastSeenAt": "2026-09-04T20:46:08.566927+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-04T20:46:08.568661+00:00", "lastSeenAt": "2026-09-04T20:46:08.568661+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-04T21:01:14.928100+00:00", "lastSeenAt": "2026-09-04T21:01:14.928100+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-04T21:08:10.100427+00:00", "lastSeenAt": "2026-09-04T21:08:10.100427+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x4"}
{"firstSeenAt": "2026-09-04T21:17:56.214617+00:00", "lastSeenAt": "2026-09-04T21:17:56.214617+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x4"}
{"firstSeenAt": "2026-09-04T21:23:38.184741+00:00", "lastSeenAt": "2026-09-04T21:23:38.184741+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-04T21:34:39.157491+00:00", "lastSeenAt": "2026-09-04T21:34:39.157491+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x4"}
{"firstSeenAt": "2026-09-04T21:34:39.159318+00:00", "lastSeenAt": "2026-09-04T21:34:39.159318+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-04T21:34:39.160913+00:00", "lastSeenAt": "2026-09-04T21:34:39.160913+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-04T21:34:39.162060+00:00", "lastSeenAt": "2026-09-04T21:34:39.162060+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-04T22:02:42.528424+00:00", "lastSeenAt": "2026-09-04T22:02:42.528424+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x4"}
{"firstSeenAt": "2026-09-04T22:02:42.530385+00:00", "lastSeenAt": "2026-09-04T22:02:42.530385+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-04T22:02:42.531558+00:00", "lastSeenAt": "2026-09-04T22:02:42.531558+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-04T22:08:39.423488+00:00", "lastSeenAt": "2026-09-04T22:08:39.423488+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-04T22:30:12.999411+00:00", "lastSeenAt": "2026-09-04T22:30:12.999411+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-04T23:01:40.210343+00:00", "lastSeenAt": "2026-09-04T23:01:40.210343+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-04T23:08:42.844010+00:00", "lastSeenAt": "2026-09-04T23:08:42.844010+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-04T23:08:42.845836+00:00", "lastSeenAt": "2026-09-04T23:08:42.845836+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-04T23:08:42.847267+00:00", "lastSeenAt": "2026-09-04T23:08:42.847267+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-04T23:16:58.513168+00:00", "lastSeenAt": "2026-09-04T23:16:58.513168+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-04T23:24:51.833226+00:00", "lastSeenAt": "2026-09-04T23:24:51.833226+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-04T23:30:00.079681+00:00", "lastSeenAt": "2026-09-04T23:30:00.079681+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
{"firstSeenAt": "2026-09-05T00:50:30.239660+00:00", "lastSeenAt": "2026-09-05T00:50:30.239660+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
{"firstSeenAt": "2026-09-05T00:50:30.241369+00:00", "lastSeenAt": "2026-09-05T00:50:30.241369+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
{"firstSeenAt": "2026-09-05T01:49:07.541676+00:00", "lastSeenAt": "2026-09-05T01:49:07.541676+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
{"firstSeenAt": "2026-09-05T02:29:40.646869+00:00", "lastSeenAt": "2026-09-05T02:29:40.646869+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
{"firstSeenAt": "2026-09-05T02:42:56.679757+00:00", "lastSeenAt": "2026-09-05T02:42:56.679757+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-05T02:42:56.681931+00:00", "lastSeenAt": "2026-09-05T02:42:56.681931+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
{"firstSeenAt": "2026-09-05T03:05:39.090955+00:00", "lastSeenAt": "2026-09-05T03:05:39.090955+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
{"firstSeenAt": "2026-09-05T03:25:37.922974+00:00", "lastSeenAt": "2026-09-05T03:25:37.922974+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Cambricon_mlu-370-x8"}
{"firstSeenAt": "2026-09-05T04:43:13.695708+00:00", "lastSeenAt": "2026-09-05T04:43:13.695708+00:00", "modelId": "ggml-org/gpt-oss-20b-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-05T05:00:03.356500+00:00", "lastSeenAt": "2026-09-05T05:00:03.356500+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-05T05:07:39.434421+00:00", "lastSeenAt": "2026-09-05T05:07:39.434421+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
{"firstSeenAt": "2026-09-05T05:07:39.436263+00:00", "lastSeenAt": "2026-09-05T05:07:39.436263+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
{"firstSeenAt": "2026-09-05T05:07:39.437496+00:00", "lastSeenAt": "2026-09-05T05:07:39.437496+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
{"firstSeenAt": "2026-09-05T05:30:45.668136+00:00", "lastSeenAt": "2026-09-05T05:30:45.668136+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
{"firstSeenAt": "2026-09-05T05:41:06.398285+00:00", "lastSeenAt": "2026-09-05T05:41:06.398285+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
{"firstSeenAt": "2026-09-05T06:46:47.510402+00:00", "lastSeenAt": "2026-09-05T06:46:47.510402+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
{"firstSeenAt": "2026-09-05T06:46:47.512965+00:00", "lastSeenAt": "2026-09-05T06:46:47.512965+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-05T06:48:38.735121+00:00", "lastSeenAt": "2026-09-05T06:48:38.735121+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-05T07:02:15.303839+00:00", "lastSeenAt": "2026-09-05T07:02:15.303839+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
{"firstSeenAt": "2026-09-05T09:06:33.202864+00:00", "lastSeenAt": "2026-09-05T09:06:33.202864+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
{"firstSeenAt": "2026-09-05T09:06:33.205809+00:00", "lastSeenAt": "2026-09-05T09:06:33.205809+00:00", "modelId": "voconly/whisper-large-v3-turbo-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-05T13:08:37.631159+00:00", "lastSeenAt": "2026-09-05T13:08:37.631159+00:00", "modelId": "voconly/Qwen3-ASR-1.7B-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-05T13:08:37.633069+00:00", "lastSeenAt": "2026-09-05T13:08:37.633069+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-05T13:08:37.635738+00:00", "lastSeenAt": "2026-09-05T13:08:37.635738+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-05T13:44:34.395810+00:00", "lastSeenAt": "2026-09-05T13:44:34.395810+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-05T16:21:23.838028+00:00", "lastSeenAt": "2026-09-05T16:21:23.838028+00:00", "modelId": "nv-community/Qwen3.6-35B-A3B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
{"firstSeenAt": "2026-09-05T16:21:23.840026+00:00", "lastSeenAt": "2026-09-05T16:21:23.840026+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
{"firstSeenAt": "2026-09-05T16:24:16.092553+00:00", "lastSeenAt": "2026-09-05T16:24:16.092553+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
{"firstSeenAt": "2026-09-05T16:24:16.095538+00:00", "lastSeenAt": "2026-09-05T16:24:16.095538+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
{"firstSeenAt": "2026-09-05T16:24:16.097321+00:00", "lastSeenAt": "2026-09-05T16:24:16.097321+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
{"firstSeenAt": "2026-09-05T16:24:16.099063+00:00", "lastSeenAt": "2026-09-05T16:24:16.099063+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
{"firstSeenAt": "2026-09-06T00:33:12.804105+00:00", "lastSeenAt": "2026-09-06T00:33:12.804105+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
{"firstSeenAt": "2026-09-06T00:53:48.753329+00:00", "lastSeenAt": "2026-09-06T00:53:48.753329+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
{"firstSeenAt": "2026-09-06T07:37:25.003613+00:00", "lastSeenAt": "2026-09-06T07:37:25.003613+00:00", "modelId": "RedHatAI/Ornith-1.0-35B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
{"firstSeenAt": "2026-09-06T07:37:25.006232+00:00", "lastSeenAt": "2026-09-06T07:37:25.006232+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "MetaX_c-500"}
{"firstSeenAt": "2026-09-06T10:24:57.089879+00:00", "lastSeenAt": "2026-09-06T10:24:57.089879+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
{"firstSeenAt": "2026-09-06T14:05:08.261809+00:00", "lastSeenAt": "2026-09-06T14:05:08.261809+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-06T14:05:08.263848+00:00", "lastSeenAt": "2026-09-06T14:05:08.263848+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-Instruct-quantized.w8a16", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-06T14:05:08.265533+00:00", "lastSeenAt": "2026-09-06T14:05:08.265533+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-06T14:05:08.267292+00:00", "lastSeenAt": "2026-09-06T14:05:08.267292+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-06T14:05:08.268964+00:00", "lastSeenAt": "2026-09-06T14:05:08.268964+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-Instruct-quantized.w8a8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-06T14:38:36.123200+00:00", "lastSeenAt": "2026-09-06T14:38:36.123200+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-06T14:58:20.797485+00:00", "lastSeenAt": "2026-09-06T14:58:20.797485+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-06T15:12:15.892392+00:00", "lastSeenAt": "2026-09-06T15:12:15.892392+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-06T15:33:09.054073+00:00", "lastSeenAt": "2026-09-06T15:33:09.054073+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-06T21:26:08.088507+00:00", "lastSeenAt": "2026-09-06T21:26:08.088507+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
{"firstSeenAt": "2026-09-08T05:54:38.612488+00:00", "lastSeenAt": "2026-09-08T05:54:38.612488+00:00", "modelId": "Mungert/s1-mini-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-08T05:59:06.169776+00:00", "lastSeenAt": "2026-09-08T05:59:06.169776+00:00", "modelId": "Mungert/s1-mini-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-08T06:03:32.307449+00:00", "lastSeenAt": "2026-09-08T06:03:32.307449+00:00", "modelId": "Mungert/s1-mini-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-08T06:08:08.143999+00:00", "lastSeenAt": "2026-09-08T06:08:08.143999+00:00", "modelId": "Mungert/s1-mini-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-08T07:15:24.577472+00:00", "lastSeenAt": "2026-09-08T07:15:24.577472+00:00", "modelId": "OpenBMB/MiniCPM5-1B-MLX", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
{"firstSeenAt": "2026-09-08T07:15:24.580859+00:00", "lastSeenAt": "2026-09-08T07:15:24.580859+00:00", "modelId": "RedHatAI/Qwen3.6-35B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
{"firstSeenAt": "2026-09-08T07:15:24.583178+00:00", "lastSeenAt": "2026-09-08T07:15:24.583178+00:00", "modelId": "OpenBMB/MiniCPM5-1B-Base", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
{"firstSeenAt": "2026-09-08T07:15:24.585248+00:00", "lastSeenAt": "2026-09-08T07:15:24.585248+00:00", "modelId": "nanbeige/Nanbeige4.2-3B", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
{"firstSeenAt": "2026-09-08T07:15:24.587116+00:00", "lastSeenAt": "2026-09-08T07:15:24.587116+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
{"firstSeenAt": "2026-09-08T10:26:28.569398+00:00", "lastSeenAt": "2026-09-08T10:26:28.569398+00:00", "modelId": "Mungert/s1-mini-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-08T23:04:21.864681+00:00", "lastSeenAt": "2026-09-08T23:04:21.864681+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-Base-BF16", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-09T07:39:29.213764+00:00", "lastSeenAt": "2026-09-09T07:39:29.213764+00:00", "modelId": "prithivMLmods/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-09T07:39:34.797658+00:00", "lastSeenAt": "2026-09-09T07:39:34.797658+00:00", "modelId": "prithivMLmods/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-09T08:00:24.606551+00:00", "lastSeenAt": "2026-09-09T08:00:24.606551+00:00", "modelId": "prithivMLmods/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-09T16:11:23.152273+00:00", "lastSeenAt": "2026-09-09T16:11:23.152273+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-09T16:13:12.582481+00:00", "lastSeenAt": "2026-09-09T16:13:12.582481+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Vastai_va16"}
{"firstSeenAt": "2026-09-09T16:14:47.383659+00:00", "lastSeenAt": "2026-09-09T16:14:47.383659+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-09T16:16:23.871046+00:00", "lastSeenAt": "2026-09-09T16:16:23.871046+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Sunrise_pt-200-x1"}
{"firstSeenAt": "2026-09-09T16:24:21.658361+00:00", "lastSeenAt": "2026-09-09T16:24:21.658361+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Biren_166m"}
{"firstSeenAt": "2026-09-09T21:08:33.555529+00:00", "lastSeenAt": "2026-09-09T21:08:33.555529+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Kunlunxin_p-800"}
{"firstSeenAt": "2026-09-10T02:01:15.114573+00:00", "lastSeenAt": "2026-09-10T02:01:15.114573+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_mrv-100"}
{"firstSeenAt": "2026-09-11T02:10:43.554485+00:00", "lastSeenAt": "2026-09-11T02:10:43.554485+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-11T02:12:44.707423+00:00", "lastSeenAt": "2026-09-11T02:12:44.707423+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-11T02:14:19.387716+00:00", "lastSeenAt": "2026-09-11T02:14:19.387716+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-11T10:27:40.959383+00:00", "lastSeenAt": "2026-09-11T10:27:40.959383+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-11T10:27:40.963126+00:00", "lastSeenAt": "2026-09-11T10:27:40.963126+00:00", "modelId": "nv-community/Qwen3.8-27B-NVFP4", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Iluvatar_bi-150"}
{"firstSeenAt": "2026-09-11T18:18:45.194944+00:00", "lastSeenAt": "2026-09-11T18:18:45.194944+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B-GGUF", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}
{"firstSeenAt": "2026-09-13T12:37:34.507858+00:00", "lastSeenAt": "2026-09-13T12:37:34.507858+00:00", "modelId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "hygon_k100-ai"}
{"firstSeenAt": "2026-09-13T12:39:25.361679+00:00", "lastSeenAt": "2026-09-13T12:39:25.361679+00:00", "modelId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b3"}
{"firstSeenAt": "2026-09-13T12:41:31.581405+00:00", "lastSeenAt": "2026-09-13T12:41:31.581405+00:00", "modelId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Ascend_910-b4"}
{"firstSeenAt": "2026-09-13T12:43:37.058665+00:00", "lastSeenAt": "2026-09-13T12:43:37.058665+00:00", "modelId": "voconly/nemotron-3.5-asr-streaming-0.6b-gguf", "occurrences": 1, "reason": "模型唯一性检查没有通过，无法进行同步", "targetGpu": "Mthreads_s4000"}

9
.modelhub_state/worker_crashes.jsonl Normal file
View File

@@ -0,0 +1,9 @@
{"at": "2026-09-04T19:47:19.971266+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 57088.798}
{"at": "2026-09-05T12:16:49.970366+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 59364.493}
{"at": "2026-09-06T07:29:16.402335+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 69140.926}
{"at": "2026-09-07T02:37:48.598308+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 68906.425}
{"at": "2026-09-08T23:49:36.488354+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 162702.112}
{"at": "2026-09-09T12:29:14.196778+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 45572.202}
{"at": "2026-09-10T15:27:02.083554+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 97062.112}
{"at": "2026-09-12T02:15:23.274335+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 125295.685}
{"at": "2026-09-13T12:45:13.097016+00:00", "exitCode": -9, "reason": "worker_exited", "restartCount": 1, "uptimeSeconds": 124184.315}

0
ledger/.submissions.jsonl.lock Normal file
View File

797
ledger/submissions.jsonl Normal file
View File

@@ -0,0 +1,797 @@
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny-GGUF", "modelId": "inclusionAI/Ling-3.0-tiny-GGUF", "submitTime": "2026-09-04T03:57:15.312611+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610785", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "submitTime": "2026-09-04T03:57:15.116974+00:00", "targetGpu": "Biren_166m", "taskId": "4610786", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T03:57:15.115591+00:00", "targetGpu": "Biren_166m", "taskId": "4610789", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T03:57:15.111739+00:00", "targetGpu": "Biren_166m", "taskId": "4610788", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T03:57:15.122454+00:00", "targetGpu": "Biren_166m", "taskId": "4610792", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-04T03:57:15.186297+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610791", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T04:13:33.449976+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4610987", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T04:13:33.436802+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4610985", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T04:13:33.448611+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4610986", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T04:18:22.296309+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4611034", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T04:18:22.294480+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4611032", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T04:18:22.293258+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4611033", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/bharatgenai/Param2-17B-A2.4B-Thinking", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "submitTime": "2026-09-04T04:29:16.672536+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611191", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-04T04:29:16.656478+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611189", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T04:34:21.517356+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611266", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T04:34:21.520300+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611267", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T04:34:21.518508+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611265", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/b77968543/Spark-X2.5-4B-Q8_0", "modelId": "b77968543/Spark-X2.5-4B-Q8_0", "submitTime": "2026-09-04T04:40:16.372199+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611339", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "submitTime": "2026-09-04T04:45:10.463600+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611409", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-04T04:45:10.465869+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611408", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T04:49:57.619810+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611460", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T04:49:57.614004+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611462", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T04:49:57.622876+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611461", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T04:51:18.804860+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4611484", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T04:51:18.803565+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4611482", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T04:51:18.805964+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4611483", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T05:06:37.162640+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611646", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T05:06:37.165709+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611648", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T05:06:37.161333+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611647", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-04T06:55:47.742909+00:00", "targetGpu": "Biren_166m", "taskId": "4621594", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "submitTime": "2026-09-04T06:55:47.759663+00:00", "targetGpu": "Biren_166m", "taskId": "4621595", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "submitTime": "2026-09-04T07:04:25.458550+00:00", "targetGpu": "Biren_166m", "taskId": "4621698", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T07:40:37.506061+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4622172", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T07:56:50.952206+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4622417", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-04T08:10:58.185038+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622623", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T08:10:58.159820+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622624", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T08:10:58.164553+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622621", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T08:10:58.158458+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622619", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T08:14:12.544960+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4622655", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T08:33:06.846794+00:00", "targetGpu": "Biren_166m", "taskId": "4623002", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T08:44:58.161709+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4623226", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-04T12:34:49.403585+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4626360", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/siliconflow/gpt-oss-20b-FP8", "modelId": "siliconflow/gpt-oss-20b-FP8", "submitTime": "2026-09-04T13:34:49.450482+00:00", "targetGpu": "MetaX_c-500", "taskId": "4627250", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "submitTime": "2026-09-04T14:08:46.692566+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4627849", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "submitTime": "2026-09-04T14:46:47.882785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4628625", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "submitTime": "2026-09-04T15:01:53.788146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4628814", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T15:17:04.545687+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4629090", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "submitTime": "2026-09-04T15:17:04.566515+00:00", "targetGpu": "Biren_166m", "taskId": "4629091", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T15:32:11.647812+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4629294", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "submitTime": "2026-09-04T15:32:11.649244+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4629295", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T15:47:16.843035+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4629532", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T15:49:37.968504+00:00", "targetGpu": "Biren_166m", "taskId": "4629573", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T16:05:38.973026+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4629768", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "submitTime": "2026-09-04T16:10:19.951781+00:00", "targetGpu": "MetaX_c-500", "taskId": "4629851", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T16:10:19.953932+00:00", "targetGpu": "MetaX_c-500", "taskId": "4629853", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "submitTime": "2026-09-04T16:45:54.339948+00:00", "targetGpu": "Biren_166m", "taskId": "4630659", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T16:50:16.092995+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4630839", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/tinyllama-marlin24-w4a16-group128", "modelId": "nm-testing/tinyllama-marlin24-w4a16-group128", "submitTime": "2026-09-04T16:55:10.211615+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4630908", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-nict-8b-base", "modelId": "pfnet/plamo-3-nict-8b-base", "submitTime": "2026-09-04T17:27:00.623821+00:00", "targetGpu": "Biren_166m", "taskId": "4631345", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "submitTime": "2026-09-04T18:06:53.125751+00:00", "targetGpu": "Biren_166m", "taskId": "4631858", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "submitTime": "2026-09-04T18:26:16.665549+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632117", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "submitTime": "2026-09-04T19:03:47.678567+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632579", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "submitTime": "2026-09-04T19:29:42.987166+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632974", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T20:26:01.012898+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4633732", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/siliconflow/gpt-oss-20b-FP8", "modelId": "siliconflow/gpt-oss-20b-FP8", "submitTime": "2026-09-04T20:33:07.760826+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4633843", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill", "modelId": "empero-ai/Qwen3.8-9B-Distill", "submitTime": "2026-09-04T20:34:23.419555+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4633876", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "submitTime": "2026-09-04T20:40:58.592221+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4633953", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T20:48:49.542529+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4634053", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-04T21:21:22.785475+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4634506", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenOneRec/OneReason-8B-pretrain-competition", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "submitTime": "2026-09-04T22:00:58.451074+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4635038", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-04T22:37:50.462232+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4635609", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "submitTime": "2026-09-04T23:12:12.056590+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4636059", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "submitTime": "2026-09-04T23:12:18.663255+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4636060", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "submitTime": "2026-09-04T23:12:29.786627+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4636099", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-04T23:29:59.915927+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636369", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T23:29:59.925332+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636370", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T23:29:59.918683+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636372", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-04T23:30:00.029529+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636376", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T23:30:00.025922+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636375", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-05T02:00:39.877205+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4638914", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-05T02:00:39.878542+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4638915", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "submitTime": "2026-09-05T02:38:10.748196+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4639409", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-2B-Distill-GGUF", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "submitTime": "2026-09-05T04:38:07.789820+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641229", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill-GGUF", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "submitTime": "2026-09-05T04:56:19.745119+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-05T05:03:01.097550+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641563", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "submitTime": "2026-09-05T05:03:09.008584+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641565", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "submitTime": "2026-09-05T05:03:09.000926+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641564", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LLM-Research/Phi-3.5-mini-instruct-bnb-4bit", "modelId": "LLM-Research/Phi-3.5-mini-instruct-bnb-4bit", "submitTime": "2026-09-05T05:03:09.034612+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4641566", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "submitTime": "2026-09-05T05:17:16.436989+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641789", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-05T05:17:16.435240+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641790", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-05T05:17:16.439814+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641788", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "submitTime": "2026-09-05T05:17:16.438354+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641791", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "submitTime": "2026-09-05T05:17:16.497948+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641785", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B", "modelId": "ornith-ai/Ornith-1.5-9B", "submitTime": "2026-09-05T05:25:57.272773+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4641967", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "submitTime": "2026-09-05T06:44:06.184901+00:00", "targetGpu": "MetaX_c-500", "taskId": "4643007", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-05T06:48:32.413847+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643045", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "submitTime": "2026-09-05T06:48:32.398253+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643046", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-05T06:48:32.415250+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643042", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-05T06:48:32.400153+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643043", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-05T06:48:32.405323+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643048", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-05T06:48:32.410291+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643049", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-230M-GGUF", "modelId": "LiquidAI/LFM2.5-230M-GGUF", "submitTime": "2026-09-05T09:04:21.884770+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4645136", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "submitTime": "2026-09-05T09:38:43.506267+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645748", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-05T09:43:33.758884+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4645816", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/zstack/qwen3-4b-fake", "modelId": "zstack/qwen3-4b-fake", "submitTime": "2026-09-05T10:33:51.484756+00:00", "targetGpu": "MetaX_c-500", "taskId": "4646505", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "submitTime": "2026-09-05T12:03:37.084154+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4648146", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "submitTime": "2026-09-05T12:03:37.105603+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648141", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "submitTime": "2026-09-05T13:07:23.099409+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4649238", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/zstack/qwen3-4b-fake", "modelId": "zstack/qwen3-4b-fake", "submitTime": "2026-09-05T13:07:23.114152+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649233", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/douyamv/Qwen3.8-27B-FP8", "modelId": "douyamv/Qwen3.8-27B-FP8", "submitTime": "2026-09-05T13:07:23.110104+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649235", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "submitTime": "2026-09-05T13:07:23.184952+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649236", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "submitTime": "2026-09-05T13:07:29.375921+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649241", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-05T13:07:29.655509+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649242", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "submitTime": "2026-09-05T13:07:29.696899+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649243", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-05T13:07:29.759253+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649244", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "submitTime": "2026-09-05T13:15:06.885148+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649368", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "submitTime": "2026-09-05T13:15:06.887234+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649370", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-7.2B-20260805", "modelId": "RWKV/RWKV7-7.2B-20260805", "submitTime": "2026-09-05T13:36:05.794989+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649667", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "submitTime": "2026-09-05T13:40:05.806797+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4649761", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "submitTime": "2026-09-05T13:43:45.755060+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649829", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "submitTime": "2026-09-05T13:52:09.758631+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650028", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "submitTime": "2026-09-05T13:55:22.931577+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650076", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "submitTime": "2026-09-05T14:30:50.543106+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650543", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "submitTime": "2026-09-05T14:35:18.733791+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650604", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "submitTime": "2026-09-05T14:39:36.525018+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4650654", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "submitTime": "2026-09-05T15:03:56.182791+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650921", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-05T16:20:38.385517+00:00", "targetGpu": "Vastai_va16", "taskId": "4651796", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-05T16:20:38.391817+00:00", "targetGpu": "Vastai_va16", "taskId": "4651794", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "submitTime": "2026-09-05T16:20:38.389388+00:00", "targetGpu": "Vastai_va16", "taskId": "4651792", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "submitTime": "2026-09-05T16:20:43.653329+00:00", "targetGpu": "Vastai_va16", "taskId": "4651782", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "submitTime": "2026-09-05T16:20:43.655577+00:00", "targetGpu": "Vastai_va16", "taskId": "4651783", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-05T16:30:08.472711+00:00", "targetGpu": "Vastai_va16", "taskId": "4651931", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "submitTime": "2026-09-06T00:30:35.389266+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657903", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "submitTime": "2026-09-06T00:30:35.396277+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657902", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "submitTime": "2026-09-06T00:30:35.385964+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657900", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/zstack/qwen3-4b-fake", "modelId": "zstack/qwen3-4b-fake", "submitTime": "2026-09-06T00:30:35.392602+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657901", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-06T00:30:35.390810+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657904", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "submitTime": "2026-09-06T00:30:35.419799+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657897", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "submitTime": "2026-09-06T00:30:35.417747+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657896", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-8bit", "modelId": "mlx-community/Qwen3.8-27B-MTP-8bit", "submitTime": "2026-09-06T00:30:35.487200+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657899", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-mxfp8", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp8", "submitTime": "2026-09-06T00:30:35.426741+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657898", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "modelId": "RedHatAI/starcoder2-3b-FP8", "submitTime": "2026-09-06T00:30:40.351789+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657907", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "submitTime": "2026-09-06T00:30:40.393987+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657908", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "submitTime": "2026-09-06T00:30:40.391226+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657911", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-06T00:30:40.392742+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657912", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "submitTime": "2026-09-06T00:30:40.349157+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657906", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "submitTime": "2026-09-06T00:30:40.350638+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657905", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-2.9B-20260805", "modelId": "RWKV/RWKV7-2.9B-20260805", "submitTime": "2026-09-06T00:51:47.515580+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4658219", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "submitTime": "2026-09-06T02:23:39.684428+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659269", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-06T02:23:39.690219+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659268", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "submitTime": "2026-09-06T02:24:31.818066+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659299", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "submitTime": "2026-09-06T02:33:58.284464+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659388", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-13.3B-20260805", "modelId": "RWKV/RWKV7-13.3B-20260805", "submitTime": "2026-09-06T03:45:55.331628+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660328", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "submitTime": "2026-09-06T03:52:18.510578+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660434", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-06T04:17:45.285806+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660827", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "submitTime": "2026-09-06T04:38:16.005175+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4661079", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "submitTime": "2026-09-06T05:06:36.493823+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661437", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-06T06:30:19.979390+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4662535", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-06T07:02:35.712857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4662918", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-06T07:17:44.185498+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4663094", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-13.3B-20260805", "modelId": "RWKV/RWKV7-13.3B-20260805", "submitTime": "2026-09-06T07:35:56.293000+00:00", "targetGpu": "MetaX_c-500", "taskId": "4663310", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "submitTime": "2026-09-06T07:56:28.496520+00:00", "targetGpu": "MetaX_c-500", "taskId": "4663539", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-06T08:12:14.777960+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4663715", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-06T08:34:09.456899+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4664143", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-06T09:06:12.932838+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4664478", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "submitTime": "2026-09-06T09:13:43.657662+00:00", "targetGpu": "MetaX_c-500", "taskId": "4664576", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-06T09:46:33.145376+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4664976", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-7.2B-20260805", "modelId": "RWKV/RWKV7-7.2B-20260805", "submitTime": "2026-09-06T10:24:50.148662+00:00", "targetGpu": "MetaX_c-500", "taskId": "4665474", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-06T10:24:50.144356+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4665470", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-06T12:37:22.515030+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4667091", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelId": "neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "submitTime": "2026-09-06T13:58:59.194804+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667926", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-70B-FP8", "modelId": "neuralmagic/Meta-Llama-3.1-70B-FP8", "submitTime": "2026-09-06T13:58:59.550329+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667927", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-06T14:01:57.388649+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668028", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/siliconflow/gpt-oss-20b-FP8", "modelId": "siliconflow/gpt-oss-20b-FP8", "submitTime": "2026-09-06T14:32:32.785339+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668538", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "submitTime": "2026-09-06T14:33:50.986624+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668642", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/zstack/qwen3-4b-fake", "modelId": "zstack/qwen3-4b-fake", "submitTime": "2026-09-06T15:05:58.785747+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669358", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "submitTime": "2026-09-06T15:07:54.384483+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669411", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-7.2B-20260805", "modelId": "RWKV/RWKV7-7.2B-20260805", "submitTime": "2026-09-06T16:48:59.678173+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4672290", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-1.5B-20260805", "modelId": "RWKV/RWKV7-1.5B-20260805", "submitTime": "2026-09-06T18:34:36.628828+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4674757", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-06T19:48:32.773868+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4676609", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "submitTime": "2026-09-06T19:48:32.797983+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4676625", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "submitTime": "2026-09-06T20:23:42.610808+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4677309", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenOneRec/OneReason-8B-pretrain-competition", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "submitTime": "2026-09-06T20:54:07.883252+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4677960", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "submitTime": "2026-09-06T21:08:47.388697+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678359", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "submitTime": "2026-09-06T21:08:47.402496+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678379", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-06T21:15:16.244457+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678529", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "submitTime": "2026-09-06T21:25:37.107095+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678756", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-06T21:25:37.111002+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678760", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "modelId": "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "submitTime": "2026-09-06T21:38:26.181785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679070", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/groxaxo/qwen36-reap-2k-mlx-q8", "modelId": "groxaxo/qwen36-reap-2k-mlx-q8", "submitTime": "2026-09-06T21:46:28.939188+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679344", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "submitTime": "2026-09-06T21:55:23.563817+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679536", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-06T22:04:12.078346+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4679732", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-06T22:04:12.072657+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4679733", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-GGUF", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-07T09:29:07.790789+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4691709", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-GGUF", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-07T09:53:15.317620+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4692145", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-GGUF", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-07T10:17:32.532423+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4692612", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-GGUF", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-07T10:34:41.435624+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4693000", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-GGUF", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-07T10:57:50.465064+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4693286", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T12:14:20.888757+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4694739", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T12:42:26.505824+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4695129", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-07T12:42:26.513703+00:00", "targetGpu": "Vastai_va16", "taskId": "4695130", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T12:50:14.422978+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4695252", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T13:14:08.050211+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4695580", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-07T14:21:55.293071+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4697078", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-07T14:48:02.492557+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4697753", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-07T15:08:53.697776+00:00", "targetGpu": "Vastai_va16", "taskId": "4698268", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-07T15:35:43.483187+00:00", "targetGpu": "MetaX_c-500", "taskId": "4698954", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-07T16:01:34.238434+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4699472", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-07T16:06:40.552870+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4699585", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-07T16:31:45.492609+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4700151", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T17:27:44.564043+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4701029", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-07T17:27:44.568075+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4701030", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-07T19:56:19.088834+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4703149", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-gguf", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "submitTime": "2026-09-08T00:43:38.323540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4707395", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-gguf", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "submitTime": "2026-09-08T00:49:03.895304+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4707512", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-gguf", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "submitTime": "2026-09-08T01:08:15.662956+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4707808", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-gguf", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "submitTime": "2026-09-08T01:27:22.581440+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4708072", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T02:54:25.526666+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4709522", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T03:16:59.351441+00:00", "targetGpu": "Vastai_va16", "taskId": "4709818", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T03:37:14.233789+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4710114", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T03:58:12.682940+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4710401", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T04:20:35.203447+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4710796", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T05:08:32.946681+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4711416", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/zstack/qwen3-4b-fake", "modelId": "zstack/qwen3-4b-fake", "submitTime": "2026-09-08T06:46:06.785300+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712808", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T06:46:06.799047+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712803", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "submitTime": "2026-09-08T06:46:11.590454+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712813", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "submitTime": "2026-09-08T06:46:11.606547+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712821", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-08T06:46:11.792714+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712824", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "submitTime": "2026-09-08T06:46:11.811424+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712831", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T07:15:16.493472+00:00", "targetGpu": "Biren_166m", "taskId": "4713227", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-08T07:15:16.486536+00:00", "targetGpu": "Biren_166m", "taskId": "4713230", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-08T07:15:16.487544+00:00", "targetGpu": "Biren_166m", "taskId": "4713228", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "submitTime": "2026-09-08T07:15:16.512621+00:00", "targetGpu": "Biren_166m", "taskId": "4713225", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-08T07:15:16.515462+00:00", "targetGpu": "Biren_166m", "taskId": "4713229", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "submitTime": "2026-09-08T07:15:16.585542+00:00", "targetGpu": "Biren_166m", "taskId": "4713226", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "submitTime": "2026-09-08T07:15:16.516825+00:00", "targetGpu": "Biren_166m", "taskId": "4713224", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-08T07:15:24.345690+00:00", "targetGpu": "Biren_166m", "taskId": "4713233", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-08T07:15:24.160342+00:00", "targetGpu": "Biren_166m", "taskId": "4713232", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "submitTime": "2026-09-08T07:15:24.169874+00:00", "targetGpu": "Biren_166m", "taskId": "4713231", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T07:30:11.995863+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4713445", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T09:15:31.168687+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4715997", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T09:42:38.119885+00:00", "targetGpu": "Vastai_va16", "taskId": "4716367", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T09:50:25.159456+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4716485", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T10:18:12.673769+00:00", "targetGpu": "Biren_166m", "taskId": "4716910", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-gguf", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "submitTime": "2026-09-08T10:26:22.306973+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4717031", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T10:26:22.313092+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4717029", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T10:26:22.308491+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4717030", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T10:53:08.602969+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4717458", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T12:11:32.114244+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4718632", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "submitTime": "2026-09-08T12:23:10.100285+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4718771", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Abiray/MiniCPM5-2B-GGUF", "modelId": "Abiray/MiniCPM5-2B-GGUF", "submitTime": "2026-09-08T12:23:10.091322+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4718772", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "submitTime": "2026-09-08T12:52:27.905778+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4719218", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Abiray/MiniCPM5-2B-GGUF", "modelId": "Abiray/MiniCPM5-2B-GGUF", "submitTime": "2026-09-08T12:52:27.907475+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4719219", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T13:04:27.346213+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4719399", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "submitTime": "2026-09-08T13:16:04.810496+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4719506", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Abiray/MiniCPM5-2B-GGUF", "modelId": "Abiray/MiniCPM5-2B-GGUF", "submitTime": "2026-09-08T13:16:04.812757+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4719505", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "submitTime": "2026-09-08T13:51:12.910659+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4720103", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Abiray/MiniCPM5-2B-GGUF", "modelId": "Abiray/MiniCPM5-2B-GGUF", "submitTime": "2026-09-08T13:51:12.945092+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4720102", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-08T14:28:33.026055+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720562", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-08T14:28:33.085348+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720559", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-08T14:28:33.024677+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720556", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-08T14:28:33.026999+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720558", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-08T14:28:33.089405+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720561", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T14:28:33.027925+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720557", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-08T14:28:33.092238+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720555", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "submitTime": "2026-09-08T14:28:33.086935+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4720553", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Abiray/MiniCPM5-2B-GGUF", "modelId": "Abiray/MiniCPM5-2B-GGUF", "submitTime": "2026-09-08T14:28:33.090401+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4720554", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-08T14:39:15.996200+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720681", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-08T14:58:24.213075+00:00", "targetGpu": "Vastai_va16", "taskId": "4720983", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-08T14:58:24.210777+00:00", "targetGpu": "Vastai_va16", "taskId": "4720979", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-08T14:58:24.208286+00:00", "targetGpu": "Vastai_va16", "taskId": "4720984", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-08T14:58:24.214242+00:00", "targetGpu": "Vastai_va16", "taskId": "4720985", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-08T14:58:24.215700+00:00", "targetGpu": "Vastai_va16", "taskId": "4720981", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T14:58:24.218435+00:00", "targetGpu": "Vastai_va16", "taskId": "4720980", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-08T14:58:24.217400+00:00", "targetGpu": "Vastai_va16", "taskId": "4720982", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-08T15:05:13.551982+00:00", "targetGpu": "Vastai_va16", "taskId": "4721081", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-08T15:22:51.992361+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721413", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-08T15:22:51.991246+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721411", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-08T15:22:51.987097+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721409", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-08T15:22:51.988362+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721412", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-08T15:22:51.993706+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721414", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T15:22:51.989914+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721415", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-08T15:22:51.985451+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721410", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-08T15:26:26.996071+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721484", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-08T15:41:22.303733+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721841", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-08T15:41:22.305654+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721844", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-08T15:41:22.307631+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721840", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-08T15:41:22.309020+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721846", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-08T15:41:22.315855+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721842", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T15:41:22.314461+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721845", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-08T15:41:22.317110+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721843", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-08T15:43:53.869220+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721908", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "submitTime": "2026-09-08T15:58:20.173410+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4722285", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-08T15:58:20.177612+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722290", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-08T15:58:20.180877+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722289", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-08T15:58:20.184579+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722291", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-08T15:58:20.179374+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722292", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-08T15:58:20.186731+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722286", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T15:58:20.188689+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722287", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-08T15:58:20.189892+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722288", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-08T16:02:47.947809+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722381", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T16:07:42.647348+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722474", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-08T16:15:24.569436+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722682", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-08T16:15:24.567153+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722680", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-08T16:15:24.576021+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722678", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-08T16:15:24.571340+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722675", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-08T16:15:24.574077+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722679", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T16:15:24.572715+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722676", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-08T16:15:24.583828+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722677", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "submitTime": "2026-09-08T16:15:24.585768+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4722681", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-08T16:20:22.756130+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722805", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-08T16:28:42.318975+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4722998", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-08T16:28:42.314056+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4722996", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-08T16:28:42.308404+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4722999", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-08T16:28:42.305740+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4722997", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-08T16:28:42.321758+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4723003", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-08T16:28:42.307265+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4723000", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T16:28:42.324067+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4723001", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-08T16:28:42.320180+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4723002", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-08T18:47:44.090028+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725841", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-08T18:47:44.091884+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725848", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-08T18:47:44.019663+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725846", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-08T18:47:44.016617+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725850", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-08T18:47:44.023701+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725842", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-08T18:47:44.085412+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725845", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T18:47:44.095472+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725851", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-08T18:47:44.088412+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725847", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "submitTime": "2026-09-08T18:47:44.094485+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725844", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-08T18:47:44.086665+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725843", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-08T18:47:44.090923+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725849", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "submitTime": "2026-09-08T18:47:44.093470+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725852", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/prithivMLmods/MiniCPM5-2B-GGUF", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "submitTime": "2026-09-08T19:24:44.852247+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4726325", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/prithivMLmods/MiniCPM5-2B-GGUF", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "submitTime": "2026-09-08T19:44:39.694828+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4726617", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-08T21:14:03.823550+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4727746", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-08T21:29:34.930719+00:00", "targetGpu": "Vastai_va16", "taskId": "4727973", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-08T21:48:30.702694+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4728207", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-08T22:05:28.693168+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4728506", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-08T22:23:01.734631+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4728907", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-08T22:24:50.419230+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4728926", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-08T22:42:29.518873+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4729173", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-08T22:49:56.922360+00:00", "targetGpu": "Biren_166m", "taskId": "4729267", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-08T22:49:56.908214+00:00", "targetGpu": "Biren_166m", "taskId": "4729269", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-08T22:49:56.920583+00:00", "targetGpu": "Biren_166m", "taskId": "4729268", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-08T22:49:56.910926+00:00", "targetGpu": "Biren_166m", "taskId": "4729272", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-08T22:49:56.914465+00:00", "targetGpu": "Biren_166m", "taskId": "4729271", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-08T22:49:56.911982+00:00", "targetGpu": "Biren_166m", "taskId": "4729270", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T22:49:56.913066+00:00", "targetGpu": "Biren_166m", "taskId": "4729273", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-08T22:49:56.923972+00:00", "targetGpu": "Biren_166m", "taskId": "4729274", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-08T22:49:56.925801+00:00", "targetGpu": "Biren_166m", "taskId": "4729275", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-08T23:02:45.687861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729507", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-08T23:02:45.664222+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729503", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-08T23:02:45.690523+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729502", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-08T23:02:45.686402+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729506", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-08T23:02:45.691566+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729498", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-08T23:02:45.689318+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729505", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-08T23:02:45.694196+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729499", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-08T23:02:45.696067+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729497", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-08T23:02:45.702007+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729500", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "submitTime": "2026-09-08T23:02:51.785155+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729509", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-08T23:02:51.831733+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729515", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "modelId": "siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "submitTime": "2026-09-08T23:02:51.924564+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729534", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "submitTime": "2026-09-08T23:02:51.933574+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729525", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill", "modelId": "empero-ai/Qwen3.8-9B-Distill", "submitTime": "2026-09-08T23:02:51.939534+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729523", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-08T23:02:52.094406+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729529", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-08T23:02:52.086476+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729527", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-7.2B-20260805", "modelId": "RWKV/RWKV7-7.2B-20260805", "submitTime": "2026-09-08T23:02:52.096464+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729531", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/dealignai/MiniMax-M2.7-JANGTQ-CRACK", "modelId": "dealignai/MiniMax-M2.7-JANGTQ-CRACK", "submitTime": "2026-09-08T23:02:52.031559+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729530", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Hy3-OptiQ-2bit", "modelId": "mlx-community/Hy3-OptiQ-2bit", "submitTime": "2026-09-08T23:02:52.159484+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729532", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/hf/OBLITERATUS-Ornith-1.5-9B-OBLITERATED", "modelId": "hf/OBLITERATUS-Ornith-1.5-9B-OBLITERATED", "submitTime": "2026-09-08T23:02:52.350274+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729535", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-08T23:02:52.386802+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729533", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/MiniMax-M2.7-JANG_K", "modelId": "JANGQ-AI/MiniMax-M2.7-JANG_K", "submitTime": "2026-09-08T23:02:52.545079+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729537", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-08T23:02:52.997156+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729536", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/prithivMLmods/MiniCPM5-2B-GGUF", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "submitTime": "2026-09-09T00:13:44.993981+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730579", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-09T00:13:45.008972+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730582", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-09T00:13:45.012578+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730585", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-09T00:13:44.995252+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730580", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-09T00:13:45.016194+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730586", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-09T00:13:45.014363+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730587", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-09T00:13:45.003355+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730583", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-09T00:13:45.007232+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730581", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-09T00:13:45.047245+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730590", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-09T00:13:45.027681+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730589", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-09T00:13:45.019303+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730588", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-09T00:13:45.021813+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730584", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "submitTime": "2026-09-09T00:13:45.139430+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730592", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-09T00:13:45.141151+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730591", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "submitTime": "2026-09-09T02:14:39.291294+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4732363", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-09T03:27:23.590101+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4733219", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-09T03:43:18.853211+00:00", "targetGpu": "Vastai_va16", "taskId": "4733415", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-09T03:59:11.865737+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4733621", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-09T04:15:09.998965+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4733756", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-09T04:30:36.752310+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4733926", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "submitTime": "2026-09-09T06:38:12.914042+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4735580", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-09T06:38:12.915477+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4735579", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "submitTime": "2026-09-09T06:54:09.304972+00:00", "targetGpu": "Vastai_va16", "taskId": "4735789", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-09T06:54:09.310751+00:00", "targetGpu": "Vastai_va16", "taskId": "4735790", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "submitTime": "2026-09-09T07:10:09.840421+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4736014", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-09T07:10:50.992166+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4736027", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-09T07:10:50.969872+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4736028", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "submitTime": "2026-09-09T07:10:50.967869+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4736026", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "submitTime": "2026-09-09T07:25:45.301380+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4736171", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-09T07:26:57.684324+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4736186", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "submitTime": "2026-09-09T07:26:57.641158+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4736185", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Mungert/Spark-X2.5-1.7B-GGUF", "modelId": "Mungert/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-09T07:39:28.588872+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4736314", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "submitTime": "2026-09-09T07:42:00.347711+00:00", "targetGpu": "Biren_166m", "taskId": "4736338", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "submitTime": "2026-09-09T07:42:00.349244+00:00", "targetGpu": "Biren_166m", "taskId": "4736341", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-09T07:42:00.352448+00:00", "targetGpu": "Biren_166m", "taskId": "4736340", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-09T07:42:00.356711+00:00", "targetGpu": "Biren_166m", "taskId": "4736339", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-09T07:52:09.059377+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4736627", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/Mungert/Spark-X2.5-1.7B-GGUF", "modelId": "Mungert/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-09T07:54:32.268749+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4736698", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-09T08:07:14.060941+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4736884", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "submitTime": "2026-09-09T08:10:45.446803+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4736920", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-09T08:10:45.450685+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4736922", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-09T08:10:45.448357+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4736923", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "submitTime": "2026-09-09T08:10:45.445768+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4736921", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-09T09:45:56.240950+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4738124", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-09T10:00:13.353192+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4738344", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-09T10:01:35.815834+00:00", "targetGpu": "Vastai_va16", "taskId": "4738373", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-09T10:15:29.199861+00:00", "targetGpu": "Vastai_va16", "taskId": "4738578", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-09T10:16:45.484218+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4738593", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-09T10:31:32.626874+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4738925", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-09T10:32:50.129162+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4738947", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-09T10:46:50.761768+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4739146", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-09T10:46:50.760190+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4739145", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-09T11:02:10.941643+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4739315", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-09T11:02:10.942699+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4739316", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-09T11:08:41.646654+00:00", "targetGpu": "Biren_166m", "taskId": "4739398", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-09T11:18:03.045534+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4739524", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-09T11:18:03.047370+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4739523", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-09T11:18:03.048835+00:00", "targetGpu": "Biren_166m", "taskId": "4739522", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-09T11:33:17.847799+00:00", "targetGpu": "Vastai_va16", "taskId": "4739773", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-09T11:33:17.843220+00:00", "targetGpu": "Vastai_va16", "taskId": "4739774", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-09T11:33:17.848974+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4739772", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-09T11:48:22.113026+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4739932", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-09T11:48:22.109630+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4739931", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-09T11:50:46.743760+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4739959", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-09T11:50:46.742747+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4739958", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-09T12:03:37.164977+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4740109", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-09T12:03:37.168524+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4740110", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-09T12:18:42.029908+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4740277", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-09T12:18:42.031229+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4740276", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-09T12:30:12.295655+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4740399", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-09T12:30:12.298654+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4740400", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-09T13:24:40.846297+00:00", "targetGpu": "Biren_166m", "taskId": "4741083", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-09T13:24:40.847590+00:00", "targetGpu": "Biren_166m", "taskId": "4741082", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-09T15:04:57.782677+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4742257", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-09T15:04:57.783545+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4742256", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-09T16:58:40.742484+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4743575", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-09T17:17:51.553387+00:00", "targetGpu": "Vastai_va16", "taskId": "4743762", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-09T17:36:33.499638+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4743919", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b3"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-09T17:53:28.482893+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4744096", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-09T18:11:56.418165+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4744370", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-09T18:31:44.217327+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4744546", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "submitTime": "2026-09-09T21:08:22.089453+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746439", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "submitTime": "2026-09-09T21:08:22.086828+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746438", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-09T21:08:22.085342+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746443", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-09T21:08:22.047953+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746444", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-09T21:08:22.090694+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746448", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-09T21:08:22.093383+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746449", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-09T21:08:22.095630+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746442", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-09T21:08:22.098266+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746440", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-09T21:08:22.088163+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746445", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "submitTime": "2026-09-09T21:08:22.091584+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746446", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "submitTime": "2026-09-09T21:08:32.651613+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746451", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-09T21:08:32.647276+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746452", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "submitTime": "2026-09-09T21:08:32.653546+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746450", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-09T21:08:32.655185+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746453", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "submitTime": "2026-09-09T21:08:32.684861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746455", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/MiniMax-M2.7-JANGTQ_K", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ_K", "submitTime": "2026-09-09T21:08:32.618999+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746456", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "submitTime": "2026-09-09T21:08:32.656390+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746454", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "submitTime": "2026-09-10T00:22:02.859936+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749146", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-10T00:22:02.850913+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749148", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-10T00:22:02.864784+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749147", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-10T00:22:02.853008+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749145", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-10T00:22:02.857970+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749149", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-10T00:22:02.862038+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749144", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-10T00:22:02.847614+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749143", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B", "modelId": "OpenBMB/MiniCPM5-2B", "submitTime": "2026-09-10T00:42:56.091512+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749457", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-10T00:42:56.051663+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749456", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-10T00:42:56.093785+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749466", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-10T00:42:56.090459+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749455", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-10T00:42:56.084513+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749459", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-10T00:42:56.097416+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749460", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-10T00:42:56.053014+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749465", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-10T00:42:56.095206+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749461", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-10T00:42:56.089395+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749462", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-10T00:42:56.092535+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749464", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "submitTime": "2026-09-10T00:42:56.087894+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749458", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-10T00:42:56.096428+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749463", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-10T00:43:04.111606+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749472", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-10T00:43:04.113703+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749467", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-10T00:43:04.115623+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749468", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "submitTime": "2026-09-10T00:43:04.107121+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749470", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-10T00:43:04.109010+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749469", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-10T00:43:04.105705+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749471", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-10T02:01:08.689124+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4750549", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-SFT", "modelId": "whq1111/M2RL-SFT", "submitTime": "2026-09-10T03:12:18.064831+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751419", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Math", "modelId": "whq1111/M2RL-RL_Math", "submitTime": "2026-09-10T03:12:18.083836+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751414", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Multi", "modelId": "whq1111/M2RL-RL_Multi", "submitTime": "2026-09-10T03:12:17.982820+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751417", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Science", "modelId": "whq1111/M2RL-RL_Science", "submitTime": "2026-09-10T03:12:17.984748+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751412", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-MT_OPD", "modelId": "whq1111/M2RL-MT_OPD", "submitTime": "2026-09-10T03:12:18.150266+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751411", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Agent", "modelId": "whq1111/M2RL-RL_Agent", "submitTime": "2026-09-10T03:12:18.172325+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751418", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_Coding", "modelId": "whq1111/M2RL-RL_Coding", "submitTime": "2026-09-10T03:12:17.999954+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751416", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/whq1111/M2RL-RL_IF", "modelId": "whq1111/M2RL-RL_IF", "submitTime": "2026-09-10T03:12:18.166785+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751421", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-MLX", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "submitTime": "2026-09-10T03:12:18.090220+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751422", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-10T03:12:18.009997+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751413", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-10T03:12:18.066416+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751420", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-10T03:12:18.084969+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751415", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-10T03:12:37.198105+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751425", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-10T03:12:37.196301+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751423", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-10T03:12:37.222862+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751424", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-10T03:12:37.226057+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751427", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-10T03:12:37.213099+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751426", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-10T05:13:27.470794+00:00", "targetGpu": "Vastai_va16", "taskId": "4753071", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-10T05:29:20.581004+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4753478", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T05:39:25.454183+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753713", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T05:39:25.451335+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753714", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "submitTime": "2026-09-10T05:39:25.452554+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753715", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-10T05:47:10.742578+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753833", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/bartowski/MiniCPM5-2B-GGUF", "modelId": "bartowski/MiniCPM5-2B-GGUF", "submitTime": "2026-09-10T05:54:18.783901+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754025", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T05:55:59.442486+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754066", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T05:55:59.435840+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754067", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "submitTime": "2026-09-10T05:55:59.437900+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754068", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-10T06:03:37.655467+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754205", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/bartowski/MiniCPM5-2B-GGUF", "modelId": "bartowski/MiniCPM5-2B-GGUF", "submitTime": "2026-09-10T06:11:11.806743+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4754342", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T06:11:11.799771+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4754343", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T06:12:56.897964+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754370", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T06:12:56.900331+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754369", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "submitTime": "2026-09-10T06:12:56.905628+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4754371", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/bartowski/MiniCPM5-2B-GGUF", "modelId": "bartowski/MiniCPM5-2B-GGUF", "submitTime": "2026-09-10T06:28:56.145522+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4754660", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T06:28:56.134725+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754659", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T06:30:53.020882+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754721", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T06:30:53.025848+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754722", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T06:38:16.883366+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754820", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-10T06:38:16.885606+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4754819", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T06:48:30.776019+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4755021", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T06:48:30.777395+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4755020", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T06:56:12.042564+00:00", "targetGpu": "Vastai_va16", "taskId": "4755190", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T07:12:26.211286+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755594", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T07:12:26.212561+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755595", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "submitTime": "2026-09-10T07:12:26.204766+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755596", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T07:12:26.209710+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755597", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-10T07:12:26.214438+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755598", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T07:23:10.180003+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4755805", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T07:33:41.787375+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4756078", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T07:50:25.385741+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4756398", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T09:52:16.471862+00:00", "targetGpu": "MetaX_c-500", "taskId": "4758203", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T13:27:23.407832+00:00", "targetGpu": "Biren_166m", "taskId": "4760701", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T13:27:23.401229+00:00", "targetGpu": "Biren_166m", "taskId": "4760703", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "submitTime": "2026-09-10T13:27:23.406185+00:00", "targetGpu": "Biren_166m", "taskId": "4760702", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T13:27:23.410963+00:00", "targetGpu": "Biren_166m", "taskId": "4760705", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-10T13:27:23.404088+00:00", "targetGpu": "Biren_166m", "taskId": "4760700", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-10T13:27:23.409305+00:00", "targetGpu": "Biren_166m", "taskId": "4760704", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-10T14:46:30.894640+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761529", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-10T14:46:30.888510+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761528", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "submitTime": "2026-09-10T14:46:30.890611+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761532", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-10T14:46:30.893195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761530", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-10T14:46:30.895806+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761531", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "modelId": "webAI-Official/TwIL-LM3", "submitTime": "2026-09-10T15:13:26.242352+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4761809", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "modelId": "webAI-Official/TwIL-LM3", "submitTime": "2026-09-10T15:29:43.673390+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4761977", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "modelId": "webAI-Official/TwIL-LM3", "submitTime": "2026-09-10T15:48:00.105279+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4762249", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "modelId": "webAI-Official/TwIL-LM3", "submitTime": "2026-09-10T16:07:13.322943+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4762525", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "modelId": "webAI-Official/TwIL-LM3", "submitTime": "2026-09-10T16:25:38.566044+00:00", "targetGpu": "Vastai_va16", "taskId": "4762814", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "modelId": "webAI-Official/TwIL-LM3", "submitTime": "2026-09-10T16:44:41.216042+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4763237", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/guaidao2/LFM2.5-2.6B-For-CTF", "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "submitTime": "2026-09-10T17:52:07.266826+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4764441", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/guaidao2/LFM2.5-2.6B-For-CTF", "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "submitTime": "2026-09-10T18:09:17.543816+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4764783", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/guaidao2/LFM2.5-2.6B-For-CTF", "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "submitTime": "2026-09-10T18:25:40.316507+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4765091", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "modelId": "webAI-Official/TwIL-LM3", "submitTime": "2026-09-10T19:50:31.405521+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4766604", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "modelId": "webAI-Official/TwIL-LM3", "submitTime": "2026-09-10T22:33:54.829362+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4768606", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-11T00:23:48.375203+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4769876", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-11T00:23:48.372888+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4769875", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "modelId": "webAI-Official/TwIL-LM3", "submitTime": "2026-09-11T02:28:05.101259+00:00", "targetGpu": "Biren_166m", "taskId": "4771184", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/guaidao2/LFM2.5-2.6B-For-CTF", "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "submitTime": "2026-09-11T10:27:33.286927+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776571", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-NVFP4", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "submitTime": "2026-09-11T10:27:33.285223+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776565", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "submitTime": "2026-09-11T10:27:33.293196+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776566", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-GPTQ", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "submitTime": "2026-09-11T10:27:33.288482+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776572", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Base", "modelId": "OpenBMB/MiniCPM5-2B-Base", "submitTime": "2026-09-11T10:27:33.289821+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776567", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-SFT", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "submitTime": "2026-09-11T10:27:33.292184+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776574", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-Midtrain", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "submitTime": "2026-09-11T10:27:33.294996+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776570", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "submitTime": "2026-09-11T10:27:33.290699+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776568", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-4B", "modelId": "TokenRhythm/NeoHorse-1-4B", "submitTime": "2026-09-11T10:27:33.294068+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776569", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/TokenRhythm/NeoHorse-1-9B", "modelId": "TokenRhythm/NeoHorse-1-9B", "submitTime": "2026-09-11T10:27:33.315729+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776573", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "submitTime": "2026-09-11T10:27:40.672353+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776577", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "modelId": "CohereLabs/tiny-aya-en-thinker", "submitTime": "2026-09-11T10:27:40.677288+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776576", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/laion/swesmith-nl2bash-stack-bugsseq", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "submitTime": "2026-09-11T10:27:40.674298+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776575", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "modelId": "BAAI/AREX-Turbo", "submitTime": "2026-09-11T10:27:40.670287+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776578", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "submitTime": "2026-09-11T15:30:58.007700+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4782245", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-11T15:45:34.084559+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4782449", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "submitTime": "2026-09-11T15:47:34.151696+00:00", "targetGpu": "Vastai_va16", "taskId": "4782467", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-11T16:03:11.891697+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4782663", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "submitTime": "2026-09-11T16:05:31.441883+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4782685", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-11T16:20:38.542601+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4782813", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "submitTime": "2026-09-11T16:22:36.317588+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4782838", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "submitTime": "2026-09-11T16:36:55.600970+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4782993", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-11T16:38:55.116829+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4783004", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-11T16:49:10.249505+00:00", "targetGpu": "Vastai_va16", "taskId": "4783129", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm-customized", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "submitTime": "2026-09-11T16:54:32.845710+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4783202", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-customized-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-11T17:01:11.403970+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4783339", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-11T17:12:06.612979+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4783476", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-11T17:22:24.744587+00:00", "targetGpu": "MetaX_c-500", "taskId": "4783634", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/guaidao2/LFM2.5-2.6B-For-CTF", "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "submitTime": "2026-09-11T18:18:29.685555+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4784429", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-11T18:18:29.687478+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4784430", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-11T18:51:22.774816+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4784981", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "submitTime": "2026-09-11T18:51:22.770505+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4784982", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-12T01:22:51.902664+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4791408", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "submitTime": "2026-09-12T01:22:51.904770+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4791409", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nex-agi/Nex-N2.5-mini", "modelId": "nex-agi/Nex-N2.5-mini", "submitTime": "2026-09-12T01:22:51.908714+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4791410", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-12T04:52:57.116897+00:00", "targetGpu": "Biren_166m", "taskId": "4794241", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "submitTime": "2026-09-12T04:52:57.114996+00:00", "targetGpu": "Biren_166m", "taskId": "4794242", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "submitTime": "2026-09-12T06:19:56.330927+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4795478", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "submitTime": "2026-09-12T06:36:56.396629+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4795634", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "submitTime": "2026-09-12T06:53:56.898337+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4795839", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "submitTime": "2026-09-12T10:58:56.807180+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800525", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "modelId": "unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "submitTime": "2026-09-12T10:58:56.798553+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800526", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "submitTime": "2026-09-12T14:09:52.635448+00:00", "targetGpu": "Biren_166m", "taskId": "4803464", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-35B-A3B-8bit", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "submitTime": "2026-09-12T16:07:22.080195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4804755", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/cloudlnk/Spark-X2.5-4B-GGUF", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-12T16:59:17.247535+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4805292", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/cloudlnk/Spark-X2.5-4B-GGUF", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-12T17:16:39.306865+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4805471", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b3"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/cloudlnk/Spark-X2.5-4B-GGUF", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-12T17:35:57.210723+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4805660", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/cloudlnk/Spark-X2.5-4B-GGUF", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-12T17:53:40.152278+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4805869", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/cloudlnk/Spark-X2.5-4B-GGUF", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "submitTime": "2026-09-13T04:41:29.954503+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4817350", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-base-32K", "modelId": "CohereLabs/tiny-aya-base-32K", "submitTime": "2026-09-13T04:41:29.963690+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4817349", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "submitTime": "2026-09-13T04:41:29.962163+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4817348", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T04:51:53.062775+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4817454", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T05:10:44.864092+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4817675", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T05:29:18.044774+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4817992", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T05:34:18.006195+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4818284", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T05:44:36.060924+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4818885", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T06:03:08.407319+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4819935", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T09:53:52.905331+00:00", "targetGpu": "MetaX_c-500", "taskId": "4823778", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T10:16:13.410881+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4824251", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T12:09:15.680573+00:00", "targetGpu": "Vastai_va16", "taskId": "4827491", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T14:02:33.487789+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4829151", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-INT8", "modelId": "XHToken/Spark-X2.5-4B-INT8", "submitTime": "2026-09-13T14:24:08.911334+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4829350", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-08T16:07:42.654192+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722475", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-2.9B-20260805", "modelId": "RWKV/RWKV7-2.9B-20260805", "submitTime": "2026-09-09T21:08:22.094532+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746447", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-09T00:13:45.146237+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730594", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nm-testing/nonuniform", "modelId": "nm-testing/nonuniform", "submitTime": "2026-09-08T06:46:06.780642+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712802", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-FP8", "modelId": "RedHatAI/starcoder2-3b-FP8", "submitTime": "2026-09-08T06:46:06.808048+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712807", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "submitTime": "2026-09-08T06:46:06.810137+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712809", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "submitTime": "2026-09-08T06:46:11.532675+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712815", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-08T06:46:11.601676+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712820", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-7.2B-20260805", "modelId": "RWKV/RWKV7-7.2B-20260805", "submitTime": "2026-09-08T06:46:11.589203+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712819", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "submitTime": "2026-09-08T23:02:45.685300+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729504", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a8", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "submitTime": "2026-09-08T23:02:51.818347+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729510", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.847566+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729520", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "submitTime": "2026-09-08T23:02:51.830682+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729514", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.824770+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729512", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.913002+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729521", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-1.5B-20260805", "modelId": "RWKV/RWKV7-1.5B-20260805", "submitTime": "2026-09-08T23:02:52.084632+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729528", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "submitTime": "2026-09-09T00:13:45.142420+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730593", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-09T00:13:45.155081+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730595", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-1.5B-20260805", "modelId": "RWKV/RWKV7-1.5B-20260805", "submitTime": "2026-09-05T13:47:55.466466+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649912", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-15b-quantized.w8a16", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-06T15:28:09.684321+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669863", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-1.5B-20260805", "modelId": "RWKV/RWKV7-1.5B-20260805", "submitTime": "2026-09-08T06:46:11.531728+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712811", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "modelId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "submitTime": "2026-09-08T23:02:45.784701+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729501", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "submitTime": "2026-09-08T23:02:45.697968+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729508", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/FlagRelease/Qwen3.5-35B-A3B-hygon-FlagOS", "modelId": "FlagRelease/Qwen3.5-35B-A3B-hygon-FlagOS", "submitTime": "2026-09-08T23:02:51.829157+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729513", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/FlagRelease/Qwen3.5-35B-A3B-iluvatar-FlagOS", "modelId": "FlagRelease/Qwen3.5-35B-A3B-iluvatar-FlagOS", "submitTime": "2026-09-08T23:02:51.822402+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729511", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.843439+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729517", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.889698+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729518", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "modelId": "RedHatAI/starcoder2-7b-FP8", "submitTime": "2026-09-08T23:02:51.841387+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729516", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "submitTime": "2026-09-08T23:02:51.888188+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729519", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "submitTime": "2026-09-08T23:02:51.995104+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729526", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "submitTime": "2026-09-08T23:02:51.985375+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729522", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-08T23:02:51.998598+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729524", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/vastai-ais/GLM-OCR-FP8", "modelId": "vastai-ais/GLM-OCR-FP8", "submitTime": "2026-09-04T21:32:51.205525+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634661", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "modelId": "BAAI/AquilaMed-RL", "submitTime": "2026-09-05T09:38:43.488297+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645739", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/sapientinc/HRM-Text-1B", "modelId": "sapientinc/HRM-Text-1B", "submitTime": "2026-09-05T16:20:38.387161+00:00", "targetGpu": "Vastai_va16", "taskId": "4651795", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "submitTime": "2026-09-05T16:23:35.585208+00:00", "targetGpu": "Vastai_va16", "taskId": "4651830", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/douyamv/Qwen3.8-27B-FP8", "modelId": "douyamv/Qwen3.8-27B-FP8", "submitTime": "2026-09-06T00:30:35.485447+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657895", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-4bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-4bit", "submitTime": "2026-09-06T00:30:40.389876+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657910", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill", "modelId": "empero-ai/Qwen3.8-9B-Distill", "submitTime": "2026-09-06T00:30:40.585784+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657913", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "submitTime": "2026-09-06T02:28:43.876366+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659340", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ZHTODD/llm-study-model", "modelId": "ZHTODD/llm-study-model", "submitTime": "2026-09-06T12:37:22.509920+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667092", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/BAAI/AquilaMed-RL", "modelId": "BAAI/AquilaMed-RL", "submitTime": "2026-09-06T15:28:09.686082+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669861", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-bf16", "modelId": "mlx-community/Qwen3.8-27B-MTP-bf16", "submitTime": "2026-09-06T20:59:59.616196+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678098", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "submitTime": "2026-09-04T03:57:15.119872+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610784", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "submitTime": "2026-09-04T03:57:15.184550+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610787", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "submitTime": "2026-09-04T03:57:15.188888+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610783", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/groxaxo/qwen36-reap-2k-mlx-q8", "modelId": "groxaxo/qwen36-reap-2k-mlx-q8", "submitTime": "2026-09-04T20:36:22.385440+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4633906", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "submitTime": "2026-09-04T20:41:27.058068+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4633956", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "modelId": "EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "submitTime": "2026-09-04T20:42:22.700314+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4633978", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "submitTime": "2026-09-04T21:21:28.856839+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634507", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/groxaxo/Qwen-AgentWorld-35B-A3B-GPTQ-Pro-Int4", "modelId": "groxaxo/Qwen-AgentWorld-35B-A3B-GPTQ-Pro-Int4", "submitTime": "2026-09-04T22:28:19.770846+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4635468", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "submitTime": "2026-09-04T23:07:33.297152+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4635981", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "submitTime": "2026-09-05T09:00:09.135600+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645040", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "submitTime": "2026-09-05T16:20:38.390632+00:00", "targetGpu": "Vastai_va16", "taskId": "4651793", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "submitTime": "2026-09-05T16:30:08.482261+00:00", "targetGpu": "Vastai_va16", "taskId": "4651930", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "modelId": "RedHatAI/starcoder2-7b-FP8", "submitTime": "2026-09-06T04:36:19.394975+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661051", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "submitTime": "2026-09-06T04:36:19.350592+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661017", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "submitTime": "2026-09-06T06:46:30.091299+00:00", "targetGpu": "MetaX_c-500", "taskId": "4662728", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "submitTime": "2026-09-06T07:25:42.990583+00:00", "targetGpu": "MetaX_c-500", "taskId": "4663206", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "submitTime": "2026-09-04T08:10:58.188745+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622622", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T08:21:52.578870+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622780", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T09:20:12.202888+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4623811", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "submitTime": "2026-09-04T14:16:10.707417+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4627927", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "submitTime": "2026-09-04T16:10:19.959444+00:00", "targetGpu": "MetaX_c-500", "taskId": "4629855", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "submitTime": "2026-09-04T21:05:48.185454+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634349", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-04T21:16:21.226380+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634451", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/douyamv/Qwen3.8-27B-FP8", "modelId": "douyamv/Qwen3.8-27B-FP8", "submitTime": "2026-09-04T21:32:51.155921+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634658", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "submitTime": "2026-09-04T21:32:51.157760+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634659", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-04T21:32:51.195048+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4634660", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-04T23:00:11.199172+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4635857", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "submitTime": "2026-09-04T23:00:11.288823+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4635881", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.8-27B-Escha-W2", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "submitTime": "2026-09-04T23:29:59.923019+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636374", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T23:30:00.024434+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636377", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill", "modelId": "empero-ai/Qwen3.8-9B-Distill", "submitTime": "2026-09-05T03:04:06.801568+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4639820", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "submitTime": "2026-09-05T05:17:16.494487+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641792", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "modelId": "nm-testing/Meta-Llama-3.1-8B-Instruct-FP8-hf", "submitTime": "2026-09-05T05:35:01.374880+00:00", "targetGpu": "MetaX_c-500", "taskId": "4642092", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "modelId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "submitTime": "2026-09-05T06:40:30.050084+00:00", "targetGpu": "MetaX_c-500", "taskId": "4642913", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "submitTime": "2026-09-05T06:44:12.985389+00:00", "targetGpu": "MetaX_c-500", "taskId": "4643008", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-05T06:44:19.785274+00:00", "targetGpu": "MetaX_c-500", "taskId": "4643009", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "submitTime": "2026-09-05T06:48:32.403505+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643044", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "submitTime": "2026-09-05T06:48:32.421211+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643047", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "submitTime": "2026-09-05T06:55:50.712446+00:00", "targetGpu": "MetaX_c-500", "taskId": "4643190", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "submitTime": "2026-09-05T09:02:11.018727+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645102", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "submitTime": "2026-09-05T09:39:34.974871+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645749", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-05T09:41:55.499198+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645815", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ValueFX/Qwen3.8-27B-CCCP-S", "modelId": "ValueFX/Qwen3.8-27B-CCCP-S", "submitTime": "2026-09-05T10:52:05.726238+00:00", "targetGpu": "MetaX_c-500", "taskId": "4646913", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "submitTime": "2026-09-05T12:03:37.093896+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648140", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/douyamv/Qwen3.8-27B-FP8", "modelId": "douyamv/Qwen3.8-27B-FP8", "submitTime": "2026-09-05T12:03:37.186540+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648144", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-4bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-4bit", "submitTime": "2026-09-05T12:03:37.188212+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648142", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-04T07:25:53.575378+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4621996", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T09:03:02.667914+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4623614", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/inclusionAI/Ling-3.0-tiny", "modelId": "inclusionAI/Ling-3.0-tiny", "submitTime": "2026-09-04T10:09:04.256069+00:00", "targetGpu": "MetaX_c-500", "taskId": "4624459", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-3b-FP8", "modelId": "neuralmagic/starcoder2-3b-FP8", "submitTime": "2026-09-04T13:16:31.483431+00:00", "targetGpu": "MetaX_c-500", "taskId": "4627000", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "submitTime": "2026-09-04T13:59:33.565872+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4627715", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "submitTime": "2026-09-04T16:10:19.950389+00:00", "targetGpu": "MetaX_c-500", "taskId": "4629854", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed", "submitTime": "2026-09-04T16:10:19.955805+00:00", "targetGpu": "MetaX_c-500", "taskId": "4629852", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "modelId": "neuralmagic/starcoder2-7b-FP8", "submitTime": "2026-09-04T16:26:22.572735+00:00", "targetGpu": "MetaX_c-500", "taskId": "4630165", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Instruct-4bit", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-4bit", "submitTime": "2026-09-04T07:42:09.151930+00:00", "targetGpu": "Biren_166m", "taskId": "4622185", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "modelId": "neuralmagic/Meta-Llama-3.1-8B-Instruct-FP8", "submitTime": "2026-09-04T11:50:51.558557+00:00", "targetGpu": "MetaX_c-500", "taskId": "4625818", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-04T20:58:35.788284+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4634199", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-04T21:05:42.757007+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4634331", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "submitTime": "2026-09-04T21:15:28.046326+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4634426", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "submitTime": "2026-09-04T22:50:01.926246+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4635732", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-04T22:55:41.172522+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4635811", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "submitTime": "2026-09-04T23:07:33.218745+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4635980", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed", "submitTime": "2026-09-04T23:29:59.903729+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636364", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "modelId": "logic65/Qwen3.8-Whittle-w50-18.3B-unrepaired", "submitTime": "2026-09-04T23:29:59.900374+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636367", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "modelId": "ewinregirgojr/Qwen3.8-9B-Instruct-Turbo", "submitTime": "2026-09-04T23:29:59.909654+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636366", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "submitTime": "2026-09-04T23:29:59.917494+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636368", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "modelId": "ewinregirgojr/Qwen3.8-14B-Instruct-Turbo", "submitTime": "2026-09-04T23:29:59.928416+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636371", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "submitTime": "2026-09-04T23:29:59.919656+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636373", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "submitTime": "2026-09-05T00:45:53.692926+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4637780", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "submitTime": "2026-09-05T00:49:16.845847+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4637844", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/douyamv/Qwen3.8-27B-FP8", "modelId": "douyamv/Qwen3.8-27B-FP8", "submitTime": "2026-09-05T01:43:47.001055+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4638700", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "submitTime": "2026-09-05T02:23:56.378267+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4639214", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill", "modelId": "empero-ai/Qwen3.8-9B-Distill", "submitTime": "2026-09-05T02:38:04.416442+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4639408", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-4bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-4bit", "submitTime": "2026-09-05T03:20:02.336601+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4640028", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "submitTime": "2026-09-05T03:20:38.385980+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4640053", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/siliconflow/gpt-oss-20b-FP8", "modelId": "siliconflow/gpt-oss-20b-FP8", "submitTime": "2026-09-05T03:56:12.609375+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4640644", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "modelId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "submitTime": "2026-09-05T03:56:12.700865+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4640661", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "submitTime": "2026-09-05T05:17:16.496259+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4641786", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "submitTime": "2026-09-06T03:59:01.992368+00:00", "targetGpu": "MetaX_c-500", "taskId": "4660498", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "submitTime": "2026-09-06T08:39:20.512136+00:00", "targetGpu": "MetaX_c-500", "taskId": "4664213", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "submitTime": "2026-09-06T10:24:50.185257+00:00", "targetGpu": "MetaX_c-500", "taskId": "4665471", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-06T10:24:50.186490+00:00", "targetGpu": "MetaX_c-500", "taskId": "4665472", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "submitTime": "2026-09-06T10:24:50.152860+00:00", "targetGpu": "MetaX_c-500", "taskId": "4665473", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "submitTime": "2026-09-06T10:24:50.157040+00:00", "targetGpu": "MetaX_c-500", "taskId": "4665469", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "modelId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "submitTime": "2026-09-06T11:11:43.508392+00:00", "targetGpu": "MetaX_c-500", "taskId": "4666063", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "modelId": "RedHatAI/SmolLM-1.7B-Instruct-quantized.w8a16", "submitTime": "2026-09-06T12:33:05.865501+00:00", "targetGpu": "MetaX_c-500", "taskId": "4667038", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/neuralmagic/starcoder2-7b-FP8", "modelId": "neuralmagic/starcoder2-7b-FP8", "submitTime": "2026-09-06T13:58:59.575035+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667928", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "modelId": "nm-testing/Meta-llama3-8b-Instruct-quant-FP8", "submitTime": "2026-09-06T15:05:45.990675+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669334", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Aimiliya0011/lora_4090", "modelId": "Aimiliya0011/lora_4090", "submitTime": "2026-09-06T15:28:15.568131+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669867", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "submitTime": "2026-09-08T06:46:06.795745+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712800", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "submitTime": "2026-09-08T06:46:06.887685+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712810", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Qwen2.5-1.5B-quantized.w4a16", "modelId": "RedHatAI/Qwen2.5-1.5B-quantized.w4a16", "submitTime": "2026-09-08T06:46:06.804740+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712806", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-15b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "submitTime": "2026-09-08T06:46:06.889991+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712799", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-3b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "submitTime": "2026-09-08T06:46:06.888683+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712801", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-FP8", "modelId": "RedHatAI/starcoder2-7b-FP8", "submitTime": "2026-09-08T06:46:06.891127+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712805", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "submitTime": "2026-09-08T06:46:06.886454+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712804", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-it-quantized.w4a16", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w4a16", "submitTime": "2026-09-08T06:46:11.594968+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712814", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/starcoder2-7b-quantized.w8a16", "modelId": "RedHatAI/starcoder2-7b-quantized.w8a16", "submitTime": "2026-09-08T06:46:11.586014+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712812", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/RedHatAI/gemma-2-2b-quantized.w8a16", "modelId": "RedHatAI/gemma-2-2b-quantized.w8a16", "submitTime": "2026-09-08T06:46:11.593738+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712817", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "submitTime": "2026-09-08T06:46:11.586261+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712822", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "submitTime": "2026-09-08T06:46:11.587867+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712816", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "modelId": "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "submitTime": "2026-09-08T06:46:11.598902+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712818", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B", "modelId": "ornith-ai/Ornith-1.5-9B", "submitTime": "2026-09-08T06:46:11.817069+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712832", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-NVFP4", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "submitTime": "2026-09-08T06:46:11.791128+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712828", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "submitTime": "2026-09-08T06:46:11.795480+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712823", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "submitTime": "2026-09-08T06:46:11.787458+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712825", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-9B-Distill", "modelId": "empero-ai/Qwen3.8-9B-Distill", "submitTime": "2026-09-08T06:46:11.788912+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712827", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "submitTime": "2026-09-08T06:46:11.785071+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712826", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-08T06:46:11.797429+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712830", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "modelId": "Youssofal/Qwen3.5-9B-MTPLX-Optimized-Speed", "submitTime": "2026-09-08T06:46:11.803703+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712829", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "submitTime": "2026-09-08T06:46:11.884676+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712833", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "modelId": "EschaLabs/Qwen3.6-35B-A3B-Escha-W2", "submitTime": "2026-09-08T06:46:11.886266+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712834", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill", "modelId": "empero-ai/Qwen3.8-4B-Distill", "submitTime": "2026-09-08T06:46:11.927161+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712835", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "submitTime": "2026-09-08T06:46:11.928754+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712837", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "submitTime": "2026-09-08T06:46:11.934706+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712836", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-cambricon-mlu-370-x8"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "submitTime": "2026-09-08T14:03:45.031522+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4720262", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/JANGQ-AI/AppleScript-8B-JANG_4M", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "submitTime": "2026-09-08T15:58:20.200513+00:00", "targetGpu": "Vastai_va16", "taskId": "4722293", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/OpenBMB/BitCPM-CANN-8B", "modelId": "OpenBMB/BitCPM-CANN-8B", "submitTime": "2026-09-09T12:30:12.314907+00:00", "targetGpu": "Vastai_va16", "taskId": "4740401", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-vastai-va16"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "submitTime": "2026-09-09T21:08:22.097030+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746441", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}

24
manifest.json Normal file
View File

@@ -0,0 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "a2e3a162b4d1af55d576da5cf652e10d48c0302f1c7405e048eed2fd3cf5c884",
".modelhub_state/architecture_history_backfill.json": "4db41adacd2a71442032a6bb6a1cd5fb73f40ac1c573ed494ad5ab8a608a6675",
".modelhub_state/market_intelligence.json": "202f3a91359582b668f79a556d9142ef1f7e12f84ad99f513d6a461efaf68ac4",
".modelhub_state/official_capabilities.json": "4c19dad263667b45b94fd8a60cec95907b5fe9320740dcb35f1019b70caf5626",
".modelhub_state/outcome_checkpoint.json": "5f341f6e4179fde6ac5f74ccdc5d166f7f250ad012b0d56e3acee14189ed876e",
".modelhub_state/queue_cleanup_latest.json": "5b0dc54b913434ae76ea5833cabfa7c00f3e8191ff58197626eeea4fbe7a9af1",
".modelhub_state/recent_outcomes.jsonl": "fc1723ffde828253ff4f9c4313e7d03c322b2061e7c4d9464305026a6b29c6d8",
".modelhub_state/recovery_active_tasks.jsonl": "6339ecffa2889cf03f81a591bae5925dae0dfefd93e64119052f678a823f67a7",
".modelhub_state/recovery_intents.jsonl": "c0f9acf8febb571a5365f7932ca203c5421664ce1f4336486d9a4f6a0f1c77f4",
".modelhub_state/routing_intelligence.json": "bec0a5fb9de2e9ca1df83acc2b9fb3f3f9de3e1fb692312f6e98735bb2821c13",
".modelhub_state/submission_exclusions.jsonl": "75ddc8b4d313a8cecec2f373afc57298143d78e0eb907ca44f420d7bf9c55263",
".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
"ledger/submissions.jsonl": "d2ddf3a16949582004e77b7e97294c06e8da2ccc28fbf89b8483e4a6143925de",
"outcomes/submissions.jsonl": "84b55e399c58fa914115eed056f62c2752c3e46c4c4823c7eb8bad9c86b35006"
},
"generation": 6801,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-13T16:14:45.329515+00:00",
"writerId": "69701e73196b4ac2b3fad0f412335168"
}

0
outcomes/.submissions.jsonl.lock Normal file
View File

640
outcomes/submissions.jsonl Normal file
View File

@@ -0,0 +1,640 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T11:58:24.844524+00:00", "modelId": "inclusionAI/Ling-3.0-tiny-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "efcec92f0f61cfcfef2bff75fcc3b460aac2425880772995e6373e3f88061c16", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8408187808, "estimatedRequiredGiB": 46.011, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 41170267110, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 41170267110}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T03:57:15.312611+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610785", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T11:58:24.844415+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11002488632, "estimatedRequiredGiB": 12.322, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 10176447713, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6340437856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:2-bit", "custom_tag:quantization", "custom_tag:escha", "custom_tag:sglang", "custom_tag:code", "custom_tag:reasoning", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "escha", "repositoryOnDiskBytes": 11025855102}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T03:57:15.116974+00:00", "targetGpu": "Biren_166m", "taskId": "4610786", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T11:58:24.844440+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T03:57:15.115591+00:00", "targetGpu": "Biren_166m", "taskId": "4610789", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T11:58:24.844516+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T03:57:15.111739+00:00", "targetGpu": "Biren_166m", "taskId": "4610788", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T11:58:24.844469+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T03:57:15.122454+00:00", "targetGpu": "Biren_166m", "taskId": "4610792", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T11:58:24.844463+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T03:57:15.186297+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610791", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T12:16:25.820685+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:13:33.449976+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4610987", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T12:16:25.820714+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:13:33.436802+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4610985", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T12:16:25.820707+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:13:33.448611+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4610986", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-04T12:19:49.890252+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:18:22.296309+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4611034", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-04T12:19:49.890224+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:18:22.294480+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4611032", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-04T12:19:49.890261+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:18:22.293258+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4611033", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:29:56.904005+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {"architectures": ["Param2MoEForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34302758832, "estimatedRequiredGiB": 38.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "param2moe", "modelscopeFileSize": 34317809830, "modelscopeLicense": null, "modelscopeParams": 17151125376, "modelscopeTags": ["model_type:param2moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:multilingual", "custom_tag:indian-languages"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 34317809830}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:29:16.672536+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611191", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:29:56.903997+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:29:16.656478+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611189", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:43:05.302336+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:34:21.517356+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611266", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:43:05.302344+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:34:21.520300+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611267", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:43:05.302380+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:34:21.518508+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611265", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T12:43:05.302313+00:00", "modelId": "b77968543/Spark-X2.5-4B-Q8_0", "modelProfile": {"architectures": [], "configFingerprint": "054a7592edf89d789e18b12765c567c3c34b2ebb58661fdd49255aad03c66d40", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 4.889, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4375025003, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "library:", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4375025003}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:40:16.372199+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611339", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-04T12:47:07.292457+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11002488632, "estimatedRequiredGiB": 12.322, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 10176447713, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6340437856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:safetensors", "task:text-generation", "custom_tag:qwen3", "custom_tag:2-bit", "custom_tag:quantization", "custom_tag:escha", "custom_tag:sglang", "custom_tag:code", "custom_tag:reasoning", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "escha", "repositoryOnDiskBytes": 11025855102}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:45:10.463600+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611409", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-04T12:47:07.292436+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:45:10.465869+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611408", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-04T13:02:07.810418+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:49:57.619810+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611460", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-04T13:02:07.810385+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:49:57.614004+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611462", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-04T13:02:07.810378+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:49:57.622876+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611461", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-04T13:02:07.810403+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:15"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:51:18.804860+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4611484", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-04T13:02:07.810313+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:15"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:51:18.803565+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4611482", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-04T13:02:07.810338+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:15"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:51:18.805964+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4611483", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T13:09:06.405170+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T05:06:37.162640+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611646", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T13:09:06.405177+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T05:06:37.165709+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611648", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T13:09:06.405152+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T05:06:37.161333+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611647", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T14:58:13.792120+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T06:55:47.742909+00:00", "targetGpu": "Biren_166m", "taskId": "4621594", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T14:58:13.792154+00:00", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31228126952, "estimatedRequiredGiB": 34.934, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 31258377392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:w8a8", "custom_tag:int8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 31258377392}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T06:55:47.759663+00:00", "targetGpu": "Biren_166m", "taskId": "4621595", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T15:07:35.511841+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:04:25.458550+00:00", "targetGpu": "Biren_166m", "taskId": "4621698", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T15:14:29.722109+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T15:43:37.898131+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:40:37.506061+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4622172", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T15:58:32.287733+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:56:50.952206+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4622417", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:14:29.511177+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:10:58.185038+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622623", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:14:29.511213+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:10:58.159820+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622624", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:14:29.511225+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:10:58.164553+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622621", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:14:29.511208+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:10:58.158458+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622619", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-04T16:14:29.511220+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:14:12.544960+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4622655", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:33:41.731498+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:33:06.846794+00:00", "targetGpu": "Biren_166m", "taskId": "4623002", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-04T16:50:26.817445+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:44:58.161709+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4623226", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T20:39:27.718139+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T12:34:49.403585+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4626360", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T21:36:16.816860+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22109595640, "estimatedRequiredGiB": 24.741, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22137550529, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 20921584848, "modelscopeTags": ["license:Apache License 2.0", "model_type:gpt_oss", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "mxfp4", "repositoryOnDiskBytes": 22137550529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T13:34:49.450482+00:00", "targetGpu": "MetaX_c-500", "taskId": "4627250", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T22:10:06.209357+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2023929984, "estimatedRequiredGiB": 2.272, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033083373, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033083377}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T14:08:46.692566+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4627849", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T22:53:17.234593+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T14:46:47.882785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4628625", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T23:04:36.601749+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:01:53.788146+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4628814", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T23:24:55.604371+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:17:04.545687+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4629090", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T23:24:55.604425+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:17:04.566515+00:00", "targetGpu": "Biren_166m", "taskId": "4629091", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T23:34:40.935412+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:32:11.647812+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4629294", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-04T23:34:40.935439+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:15"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22125413673, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:32:11.649244+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4629295", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-04T23:48:19.100125+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:15"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:47:16.843035+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4629532", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T23:51:52.413124+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T15:49:37.968504+00:00", "targetGpu": "Biren_166m", "taskId": "4629573", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T00:08:56.210086+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:05:38.973026+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4629768", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T00:12:22.613750+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 44221632439, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:10:19.951781+00:00", "targetGpu": "MetaX_c-500", "taskId": "4629851", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T00:12:22.613744+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:10:19.953932+00:00", "targetGpu": "MetaX_c-500", "taskId": "4629853", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T00:55:08.690919+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9536343971, "modelscopeLicense": null, "modelscopeParams": 2519020032, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9536343971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:45:54.339948+00:00", "targetGpu": "Biren_166m", "taskId": "4630659", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T00:55:08.690909+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:50:16.092995+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4630839", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T00:58:33.712526+00:00", "modelId": "nm-testing/tinyllama-marlin24-w4a16-group128", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 640856992, "estimatedRequiredGiB": 0.718, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 642705637, "modelscopeLicense": null, "modelscopeParams": 259844096, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 642705637}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T16:55:10.211615+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4630908", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T01:29:42.410346+00:00", "modelId": "pfnet/plamo-3-nict-8b-base", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16182734928, "estimatedRequiredGiB": 18.09, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 16186391993, "modelscopeLicense": "other", "modelscopeParams": 8091348992, "modelscopeTags": ["license:other", "model_type:plamo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16186391993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T17:27:00.623821+00:00", "targetGpu": "Biren_166m", "taskId": "4631345", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T02:08:42.512158+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28168623119, "estimatedRequiredGiB": 31.505, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 28190535646, "modelscopeLicense": null, "modelscopeParams": 7584230528, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 28190535646}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T18:06:53.125751+00:00", "targetGpu": "Biren_166m", "taskId": "4631858", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T02:32:00.692516+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020564058, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020564058}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T18:26:10.985611+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632116", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T02:32:00.692571+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T18:26:16.665549+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632117", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:05:43.096396+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998609696, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020499228, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020499228}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:03:47.678567+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632579", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:32:15.596901+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:29:42.987166+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632974", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T04:28:47.207692+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T20:26:01.012898+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4633732", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T04:35:49.427693+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22109595640, "estimatedRequiredGiB": 24.741, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22137550529, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 20921584848, "modelscopeTags": ["license:Apache License 2.0", "model_type:gpt_oss", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "mxfp4", "repositoryOnDiskBytes": 22137550529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T20:33:07.760826+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4633843", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T04:35:49.427716+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306305296, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19329225494, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329225494}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T20:34:23.419555+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4633876", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-05T04:45:59.433680+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:15"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T20:40:58.592221+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4633953", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T04:49:26.595714+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T20:48:49.542529+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4634053", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T05:30:50.210768+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T21:21:22.785475+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4634506", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T06:01:03.547559+00:00", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959216, "estimatedRequiredGiB": 18.783, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 8389956608, "modelscopeTags": ["model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:recommendation", "custom_tag:generative-recommendation", "custom_tag:reasoning", "custom_tag:itemic-token", "custom_tag:qwen3", "custom_tag:pretraining", "custom_tag:competition"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16806898419}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T22:00:58.451074+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4635038", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-05T06:47:43.600970+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "published_card_spec", "sourceUrl": "https://aclanthology.org/2025.emnlp-main.1630.pdf"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T22:37:50.462232+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4635609", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-05T07:14:11.020202+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:12:12.056590+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4636059", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T07:14:11.020212+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:12:18.663255+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4636060", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T07:14:11.020096+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5705684944, "estimatedRequiredGiB": 6.387, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5714910031, "modelscopeLicense": null, "modelscopeParams": 8031506432, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5714910031}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:12:29.786627+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4636099", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823946+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:29:59.915927+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636369", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823927+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:29:59.925332+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636370", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823920+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:29:59.918683+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636372", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823934+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:30:00.029529+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636376", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823906+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:30:00.025922+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636375", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T10:00:40.262694+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T02:00:39.877205+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4638914", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T10:00:40.262740+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T02:00:39.878542+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4638915", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T10:41:43.740753+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5700679600, "estimatedRequiredGiB": 6.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5709884743, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5709884743}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T02:38:10.748196+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4639409", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:40:37.707812+00:00", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8dbcfce641caa83ec7080451f0410ae2c4732d92c35c6ea116cea836d3424ea2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2076674432, "estimatedRequiredGiB": 11.564, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10347343046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1942653248, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "custom_tag:edge", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10347343046}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:38:07.789820+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641229", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:57:50.112723+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "7fcefcc66e6b781d939ce31d9aa1c7a89bdfb773b9556e6dcde4e21754b1189f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4610579744, "estimatedRequiredGiB": 25.463, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 22784105135, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4326350848, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22784105135}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:56:19.745119+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397755+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:01.097550+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641563", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397684+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:09.008584+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641565", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397729+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:09.000926+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641564", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:04:40.397749+00:00", "modelId": "LLM-Research/Phi-3.5-mini-instruct-bnb-4bit", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2264298476, "estimatedRequiredGiB": 2.533, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2266692143, "modelscopeLicense": "mit", "modelscopeParams": 3934684872, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:unsloth", "custom_tag:transformers", "custom_tag:phi3", "custom_tag:phi", "custom_tag:microsoft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "bitsandbytes", "repositoryOnDiskBytes": 2266692143}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:03:09.034612+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4641566", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142883+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9536343971, "modelscopeLicense": null, "modelscopeParams": 2519020032, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9536343971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.436989+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641789", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142867+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896238160, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898265436, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2948065280, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898265436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.486519+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641787", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142903+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.435240+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641790", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142876+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.439814+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641788", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142845+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21921675140, "estimatedRequiredGiB": 24.525, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 21944922993, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18589348592, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:vllm", "custom_tag:sm121", "custom_tag:gb10", "custom_tag:dgx-spark", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:modelopt"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21944922993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.438354+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641791", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:20:02.142890+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:17:16.497948+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641785", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T13:26:54.507078+00:00", "modelId": "ornith-ai/Ornith-1.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306303864, "estimatedRequiredGiB": 21.604, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19331003204, "modelscopeLicense": "mit", "modelscopeParams": 9653104368, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19331003204}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T05:25:57.272773+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4641967", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T14:47:47.007002+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T06:44:06.184901+00:00", "targetGpu": "MetaX_c-500", "taskId": "4643007", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T14:51:17.315130+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T06:48:32.413847+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643045", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T14:51:17.315106+00:00", "modelId": "amd/gpt-oss-20b-BF16-w8a8-llmcompressor", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 44193251544, "estimatedRequiredGiB": 49.422, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 44221632439, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20914757184, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:int8", "custom_tag:w8a8", "custom_tag:dynamic-quantization", "custom_tag:8-bit", "custom_tag:llm-compressor", "custom_tag:compressed-tensors", "custom_tag:zendnn", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 44221632439}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T06:48:32.398253+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643046", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T14:51:17.315136+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T06:48:32.415250+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643042", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T14:51:17.315051+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T06:48:32.400153+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643043", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T14:51:17.315115+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T06:48:32.405323+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643048", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T14:51:17.315123+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T06:48:32.410291+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4643049", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T17:06:08.800571+00:00", "modelId": "LiquidAI/LFM2.5-230M-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c331f3d8906467b7947cec00daebfec4ccad1f351223a1eced4dea452a1012df", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 149080928, "estimatedRequiredGiB": 2.218, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1984559598, "modelscopeLicense": "other", "modelscopeParams": 229693184, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:gguf", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1984559598}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:04:21.884770+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4645136", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T17:46:46.041785+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20041566112, "estimatedRequiredGiB": 22.408, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 20050750527, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "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}, "repositoryOnDiskBytes": 20050750527}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:38:43.506267+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645748", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T17:46:46.041763+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:43:33.758884+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4645816", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T18:34:58.235126+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T10:33:51.484756+00:00", "targetGpu": "MetaX_c-500", "taskId": "4646505", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T20:12:28.913845+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e023b149992af42872de3c0c0c07dafd6a98d965e5bdb5a29ec5869e58d45725", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.084154+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4648146", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T20:12:28.913926+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 31280205657, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 30554505408, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_moe", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31280205657}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T12:03:37.105603+00:00", "targetGpu": "MetaX_c-500", "taskId": "4648141", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T21:15:28.523439+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0dce7c4be445254429760db90c7969177ecdca460563778d8b3371a37cc1a50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.099409+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4649238", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523328+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.114152+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649233", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523422+00:00", "modelId": "douyamv/Qwen3.8-27B-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28178526992, "estimatedRequiredGiB": 31.518, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 28201576294, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:vllm", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 28201576294}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.110104+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649235", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523453+00:00", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119861184, "estimatedRequiredGiB": 29.243, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26165778261, "modelscopeLicense": "mit", "modelscopeParams": 35951822704, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26165778261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:23.184952+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649236", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523413+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385168, "estimatedRequiredGiB": 13.339, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11935116462, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11935116462}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:29.375921+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649241", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523404+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:29.655509+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649242", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523320+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20034587064, "estimatedRequiredGiB": 22.413, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20054851725, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:qwen3.5-architecture", "custom_tag:gptq-pro", "custom_tag:gptq", "custom_tag:4-bit", "custom_tag:4bit", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:text-generation", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 20054851725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:29.696899+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649243", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523467+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:07:29.759253+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649244", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:15:28.523345+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9536343971, "modelscopeLicense": null, "modelscopeParams": 2519020032, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9536343971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:15:06.885148+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649368", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:24:35.912104+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:15:06.887234+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649370", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:42:08.215425+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14399972864, "estimatedRequiredGiB": 16.095, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 14402000339, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7199932416, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14402000339}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:36:05.794989+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649667", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T21:42:08.215400+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "49c09622b187326c7d52c77c501ea1ed17ae85611b418c974c6d1dd95d2ec84c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:40:05.806797+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4649761", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:42:08.215443+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26540803088, "estimatedRequiredGiB": 29.664, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 26542898184, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13270298624, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26542898184}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:40:05.816872+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649762", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T21:50:41.400421+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28168623119, "estimatedRequiredGiB": 31.505, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 28190535646, "modelscopeLicense": null, "modelscopeParams": 7584230528, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 28190535646}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:43:45.755060+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4649829", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T22:00:13.693262+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21921675140, "estimatedRequiredGiB": 24.525, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 21944922993, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18589348592, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:vllm", "custom_tag:sm121", "custom_tag:gb10", "custom_tag:dgx-spark", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:modelopt"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21944922993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:52:09.758631+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650028", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T22:00:13.693287+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T13:55:22.931577+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650076", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T22:35:47.104165+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "99fcfb5673a881c74d82451063f2e7a90a328c33bce1e63a9d0bf3ccffd99170", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:30:50.543106+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650543", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T22:35:47.104188+00:00", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19452784112, "estimatedRequiredGiB": 21.763, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19472982631, "modelscopeLicense": "openrail", "modelscopeParams": 27356728560, "modelscopeTags": ["license:openrail", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19472982631}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:35:18.733791+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650604", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T22:44:15.950234+00:00", "modelId": "LiquidAI/LFM2.5-8B-A1B-DSpark-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "05c5a771e8ede0f61c61c1696314e8cb295d87d07704eedc68e43f7483931e45", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 356491104, "estimatedRequiredGiB": 1.363, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1219879026, "modelscopeLicense": "other", "modelscopeParams": 327707521, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:speculative-decoding", "custom_tag:dspark", "custom_tag:lfm2", "custom_tag:draft-model", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1219879026}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T14:39:36.525018+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4650654", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T23:08:33.934658+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T15:03:56.182791+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4650921", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:23:33.113639+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:20:38.385517+00:00", "targetGpu": "Vastai_va16", "taskId": "4651796", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:23:33.113688+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:20:38.391817+00:00", "targetGpu": "Vastai_va16", "taskId": "4651794", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:23:33.113630+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:20:38.389388+00:00", "targetGpu": "Vastai_va16", "taskId": "4651792", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:23:33.113651+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:20:43.653329+00:00", "targetGpu": "Vastai_va16", "taskId": "4651782", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:23:33.113645+00:00", "modelId": "solidrust/Llama-3-13B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8447876488, "estimatedRequiredGiB": 9.452, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 8457284244, "modelscopeLicense": "other", "modelscopeParams": 13264949248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 8457284244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:20:43.655577+00:00", "targetGpu": "Vastai_va16", "taskId": "4651783", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T00:33:16.913577+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T16:30:08.472711+00:00", "targetGpu": "Vastai_va16", "taskId": "4651931", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503349+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663867, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663867}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.387500+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657894", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503426+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084014480, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093198689, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093198689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.389266+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657903", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503337+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081293776, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504091, "modelscopeLicense": "llama3", "modelscopeParams": 8030261312, "modelscopeTags": ["license:llama3", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9090504091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.396277+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657902", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503433+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 39365175520, "estimatedRequiredGiB": 44.029, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 39396646235, "modelscopeLicense": "mit", "modelscopeParams": 35951822704, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 39396646235}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.385964+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657900", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503369+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.392602+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657901", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503449+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788612468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.390810+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657904", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503472+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19509024201, "estimatedRequiredGiB": 21.828, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19530936726, "modelscopeLicense": null, "modelscopeParams": 5419330688, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19530936726}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.419799+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657897", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503494+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 31280205657, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 30554505408, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_moe", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31280205657}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.417747+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657896", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503479+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-8bit", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 451270785, "estimatedRequiredGiB": 0.534, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 478002291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 119465472, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 478002291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.487200+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657899", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503442+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp8", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 437998912, "estimatedRequiredGiB": 0.519, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 464729926, "modelscopeLicense": "apache-2.0", "modelscopeParams": 119465472, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:mxfp8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 464729926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:35.426741+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657898", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503409+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.351789+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657907", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503418+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293335560, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295942065, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295942065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.393987+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657908", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503487+00:00", "modelId": "RedHatAI/gemma-2-2b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4385544296, "estimatedRequiredGiB": 4.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 4407367933, "modelscopeLicense": "gemma", "modelscopeParams": 3204165888, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4407367933}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.391226+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657911", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503463+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020563851, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 12020563851}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.392742+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657912", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503359+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 36828222561, "estimatedRequiredGiB": 41.183, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 36850135087, "modelscopeLicense": null, "modelscopeParams": 9749130368, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36850135087}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.349157+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657906", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503379+00:00", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119861184, "estimatedRequiredGiB": 29.243, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26165778261, "modelscopeLicense": "mit", "modelscopeParams": 35951822704, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26165778261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.350638+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657905", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T08:35:17.503389+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 238933307, "estimatedRequiredGiB": 0.297, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 265664321, "modelscopeLicense": "apache-2.0", "modelscopeParams": 106194432, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:nvfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 265664321}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:30:40.388241+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4657909", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T08:54:40.814445+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896238160, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898265436, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2948065280, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898265436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T00:51:47.515580+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4658219", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T10:30:17.601493+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385168, "estimatedRequiredGiB": 13.339, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11935116462, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11935116462}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T02:23:39.684428+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659269", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T10:30:17.601408+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703969742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703969742}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T02:23:39.690219+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659268", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T10:30:17.601473+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21921675140, "estimatedRequiredGiB": 24.525, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 21944922993, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18589348592, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:vllm", "custom_tag:sm121", "custom_tag:gb10", "custom_tag:dgx-spark", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:modelopt"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21944922993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T02:24:31.818066+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659299", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T10:38:48.141866+00:00", "modelId": "callmezcc/Qwen3.8-27B-GPTQ-W4A16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19452784112, "estimatedRequiredGiB": 21.763, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19472982631, "modelscopeLicense": "openrail", "modelscopeParams": 27356728560, "modelscopeTags": ["license:openrail", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19472982631}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T02:33:58.284464+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4659388", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T11:46:43.318197+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26540803088, "estimatedRequiredGiB": 29.664, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 26542898184, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13270298624, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26542898184}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T03:45:55.331628+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660328", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T11:53:42.913364+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9536343971, "modelscopeLicense": null, "modelscopeParams": 2519020032, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9536343971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T03:52:18.510578+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660434", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T12:21:22.998937+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T04:17:45.285806+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660827", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T12:39:38.309054+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20034587064, "estimatedRequiredGiB": 22.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20054851725, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:qwen3.5-architecture", "custom_tag:gptq-pro", "custom_tag:gptq", "custom_tag:4-bit", "custom_tag:4bit", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:text-generation", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 20054851725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T04:38:16.005175+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4661079", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T13:08:06.614723+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T05:06:36.493823+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661437", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-06T14:42:01.034713+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "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": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T06:30:19.979390+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4662535", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-06T15:03:37.399221+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T07:02:35.712857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4662918", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-06T15:18:32.207677+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "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": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T07:17:44.185498+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4663094", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T15:39:34.751776+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26540803088, "estimatedRequiredGiB": 29.664, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 26542898184, "modelscopeLicense": "apache-2.0", "modelscopeParams": 13270298624, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26542898184}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T07:35:56.293000+00:00", "targetGpu": "MetaX_c-500", "taskId": "4663310", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T16:00:10.996019+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T07:56:28.496520+00:00", "targetGpu": "MetaX_c-500", "taskId": "4663539", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-06T16:14:21.709544+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T08:12:14.777960+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4663715", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-06T16:36:18.900122+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T08:34:09.456899+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4664143", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-06T17:08:48.403518+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T09:06:12.932838+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4664478", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T17:15:41.925546+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T09:13:43.657662+00:00", "targetGpu": "MetaX_c-500", "taskId": "4664576", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T17:46:47.144783+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T09:46:33.145376+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4664976", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T18:28:08.305021+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14399972864, "estimatedRequiredGiB": 16.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 14402000339, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7199932416, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14402000339}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T10:24:50.148662+00:00", "targetGpu": "MetaX_c-500", "taskId": "4665474", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T18:28:08.305046+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T10:24:50.144356+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4665470", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T20:39:29.797774+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T12:37:22.515030+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4667091", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613082+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679222028, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679222028}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T13:58:59.194804+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667926", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613054+00:00", "modelId": "neuralmagic/Meta-Llama-3.1-70B-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72656575880, "estimatedRequiredGiB": 81.21, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72665883326, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72665883326}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T13:58:59.550329+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4667927", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:04:22.613090+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "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": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:01:57.388649+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668028", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:33:26.815214+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22109595640, "estimatedRequiredGiB": 24.741, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 22137550529, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 20921584848, "modelscopeTags": ["license:Apache License 2.0", "model_type:gpt_oss", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "mxfp4", "repositoryOnDiskBytes": 22137550529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:32:32.785339+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668538", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:43:37.806846+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679220993, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679220993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:33:50.986624+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668642", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:14:15.399910+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:05:58.785747+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669358", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T23:14:15.399880+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385168, "estimatedRequiredGiB": 13.339, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11935116462, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11935116462}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T15:07:54.384483+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4669411", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T00:59:44.608188+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14399972864, "estimatedRequiredGiB": 16.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 14402000339, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7199932416, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14402000339}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T16:48:59.678173+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4672290", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T02:37:59.437424+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055418240, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057371034, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1527668736, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3057371034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T18:34:36.628828+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4674757", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T03:57:59.407871+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T19:48:32.773868+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4676609", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T03:57:59.407808+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28168623119, "estimatedRequiredGiB": 31.505, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 28190535646, "modelscopeLicense": null, "modelscopeParams": 7584230528, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 28190535646}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T19:48:32.797983+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4676625", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T04:34:12.697055+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T20:23:42.610808+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4677309", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:05:30.903841+00:00", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959216, "estimatedRequiredGiB": 18.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 8389956608, "modelscopeTags": ["model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:recommendation", "custom_tag:generative-recommendation", "custom_tag:reasoning", "custom_tag:itemic-token", "custom_tag:qwen3", "custom_tag:pretraining", "custom_tag:competition"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16806898419}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T20:54:07.883252+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4677960", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:18:43.228856+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:08:47.388697+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678359", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:18:43.228798+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:08:47.402496+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678379", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:18:43.228865+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:15:16.244457+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678529", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:31:35.012291+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:25:37.107095+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678756", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:31:35.012329+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:25:37.111002+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678760", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:45:22.903446+00:00", "modelId": "nota-ai/Nemotron-3.5-Lightning-30B-A3B-NVFP4-Global-Pruned-15", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18974813860, "estimatedRequiredGiB": 21.229, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 18995666906, "modelscopeLicense": "other", "modelscopeParams": 15524066944, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18995666906}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:38:26.181785+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679070", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T06:07:37.711983+00:00", "modelId": "groxaxo/qwen36-reap-2k-mlx-q8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21551054131, "estimatedRequiredGiB": 24.108, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21571271615, "modelscopeLicense": "other", "modelscopeParams": 6393958256, "modelscopeTags": ["license:other", "model_type:qwen3_5_moe", "library:mlx", "library:lora", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen3", "custom_tag:multimodal", "custom_tag:vision", "custom_tag:lora", "custom_tag:merged", "custom_tag:q8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21571271615}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:46:28.939188+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679344", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T06:07:37.712071+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-4B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.438, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9339955920, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:math", "custom_tag:stem", "custom_tag:mtp", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9339955920}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:55:23.563817+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4679536", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-07T06:07:37.712055+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "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": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T22:04:12.078346+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4679732", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-07T06:07:37.712005+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "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": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T22:04:12.072657+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4679733", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T17:31:43.302628+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9fba363aef42aed2b52f3be34868ab5830a7c956f45e65fceed6561122eb8743", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8229925227, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T09:29:07.790789+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4691709", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T18:00:51.826326+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8bb72add25c6bbefdaaa3d4fc9d420176b02cfa13433975a607b2e5a23d944d6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8229925227, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T09:53:15.317620+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4692145", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T18:18:26.905231+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c8002a19ceb3b3bde544f5a0cc84985eeda610b7a8666758689c1b5d9da4f882", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8229925227, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T10:17:32.532423+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4692612", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T18:43:35.404773+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "b305ed8a329c4e69e3f159bd931bac369985a92f65070a7d6771814b8bc7d7b4", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 12604946379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T10:34:41.435624+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4693000", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T19:09:44.610099+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "054a7592edf89d789e18b12765c567c3c34b2ebb58661fdd49255aad03c66d40", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 12604946379, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T10:57:50.465064+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4693286", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T20:17:14.292443+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "cf08bd790fcd1d2576f2e93c74fd48ff973459e147ef9d96bb7575547785cb72", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3420936797, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T12:14:20.888757+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4694739", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T20:52:41.332115+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "5b544f6f344d670dc906febb49993caf4b7d39b21860557b2416591a1a8c41bf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3420936797, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T12:42:26.505824+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4695129", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-07T20:52:41.332086+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T12:42:26.513703+00:00", "targetGpu": "Vastai_va16", "taskId": "4695130", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T20:52:41.332095+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "5f7f0613db77a9df3302ec352997953a9eba59a0aa6b38bb4fbb9466fb50fd7b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T12:50:14.422978+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4695252", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T21:18:24.608680+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "ea2321217291fd0be7b6ccbad7b7c81bf62a9ac5c888c7ee1e080e1ea85862ae", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T13:14:08.050211+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4695580", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-07T22:23:41.399386+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T14:21:55.293071+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4697078", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-07T22:50:29.406678+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T14:48:02.492557+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4697753", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-07T23:16:42.601405+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T15:08:53.697776+00:00", "targetGpu": "Vastai_va16", "taskId": "4698268", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T23:43:05.101242+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T15:35:43.483187+00:00", "targetGpu": "MetaX_c-500", "taskId": "4698954", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-08T00:02:57.396828+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T16:01:34.238434+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4699472", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T00:12:24.015192+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T16:06:40.552870+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4699585", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T00:32:26.904342+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T16:31:45.492609+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4700151", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T01:37:35.725250+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0e96112008e09ac1841408e47a35f72b68023fca4efc76695e6eb96ba540ba1c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T17:27:44.564043+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4701029", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-08T01:37:35.725230+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T17:27:44.568075+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4701030", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T04:10:28.996444+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:50"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T19:56:19.088834+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4703149", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T09:05:31.097982+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "cfe08978e062dae728d260488110f70f7f12953c8f377a0f9c0a93bc3f6b0862", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.371, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280253884, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280253884}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T00:43:38.323540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4707395", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T09:05:31.097932+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "78f026e44886f960cbcecb5cfbfc4b0b2239d86ba4b225a73df72965f73e0ed2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.371, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280253884, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280253884}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T00:49:03.895304+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4707512", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T09:34:21.991798+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "e2a7b7c51552e96dae7e97291f0664b9c7fbde7d5b1322eb96e684dc410a4ec3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.371, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280253884, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280253884}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T01:08:15.662956+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4707808", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T09:34:21.991771+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "47b99bf102c8c855259a4427d2ee4726c9c38833b231e86c64e74198958fa242", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.371, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280253884, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280253884}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T01:27:22.581440+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4708072", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T11:18:26.601925+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T02:54:25.526666+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4709522", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T11:18:26.601986+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T03:16:59.351441+00:00", "targetGpu": "Vastai_va16", "taskId": "4709818", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-08T11:42:26.289394+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T03:37:14.233789+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4710114", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T12:11:42.795256+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T03:58:12.682940+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4710401", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-08T12:42:19.103199+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T04:20:35.203447+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4710796", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T13:16:14.206207+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T05:08:32.946681+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4711416", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614464+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:06.785300+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712808", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614275+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:06.799047+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712803", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614292+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:11.590454+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712813", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614454+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:11.606547+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712821", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614444+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:11.792714+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712824", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614239+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:11.811424+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712831", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903556+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:16.493472+00:00", "targetGpu": "Biren_166m", "taskId": "4713227", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903633+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "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": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:16.486536+00:00", "targetGpu": "Biren_166m", "taskId": "4713230", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903644+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "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": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:16.487544+00:00", "targetGpu": "Biren_166m", "taskId": "4713228", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903577+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11910385168, "estimatedRequiredGiB": 13.339, "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": 11935116462, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11935116462}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:16.512621+00:00", "targetGpu": "Biren_166m", "taskId": "4713225", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903614+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "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": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:16.515462+00:00", "targetGpu": "Biren_166m", "taskId": "4713229", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903607+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20034587064, "estimatedRequiredGiB": 22.413, "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": 20054851725, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:qwen3.5-architecture", "custom_tag:gptq-pro", "custom_tag:gptq", "custom_tag:4-bit", "custom_tag:4bit", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:text-generation", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 20054851725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:16.585542+00:00", "targetGpu": "Biren_166m", "taskId": "4713226", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903599+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21921675140, "estimatedRequiredGiB": 24.525, "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": 21944922993, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18589348592, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:vllm", "custom_tag:sm121", "custom_tag:gb10", "custom_tag:dgx-spark", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:modelopt"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21944922993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:16.516825+00:00", "targetGpu": "Biren_166m", "taskId": "4713224", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903621+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "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": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:24.345690+00:00", "targetGpu": "Biren_166m", "taskId": "4713233", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903627+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:24.160342+00:00", "targetGpu": "Biren_166m", "taskId": "4713232", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T15:18:01.903639+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:15:24.169874+00:00", "targetGpu": "Biren_166m", "taskId": "4713231", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T15:30:55.706707+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T07:30:11.995863+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4713445", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T17:15:48.506915+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426226990, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T09:15:31.168687+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4715997", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T17:52:18.933025+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T09:42:38.119885+00:00", "targetGpu": "Vastai_va16", "taskId": "4716367", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T17:52:18.933043+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T09:50:25.159456+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4716485", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T18:22:22.226463+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "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": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T10:18:12.673769+00:00", "targetGpu": "Biren_166m", "taskId": "4716910", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T18:32:01.542042+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "c03adae4b35c577b219efa214a72e6ba0eee2287660172b6efc70ec1f7b26139", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.372, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280496017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280496017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T10:26:22.306973+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4717031", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T18:32:01.542105+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5044047987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5044047987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T10:26:22.313092+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4717029", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T18:32:01.542064+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "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": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T10:26:22.308491+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4717030", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-08T19:02:28.697202+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T10:53:08.602969+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4717458", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T20:16:09.104286+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T12:11:32.114244+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4718632", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T20:25:19.301759+00:00", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c0a22d315ebe878ba44106414a577af03c793aca1443a9ac1292a8dddeb30f64", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1908528192, "estimatedRequiredGiB": 5.052, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4520619452, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1791080448, "modelscopeTags": ["license:apache-2.0", "library:pytorch", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4520619479}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T12:23:10.100285+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4718771", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T20:25:19.301793+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "cfe08978e062dae728d260488110f70f7f12953c8f377a0f9c0a93bc3f6b0862", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T12:23:10.091322+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4718772", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T20:58:55.412646+00:00", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0f182c60e08246cffa89958d8d6a49257753ec0079779607a24d3f4762f95536", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1908528192, "estimatedRequiredGiB": 5.052, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4520619452, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1791080448, "modelscopeTags": ["license:apache-2.0", "library:pytorch", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4520619479}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T12:52:27.905778+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4719218", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T20:58:55.412627+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "78f026e44886f960cbcecb5cfbfc4b0b2239d86ba4b225a73df72965f73e0ed2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T12:52:27.907475+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4719219", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-08T21:08:14.021122+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426469123, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426469123}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T13:04:27.346213+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4719399", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T21:18:07.599908+00:00", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9294c48825334146131a77fed6083f3e1a641f9feb25fb7c3cab049e21d5f81e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1908528192, "estimatedRequiredGiB": 5.052, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4520619452, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1791080448, "modelscopeTags": ["license:apache-2.0", "library:pytorch", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4520619479}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T13:16:04.810496+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4719506", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T21:18:07.599874+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c03adae4b35c577b219efa214a72e6ba0eee2287660172b6efc70ec1f7b26139", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T13:16:04.812757+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4719505", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T21:51:48.716975+00:00", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "781818a9e50a17094d0f92de6e822f23f13d475b94f3e496485b51719b9fea9c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1908528192, "estimatedRequiredGiB": 5.052, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4520619452, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1791080448, "modelscopeTags": ["license:apache-2.0", "library:pytorch", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4520619479}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T13:51:12.910659+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4720103", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T21:51:48.716995+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "e2a7b7c51552e96dae7e97291f0664b9c7fbde7d5b1322eb96e684dc410a4ec3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T13:51:12.945092+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4720102", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T22:32:41.015054+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.026055+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720562", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T22:32:41.015061+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.085348+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720559", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T22:32:41.015030+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.024677+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720556", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T22:32:41.015116+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.026999+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720558", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T22:32:41.015067+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.089405+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720561", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T22:32:41.015103+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.027925+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720557", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T22:32:41.015123+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.092238+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720555", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T22:32:41.015110+00:00", "modelId": "Tencent-Hunyuan/Hy-MT2-1.8B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "abb02b8a1726c2017f3e58267b0dcef5c53ad69497de685319b66fb05de32644", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1908528192, "estimatedRequiredGiB": 5.052, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4520619479, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1791080448, "modelscopeTags": ["license:apache-2.0", "library:pytorch", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4520619479}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.086935+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4720553", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T22:32:41.015128+00:00", "modelId": "Abiray/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "47b99bf102c8c855259a4427d2ee4726c9c38833b231e86c64e74198958fa242", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679712768, "estimatedRequiredGiB": 12.192, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10909231864, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10909231864}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:28:33.090401+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4720554", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-08T22:40:59.024520+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:39:15.996200+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4720681", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T23:04:25.910485+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:58:24.213075+00:00", "targetGpu": "Vastai_va16", "taskId": "4720983", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T23:04:25.910504+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:58:24.210777+00:00", "targetGpu": "Vastai_va16", "taskId": "4720979", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T23:04:25.910497+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:58:24.208286+00:00", "targetGpu": "Vastai_va16", "taskId": "4720984", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T23:04:25.910491+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:58:24.214242+00:00", "targetGpu": "Vastai_va16", "taskId": "4720985", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T23:04:25.910479+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:58:24.215700+00:00", "targetGpu": "Vastai_va16", "taskId": "4720981", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T23:04:25.910451+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:58:24.218435+00:00", "targetGpu": "Vastai_va16", "taskId": "4720980", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T23:04:25.910471+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T14:58:24.217400+00:00", "targetGpu": "Vastai_va16", "taskId": "4720982", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T23:08:02.743261+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:05:13.551982+00:00", "targetGpu": "Vastai_va16", "taskId": "4721081", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T23:25:13.221382+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:22:51.992361+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721413", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T23:25:13.221377+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:22:51.991246+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721411", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T23:25:13.221352+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:22:51.987097+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721409", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T23:25:13.221367+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:22:51.988362+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721412", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T23:25:13.221360+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:22:51.993706+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721414", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T23:25:13.221372+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:22:51.989914+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721415", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T23:25:13.221332+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:22:51.985451+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721410", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T23:28:43.421477+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:26:26.996071+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4721484", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T23:42:27.831509+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:41:22.303733+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721841", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T23:42:27.831433+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:41:22.305654+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721844", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T23:42:27.831362+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:41:22.307631+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721840", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T23:42:27.831418+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:41:22.309020+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721846", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T23:42:27.831482+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:41:22.315855+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721842", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T23:42:27.831403+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:41:22.314461+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721845", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T23:42:27.831453+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:41:22.317110+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721843", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T23:45:55.808667+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:43:53.869220+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4721908", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T23:59:40.403440+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608338785, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:58:20.173410+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4722285", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-08T23:59:40.403491+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:58:20.177612+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722290", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-08T23:59:40.403507+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:58:20.180877+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722289", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-08T23:59:40.403431+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:58:20.184579+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722291", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-08T23:59:40.403500+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:58:20.179374+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722292", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-08T23:59:40.403421+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:58:20.186731+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722286", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-08T23:59:40.403397+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:58:20.188689+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722287", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-08T23:59:40.403483+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T15:58:20.189892+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722288", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-09T00:03:07.803208+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:02:47.947809+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4722381", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T00:10:07.197495+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426230291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426230291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:07:42.647348+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722474", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T00:15:57.396004+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:15:24.569436+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722682", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T00:15:57.395998+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:15:24.567153+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722680", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T00:15:57.395984+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:15:24.576021+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722678", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T00:15:57.395935+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:15:24.571340+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722675", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T00:15:57.395976+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:15:24.574077+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722679", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T00:15:57.395961+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:15:24.572715+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722676", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T00:15:57.395990+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:15:24.583828+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722677", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T00:15:57.395969+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608338785, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:15:24.585768+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4722681", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T00:22:49.105696+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:20:22.756130+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4722805", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T00:29:40.902076+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:28:42.318975+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4722998", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T00:29:40.902066+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:28:42.314056+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4722996", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T00:29:40.902045+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:28:42.308404+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4722999", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T00:29:40.902084+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:28:42.305740+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4722997", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T00:29:40.902092+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:28:42.321758+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4723003", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T00:29:40.902114+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:28:42.307265+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4723000", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T00:29:40.902100+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:28:42.324067+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4723001", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T00:29:40.902122+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T16:28:42.320180+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4723002", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499797+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.090028+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725841", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499713+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.091884+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725848", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499785+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.019663+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725846", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499765+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.016617+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725850", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499745+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.023701+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725842", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499759+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.085412+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725845", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499736+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.095472+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725851", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499791+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.088412+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725847", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499753+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463495, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463495}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.094485+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725844", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499771+00:00", "modelId": "JANGQ-AI/Osaurus-AppleScript-8B-JANG_6M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463197, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463197}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.086665+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725843", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499802+00:00", "modelId": "JANGQ-AI/AppleScript-8B-JANG_4M", "modelProfile": {"architectures": ["ZayaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7915599888, "estimatedRequiredGiB": 8.885, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "zaya", "modelscopeFileSize": 7950463599, "modelscopeLicense": "other", "modelscopeParams": 2274126328, "modelscopeTags": ["license:other", "model_type:zaya", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:applescript", "custom_tag:macos", "custom_tag:computer-use", "custom_tag:agent", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:mlx", "custom_tag:moe", "custom_tag:osaurus"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7950463599}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.090923+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725849", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T02:50:57.499779+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T18:47:44.093470+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4725852", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-09T03:24:59.424997+00:00", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "810417097cbc089138743623f5b2d9e7e0819ca3b5e09a46ae05ee92ae0998ba", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1490357184, "estimatedRequiredGiB": 43.21, "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": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:llama-cpp", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38663413453}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T19:24:44.852247+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4726325", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-09T03:46:44.543748+00:00", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0c20bbf40c5417bddba738862516ad2bc8c9ec5013c0fd3e0fa9220f64035056", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1490357184, "estimatedRequiredGiB": 43.21, "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": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:llama-cpp", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38663413453}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T19:44:39.694828+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4726617", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-09T05:15:37.097517+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794148, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794148}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T21:14:03.823550+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4727746", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T05:32:40.605323+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794148, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794148}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T21:29:34.930719+00:00", "targetGpu": "Vastai_va16", "taskId": "4727973", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-09T05:49:44.122625+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "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": 8435794148, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794148}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T21:48:30.702694+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4728207", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:06:56.823871+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794148, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794148}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:05:28.693168+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4728506", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T06:23:50.502374+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "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": 8435794148, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794148}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:23:01.734631+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4728907", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-09T06:27:15.307637+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794148, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794148}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:24:50.419230+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4728926", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:43:52.702366+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794148, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794148}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:42:29.518873+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4729173", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:50:35.321521+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:49:56.922360+00:00", "targetGpu": "Biren_166m", "taskId": "4729267", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:50:35.321462+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:49:56.908214+00:00", "targetGpu": "Biren_166m", "taskId": "4729269", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:50:35.321507+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:49:56.920583+00:00", "targetGpu": "Biren_166m", "taskId": "4729268", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:50:35.321481+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:49:56.910926+00:00", "targetGpu": "Biren_166m", "taskId": "4729272", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:50:35.321489+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:49:56.914465+00:00", "targetGpu": "Biren_166m", "taskId": "4729271", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:50:35.321501+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:49:56.911982+00:00", "targetGpu": "Biren_166m", "taskId": "4729270", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:50:35.321495+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:49:56.913066+00:00", "targetGpu": "Biren_166m", "taskId": "4729273", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:50:35.321517+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:49:56.923972+00:00", "targetGpu": "Biren_166m", "taskId": "4729274", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T06:50:35.321512+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "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": 8435794148, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794148}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T22:49:56.925801+00:00", "targetGpu": "Biren_166m", "taskId": "4729275", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504572+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043809154, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043809154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:45.687861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729507", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504658+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "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": "2026-09-07T05:31:35.012313+00:00", "modelType": "qwen3", "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": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:45.664222+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729503", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504520+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "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": "2026-09-07T05:31:35.012313+00:00", "modelType": "qwen3", "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": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:45.690523+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729502", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504454+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "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": "2026-09-07T05:31:35.012313+00:00", "modelType": "qwen3", "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": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:45.686402+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729506", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504504+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "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": "2026-09-07T05:31:35.012313+00:00", "modelType": "qwen3", "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": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:45.691566+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729498", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504473+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "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": "2026-09-07T05:31:35.012313+00:00", "modelType": "qwen3", "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": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:45.689318+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729505", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504488+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "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": "2026-09-07T05:31:35.012313+00:00", "modelType": "qwen3", "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": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:45.694196+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729499", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504590+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "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": "2026-09-07T05:31:35.012313+00:00", "modelType": "qwen3", "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": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:45.696067+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729497", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504637+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "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": "2026-09-07T05:31:35.012313+00:00", "modelType": "qwen3", "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": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:45.702007+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729500", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504652+00:00", "modelId": "siliconflow/Qwen3-Coder-30B-A3B-Instruct-fp8", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31263441624, "estimatedRequiredGiB": 34.958, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 31280205657, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 30554505408, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_moe", "library:safetensors", "library:other", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 31280205657}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.785155+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729509", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504496+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.831733+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729515", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504528+00:00", "modelId": "siliconflow/Hunyuan-A13B-Instruct-SF-FP8", "modelProfile": {"architectures": ["HunYuanMoEV1ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1700, "estimatedRequiredGiB": 90.469, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hunyuan", "modelscopeFileSize": 80949912827, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 80393195968, "modelscopeTags": ["license:Apache License 2.0", "model_type:hunyuan", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 80949912827}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.924564+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729534", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504434+00:00", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119861184, "estimatedRequiredGiB": 29.243, "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": 26165778261, "modelscopeLicense": "mit", "modelscopeParams": 35951822704, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26165778261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.933574+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729525", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504558+00:00", "modelId": "empero-ai/Qwen3.8-9B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306305296, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19329225494, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19329225494}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:51.939534+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729523", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504596+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426230291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426230291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.094406+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729529", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504631+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.086476+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729527", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504642+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14399972864, "estimatedRequiredGiB": 16.095, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 14402000339, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7199932416, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 14402000339}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.096464+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729531", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504584+00:00", "modelId": "dealignai/MiniMax-M2.7-JANGTQ-CRACK", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60691028969, "estimatedRequiredGiB": 67.863, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60722546540, "modelscopeLicense": null, "modelscopeParams": 15303654400, "modelscopeTags": ["model_type:minimax_m2", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:turboquant", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:apple-silicon", "custom_tag:mlx", "custom_tag:moe", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:crack", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60722546540}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.031559+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729530", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504536+00:00", "modelId": "mlx-community/Hy3-OptiQ-2bit", "modelProfile": {"architectures": ["HYV3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 88126421229, "estimatedRequiredGiB": 98.5, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hy_v3", "modelscopeFileSize": 88136486889, "modelscopeLicense": "apache-2.0", "modelscopeParams": 24386771776, "modelscopeTags": ["license:apache-2.0", "model_type:hy_v3", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:2bit", "custom_tag:mixed-precision", "custom_tag:moe", "custom_tag:ssd-streaming", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 88136486889}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.159484+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729532", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504481+00:00", "modelId": "hf/OBLITERATUS-Ornith-1.5-9B-OBLITERATED", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306303864, "estimatedRequiredGiB": 92.13, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 82436368524, "modelscopeLicense": "mit", "modelscopeParams": 9653104368, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:gguf", "library:safetensors", "task:text-generation", "custom_tag:abliterated", "custom_tag:uncensored", "custom_tag:ornith", "custom_tag:qwen3.5", "custom_tag:obliteratus", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 82436368524}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.350274+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729535", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504578+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.386802+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729533", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504608+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANG_K", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 85943947264, "estimatedRequiredGiB": 96.069, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 85961192668, "modelscopeLicense": "other", "modelscopeParams": 23296987648, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jang-k", "custom_tag:mixed-precision", "custom_tag:awq", "custom_tag:minimax", "custom_tag:minimax-m2", "custom_tag:moe", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 85961192668}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.545079+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729537", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T07:05:13.504626+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794148, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794148}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T23:02:52.997156+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729536", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-09T08:15:14.695093+00:00", "modelId": "prithivMLmods/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "4f3136f992dfe382f83b8c05ac28a4f522cfe037720f66fc7a6d516d08ffcc0f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1490357184, "estimatedRequiredGiB": 43.21, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 38663413453, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:llama-cpp", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38663413453}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:44.993981+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730579", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695166+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043809154, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043809154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.008972+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730582", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695125+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.012578+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730585", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695156+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:44.995252+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730580", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695186+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.016194+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730586", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695177+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.014363+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730587", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695114+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.003355+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730583", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695136+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.007232+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730581", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695108+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.047245+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730590", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695150+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.027681+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730589", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695181+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.019303+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730588", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695069+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426230291, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426230291}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.021813+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730584", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695130+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.139430+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730592", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T08:15:14.695162+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T00:13:45.141151+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4730591", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T10:16:34.504615+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9536343971, "modelscopeLicense": null, "modelscopeParams": 2519020032, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9536343971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T02:14:39.291294+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4732363", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-09T11:30:49.443130+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574489, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T03:27:23.590101+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4733219", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T11:43:37.216638+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574489, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T03:43:18.853211+00:00", "targetGpu": "Vastai_va16", "taskId": "4733415", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-09T12:02:14.907044+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "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": 17931574489, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T03:59:11.865737+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4733621", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T12:18:30.400502+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574577, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T04:15:09.998965+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4733756", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T12:31:26.641233+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "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": 17931574577, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T04:30:36.752310+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4733926", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-09T14:42:07.646479+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T06:38:12.914042+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4735580", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-09T14:42:07.646519+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T06:38:12.915477+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4735579", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T14:59:28.333281+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T06:54:09.304972+00:00", "targetGpu": "Vastai_va16", "taskId": "4735789", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T14:59:28.333320+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T06:54:09.310751+00:00", "targetGpu": "Vastai_va16", "taskId": "4735790", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T15:13:55.015976+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35620174949, "estimatedRequiredGiB": 39.84, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9345525760, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35648665467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:10:09.840421+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4736014", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T15:13:55.015983+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:10:50.992166+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4736027", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-09T15:13:55.015946+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574577, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:10:50.969872+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4736028", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-09T15:13:55.015968+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "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": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:10:50.967869+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4736026", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T15:30:59.418702+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35620174949, "estimatedRequiredGiB": 39.84, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9345525760, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35648665467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:25:45.301380+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4736171", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-09T15:30:59.418738+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:26:57.684324+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4736186", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T15:30:59.418729+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:26:57.641158+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4736185", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-09T15:47:37.673636+00:00", "modelId": "Mungert/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "50b371e6c8f9d28c4f46314b835c0bfdf8660f3714d3c2804419c82f88e71ddb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 966342688, "estimatedRequiredGiB": 57.767, "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": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 51688732063}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:39:28.588872+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4736314", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T15:47:37.673652+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35620174949, "estimatedRequiredGiB": 39.84, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9345525760, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35648665467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:42:00.347711+00:00", "targetGpu": "Biren_166m", "taskId": "4736338", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T15:47:37.673626+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "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": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:42:00.349244+00:00", "targetGpu": "Biren_166m", "taskId": "4736341", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T15:47:37.673601+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:42:00.352448+00:00", "targetGpu": "Biren_166m", "taskId": "4736340", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T15:47:37.673645+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "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": 17931574577, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:42:00.356711+00:00", "targetGpu": "Biren_166m", "taskId": "4736339", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T15:55:15.906585+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:52:09.059377+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4736627", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-09T15:55:15.906558+00:00", "modelId": "Mungert/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "38a6a494beb1fd4000e1da86904f50b5cfaa988a3687ee5b00ea05055270e6fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 966342688, "estimatedRequiredGiB": 57.767, "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": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 51688732063}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T07:54:32.268749+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4736698", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T16:11:26.734427+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T08:07:14.060941+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4736884", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T16:11:26.734352+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35620174949, "estimatedRequiredGiB": 39.84, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 35648665467, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9345525760, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35648665467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T08:10:45.446803+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4736920", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T16:11:26.734418+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T08:10:45.450685+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4736922", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T16:11:26.734408+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574577, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T08:10:45.448357+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4736923", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T16:11:26.734435+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T08:10:45.445768+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4736921", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-09T17:51:53.704053+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T09:45:56.240950+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4738124", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-09T18:00:30.188901+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838556, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838556}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:00:13.353192+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4738344", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T18:09:45.834719+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:01:35.815834+00:00", "targetGpu": "Vastai_va16", "taskId": "4738373", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T18:17:57.609954+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838556, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838556}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:15:29.199861+00:00", "targetGpu": "Vastai_va16", "taskId": "4738578", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T18:17:57.609926+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:16:45.484218+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4738593", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T18:37:50.109560+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838556, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838556}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:31:32.626874+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4738925", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-09T18:37:50.109584+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:32:50.129162+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4738947", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T18:48:23.446781+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:46:50.761768+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4739146", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T18:48:23.446807+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838556, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838556}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T10:46:50.760190+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4739145", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-09T19:08:24.911927+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838556, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838556}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:02:10.941643+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4739315", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T19:08:24.911871+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:02:10.942699+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4739316", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T19:18:48.711692+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:08:41.646654+00:00", "targetGpu": "Biren_166m", "taskId": "4739398", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-09T19:18:48.711711+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777904, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:18:03.045534+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4739524", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-09T19:18:48.711731+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:18:03.047370+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4739523", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T19:18:48.711702+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838556, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838556}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:18:03.048835+00:00", "targetGpu": "Biren_166m", "taskId": "4739522", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T19:37:31.704706+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:33:17.847799+00:00", "targetGpu": "Vastai_va16", "taskId": "4739773", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T19:37:31.704762+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777904, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:33:17.843220+00:00", "targetGpu": "Vastai_va16", "taskId": "4739774", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T19:37:31.704726+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838556, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838556}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:33:17.848974+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4739772", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T19:56:42.896510+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:48:22.113026+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4739932", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T19:56:42.896500+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777904, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:48:22.109630+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4739931", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T19:56:42.896476+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:50:46.743760+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4739959", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T19:56:42.896518+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838556, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838556}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T11:50:46.742747+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4739958", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-09T20:05:01.109374+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T12:03:37.164977+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4740109", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-09T20:05:01.109303+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777904, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T12:03:37.168524+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4740110", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T20:23:37.101884+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777904, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T12:18:42.029908+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4740277", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T20:23:37.101831+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043777882}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T12:18:42.031229+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4740276", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T20:34:13.525536+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777882, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T12:30:12.295655+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4740399", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-09T20:34:13.525528+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043777904, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T12:30:12.298654+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4740400", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T21:28:48.925732+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778298, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T13:24:40.846297+00:00", "targetGpu": "Biren_166m", "taskId": "4741083", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-09T21:28:48.925753+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778320, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T13:24:40.847590+00:00", "targetGpu": "Biren_166m", "taskId": "4741082", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T23:05:47.802256+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778298, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T15:04:57.782677+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4742257", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T23:05:47.802235+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778320, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T15:04:57.783545+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4742256", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T00:59:29.336134+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T16:58:40.742484+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4743575", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T01:25:11.702629+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T17:17:51.553387+00:00", "targetGpu": "Vastai_va16", "taskId": "4743762", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T01:42:34.770227+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T17:36:33.499638+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4743919", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T01:59:31.241046+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T17:53:28.482893+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4744096", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-10T02:15:07.106881+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T18:11:56.418165+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4744370", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T02:32:07.501649+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16397514624, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T18:31:44.217327+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4744546", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395938+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35620174949, "estimatedRequiredGiB": 39.84, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 35648665467, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9345525760, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35648665467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:22.089453+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746439", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395982+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "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": "2026-09-09T14:21:21.949441+00:00", "modelType": "qwen3_5", "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": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:22.086828+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746438", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395927+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838972, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838972}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:22.085342+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746443", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395960+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778298, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:22.047953+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746444", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395972+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778298, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:22.090694+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746448", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395995+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778320, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:22.093383+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746449", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395932+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:22.095630+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746442", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395966+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "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": "2026-09-09T14:21:21.949441+00:00", "modelType": "qwen3_5", "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": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:22.098266+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746440", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395955+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574577, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:22.088163+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746445", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395950+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20034587064, "estimatedRequiredGiB": 22.413, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20054851725, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:qwen3.5-architecture", "custom_tag:gptq-pro", "custom_tag:gptq", "custom_tag:4-bit", "custom_tag:4bit", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:text-generation", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 20054851725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:22.091584+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746446", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395907+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952487299, "estimatedRequiredGiB": 33.498, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 29973198172, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "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": "2026-09-09T14:21:21.949441+00:00", "modelType": "qwen3_5", "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": 29973198172}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:32.651613+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746451", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395988+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:32.647276+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746452", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395944+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21921675140, "estimatedRequiredGiB": 24.525, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 21944922993, "modelscopeLicense": "apache-2.0", "modelscopeParams": 18589348592, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:vllm", "custom_tag:sm121", "custom_tag:gb10", "custom_tag:dgx-spark", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:modelopt"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21944922993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:32.653546+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746450", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395862+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8991501632, "estimatedRequiredGiB": 10.084, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9023443508, "modelscopeLicense": "mit", "modelscopeParams": 9409813744, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9023443508}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:32.655185+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746453", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395920+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 28168623119, "estimatedRequiredGiB": 31.505, "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": 28190535646, "modelscopeLicense": null, "modelscopeParams": 7584230528, "modelscopeTags": ["model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:00:25.508497+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 28190535646}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:32.684861+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746455", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395914+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ_K", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 79395122602, "estimatedRequiredGiB": 88.75, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 79412319434, "modelscopeLicense": "other", "modelscopeParams": 19984155322, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:jangtq-prestack", "custom_tag:jangtq-k", "custom_tag:mixed-precision", "custom_tag:minimax", "custom_tag:minimax-m2", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:conversational", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:quantization", "custom_tag:230b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 79412319434}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:32.618999+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746456", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T05:11:27.395892+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3554214621, "estimatedRequiredGiB": 3.984, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3564406686, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1777088000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3564406686}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-09T21:08:32.656390+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4746454", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218174+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35620174949, "estimatedRequiredGiB": 39.84, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 35648665467, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9345525760, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35648665467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.859936+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749146", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218150+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838972, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838972}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.850913+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749148", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218196+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778320, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.864784+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749147", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218234+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778298, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.853008+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749145", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218190+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778298, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.857970+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749149", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218240+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.862038+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749144", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:28:01.218183+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:22:02.847614+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4749143", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454674+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043809570, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043809570}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.091512+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749457", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454453+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.051663+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749456", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454574+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.093785+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749466", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454659+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.090459+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749455", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454514+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.084513+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749459", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454606+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.097416+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749460", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454636+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.053014+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749465", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454644+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.095206+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749461", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454565+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.089395+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749462", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454428+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "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": 1426230707, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426230707}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.092535+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749464", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454615+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-8bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35620174949, "estimatedRequiredGiB": 39.84, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 35648665467, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9345525760, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35648665467}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.087894+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749458", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454506+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838972, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838972}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:42:56.096428+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749463", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454557+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778320, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:43:04.111606+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749472", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454651+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778298, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:43:04.113703+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749467", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454666+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778298, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:43:04.115623+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749468", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454482+00:00", "modelId": "JANGQ-AI/Ling-2.6-flash-JANGTQ", "modelProfile": {"architectures": ["BailingMoeV2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30593642304, "estimatedRequiredGiB": 34.208, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 30608423891, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:mixture-of-experts", "custom_tag:hybrid-attention", "custom_tag:mla", "custom_tag:lightning-attention", "custom_tag:jangtq", "custom_tag:jangq-ai", "custom_tag:mlx", "custom_tag:bailing", "custom_tag:ling", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 30608423891}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:43:04.107121+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749470", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454464+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:43:04.109010+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749469", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T08:45:45.454474+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T00:43:04.105705+00:00", "targetGpu": "MetaX_c-500", "taskId": "4749471", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T10:04:06.914723+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T02:01:08.689124+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4750549", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402494+00:00", "modelId": "whq1111/M2RL-SFT", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:18.064831+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751419", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402583+00:00", "modelId": "whq1111/M2RL-RL_Math", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:18.083836+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751414", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402567+00:00", "modelId": "whq1111/M2RL-RL_Multi", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:17.982820+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751417", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402552+00:00", "modelId": "whq1111/M2RL-RL_Science", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:17.984748+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751412", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402470+00:00", "modelId": "whq1111/M2RL-MT_OPD", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044982008, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912361, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912361}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:18.150266+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751411", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402500+00:00", "modelId": "whq1111/M2RL-RL_Agent", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:18.172325+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751418", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402451+00:00", "modelId": "whq1111/M2RL-RL_Coding", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981872, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912225, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912225}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:17.999954+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751416", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402562+00:00", "modelId": "whq1111/M2RL-RL_IF", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8044981832, "estimatedRequiredGiB": 9.009, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 8060912185, "modelscopeLicense": null, "modelscopeParams": 4022468096, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8060912185}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:18.166785+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751421", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402477+00:00", "modelId": "OpenBMB/MiniCPM5-2B-MLX", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1426230707, "modelscopeLicense": "apache-2.0", "modelscopeParams": 393390080, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426230707}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:18.090220+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751422", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402572+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109838972, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109838972}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:18.009997+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751413", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402489+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778298, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:18.066416+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751420", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402546+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778320, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:18.084969+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751415", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402533+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043778298, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043778298}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:37.198105+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751425", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402483+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794236, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794236}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:37.196301+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751423", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402540+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:37.222862+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751424", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402557+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574577, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574577}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:37.226057+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751427", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T11:14:50.402577+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T03:12:37.213099+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4751426", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T13:14:20.004672+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:13:27.470794+00:00", "targetGpu": "Vastai_va16", "taskId": "4753071", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:30:05.632354+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:29:20.581004+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4753478", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:47:00.004700+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "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": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:39:25.454183+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753713", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:47:00.004708+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": null, "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": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:39:25.451335+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753714", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:47:00.004674+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "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": 35107181936, "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:fp8", "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": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:39:25.452554+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753715", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T13:55:40.785136+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "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": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:47:10.742578+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4753833", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T13:55:40.785159+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1764a9124cd000c7904ba9cee10ecdf5f9bfd4e65fc6896e0120a683f5e606e3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "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": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:54:18.783901+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754025", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:03:50.607039+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "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": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:55:59.442486+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754066", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:03:50.607077+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "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": 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": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:55:59.435840+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754067", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-10T14:03:50.607061+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "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": 35107181936, "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:fp8", "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": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T05:55:59.437900+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754068", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:03:50.607069+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:03:37.655467+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754205", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T14:13:15.207776+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "37bac6ce21d60134ebaca4c6569bab1151fd62af1ad962effbf472bc8bdbafbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 36341551917, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:11:11.806743+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4754342", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T14:13:15.207795+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:11:11.799771+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4754343", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T14:13:15.207804+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "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": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:12:56.897964+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754370", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T14:13:15.207812+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "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": 26090095180, "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": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:12:56.900331+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754369", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:13:15.207818+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "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:fp8", "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": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:12:56.905628+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4754371", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T14:29:51.626225+00:00", "modelId": "bartowski/MiniCPM5-2B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9ee85a9702ae695242c8b5436b1b856292d4a16c2f839d36bf93fbe98fb66d4e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1516997856, "estimatedRequiredGiB": 40.615, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 36341551917, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36341551917}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:28:56.145522+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4754660", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:29:51.626244+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:28:56.134725+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4754659", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-10T14:38:26.994325+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "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": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:30:53.020882+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754721", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-10T14:38:26.994318+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": 26090095180, "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": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:30:53.025848+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4754722", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-10T14:38:26.994284+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:38:16.883366+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4754820", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-10T14:38:26.994309+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:38:16.885606+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4754819", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:54:51.795891+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:48:30.776019+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4755021", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T14:54:51.795870+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "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": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:48:30.777395+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4755020", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:03:19.195695+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T06:56:12.042564+00:00", "targetGpu": "Vastai_va16", "taskId": "4755190", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009062+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.211286+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755594", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009036+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "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": 26090095180, "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": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.212561+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755595", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009053+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "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": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "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:fp8", "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": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.204766+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755596", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009045+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.209710+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755597", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009069+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "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": "2026-09-09T14:21:21.949441+00:00", "modelType": "qwen3_5", "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": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.214438+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755598", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T15:27:09.820539+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:23:10.180003+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4755805", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-10T15:40:28.508808+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:33:41.787375+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4756078", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T15:56:47.546297+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:50:25.385741+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4756398", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T17:58:58.347463+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T09:52:16.471862+00:00", "targetGpu": "MetaX_c-500", "taskId": "4758203", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930680+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "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": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.407832+00:00", "targetGpu": "Biren_166m", "taskId": "4760701", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930709+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "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": 26090095180, "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": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.401229+00:00", "targetGpu": "Biren_166m", "taskId": "4760703", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930689+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "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": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "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:fp8", "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": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.406185+00:00", "targetGpu": "Biren_166m", "taskId": "4760702", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930703+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.410963+00:00", "targetGpu": "Biren_166m", "taskId": "4760705", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930696+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.404088+00:00", "targetGpu": "Biren_166m", "taskId": "4760700", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T21:33:23.930655+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "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": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T13:27:23.409305+00:00", "targetGpu": "Biren_166m", "taskId": "4760704", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504477+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.894640+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761529", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504471+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "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": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.888510+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761528", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504443+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "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:fp8", "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": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.890611+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761532", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504483+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.893195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761530", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-10T22:47:57.504463+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T14:46:30.895806+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761531", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T23:20:13.106498+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "e4ab8f6cadfae4845d02aa9c1f89de5907e1f311ae817b1e8e370b501bd7f2e9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3275575456, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451378, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T15:13:26.242352+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4761809", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T23:36:16.447898+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "2be5f709184000d7e6bae759e29c6586ad3430b235ef3eb2dab86a5c2487a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3275575456, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451381, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T15:29:43.673390+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4761977", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-10T23:52:39.100998+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "3c43a7b363b10641156f2dcd17c04ae440fc05853ca582765c541a11de39bf3c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3275575456, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451381, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T15:48:00.105279+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4762249", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-11T00:08:37.400455+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "64a1b6ebfb0622fcb0e9711de8fd762fea6114b6c735fc8869cefa58db373ce1", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3275575456, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451381, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T16:07:13.322943+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4762525", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-11T00:31:28.598295+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235096, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451381, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T16:25:38.566044+00:00", "targetGpu": "Vastai_va16", "taskId": "4762814", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-11T00:48:10.746596+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235096, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451381, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T16:44:41.216042+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4763237", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-11T01:55:11.999406+00:00", "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "modelProfile": {"architectures": [], "configFingerprint": "34532436dbc855d32b74faf635c17eb60fc9f7a7dc8d2b76403af96f7424ebf3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2874779040, "estimatedRequiredGiB": 11.734, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10499570876, "modelscopeLicense": null, "modelscopeParams": 2697198592, "modelscopeTags": ["library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10499570876}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T17:52:07.266826+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4764441", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-11T02:10:47.005312+00:00", "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "modelProfile": {"architectures": [], "configFingerprint": "1bb1691a97b5ca0ea0c7ced63e4ad26ae05d4e6853c41103188e78e754faa6b2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2874779040, "estimatedRequiredGiB": 11.734, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10499570876, "modelscopeLicense": null, "modelscopeParams": 2697198592, "modelscopeTags": ["library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10499570876}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T18:09:17.543816+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4764783", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-11T02:33:13.897390+00:00", "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "modelProfile": {"architectures": [], "configFingerprint": "5f5faa291a86bf437595530575b613347621c9e314bbff70f201eec1d3f4e9bd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2874779040, "estimatedRequiredGiB": 11.734, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10499570876, "modelscopeLicense": null, "modelscopeParams": 2697198592, "modelscopeTags": ["library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10499570876}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T18:25:40.316507+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4765091", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-11T03:51:09.601013+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235096, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451381, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T19:50:31.405521+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4766604", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-11T06:36:38.210693+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235096, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451381, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T22:33:54.829362+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4768606", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-11T08:31:10.193623+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T00:23:48.375203+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4769876", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-11T08:31:10.193598+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T00:23:48.372888+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4769875", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-11T10:30:30.924990+00:00", "modelId": "webAI-Official/TwIL-LM3", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235096, "estimatedRequiredGiB": 24.879, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 22261451381, "modelscopeLicense": "other", "modelscopeParams": 3075098624, "modelscopeTags": ["license:other", "model_type:smollm3", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:smollm3", "custom_tag:twil-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22261451381}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T02:28:05.101259+00:00", "targetGpu": "Biren_166m", "taskId": "4771184", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-11T18:34:19.116348+00:00", "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "modelProfile": {"architectures": [], "configFingerprint": "210478cd4aaac159760a821d912afadc8c24e731c59a89524484711a2c016d6a", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2874779040, "estimatedRequiredGiB": 11.734, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10499570876, "modelscopeLicense": null, "modelscopeParams": 2697198592, "modelscopeTags": ["library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10499570876}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.286927+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776571", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116420+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23926484304, "estimatedRequiredGiB": 26.777, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23959625409, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107212656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23959625409}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.285223+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776565", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116372+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26057989872, "estimatedRequiredGiB": 29.158, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26090095180, "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": 26090095180}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.293196+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776566", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116384+00:00", "modelId": "OpenBMB/MiniCPM5-2B-GPTQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2099615880, "estimatedRequiredGiB": 2.358, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2109839916, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 2109839916}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.288482+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776572", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116366+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Base", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043779264, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043779264}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.289821+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776567", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116394+00:00", "modelId": "OpenBMB/MiniCPM5-2B-SFT", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043779242, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043779242}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.292184+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776574", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116415+00:00", "modelId": "OpenBMB/MiniCPM5-2B-Midtrain", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043779242, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043779242}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.294996+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776570", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116404+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22263760648, "estimatedRequiredGiB": 24.908, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 22286993822, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6019449856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22286993822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.290699+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776568", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116411+00:00", "modelId": "TokenRhythm/NeoHorse-1-4B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8411552560, "estimatedRequiredGiB": 9.428, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 8435794426, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 4205751296, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8435794426}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.294068+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776569", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116319+00:00", "modelId": "TokenRhythm/NeoHorse-1-9B", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17907657384, "estimatedRequiredGiB": 20.04, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 17931574767, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 8953803264, "modelscopeTags": ["license:Apache License 2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agentic", "custom_tag:tool-use", "custom_tag:coding", "custom_tag:reasoning", "custom_tag:instruction-following"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17931574767}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:33.315729+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776573", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116359+00:00", "modelId": "ddalcu/Muse-Glimmer-30B-MLX-Serve-4bit", "modelProfile": {"architectures": ["MuseGlimmerForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21407235494, "estimatedRequiredGiB": 23.956, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "muse_glimmer", "modelscopeFileSize": 21435726263, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5792290816, "modelscopeTags": ["license:apache-2.0", "model_type:muse_glimmer", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:muse_glimmer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21435726263}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:40.672353+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776577", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116390+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:40.677288+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776576", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116399+00:00", "modelId": "laion/swesmith-nl2bash-stack-bugsseq", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8593, "estimatedRequiredGiB": 18.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 16398873171, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8190735360, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama-factory", "custom_tag:full", "custom_tag:generated_from_trainer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16398873171}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:40.674298+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776575", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-11T18:34:19.116378+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T10:27:40.670287+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4776578", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-11T23:35:43.695551+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T15:30:58.007700+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4782245", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-11T23:52:34.207593+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 3443, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T15:45:34.084559+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4782449", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-11T23:52:34.207615+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T15:47:34.151696+00:00", "targetGpu": "Vastai_va16", "taskId": "4782467", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-12T00:09:40.009697+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 3443, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:03:11.891697+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4782663", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-12T00:09:40.009666+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:05:31.441883+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4782685", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-12T00:26:24.633017+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 3443, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:20:38.542601+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4782813", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T00:26:24.633044+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:22:36.317588+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4782838", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-12T00:43:33.238151+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "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": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:36:55.600970+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4782993", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-12T00:43:33.238131+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:38:55.116829+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4783004", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T00:52:00.210563+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:49:10.249505+00:00", "targetGpu": "Vastai_va16", "taskId": "4783129", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-customized", "lastSyncTime": "2026-09-12T01:00:32.503357+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T16:54:32.845710+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4783202", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T01:09:07.406128+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T17:01:11.403970+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4783339", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-12T01:18:10.999715+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T17:12:06.612979+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4783476", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T01:25:57.322160+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T17:22:24.744587+00:00", "targetGpu": "MetaX_c-500", "taskId": "4783634", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-12T02:21:54.921668+00:00", "modelId": "guaidao2/LFM2.5-2.6B-For-CTF", "modelProfile": {"architectures": [], "configFingerprint": "6647f6920340e837cb19ab6ec8bc02c4d5d8cebe4d720e359319e40aa1ebaf79", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2874779040, "estimatedRequiredGiB": 11.734, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10499570876, "modelscopeLicense": null, "modelscopeParams": 2697198592, "modelscopeTags": ["library:gguf", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10499570876}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T18:18:29.685555+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4784429", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T02:21:54.921691+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T18:18:29.687478+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4784430", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T02:56:54.383907+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T18:51:22.774816+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4784981", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T02:56:54.383964+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-11T18:51:22.770505+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4784982", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T09:26:00.311248+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T01:22:51.902664+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4791408", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T09:26:00.311215+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-10T18:58:50.012615+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T01:22:51.904770+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4791409", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T09:26:00.311239+00:00", "modelId": "nex-agi/Nex-N2.5-mini", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70214494016, "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": 70235999301, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:00:25.508497+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 70235999301}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T01:22:51.908714+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4791410", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T13:02:08.318710+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T04:52:57.116897+00:00", "targetGpu": "Biren_166m", "taskId": "4794241", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T13:02:08.318700+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "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": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T04:52:57.114996+00:00", "targetGpu": "Biren_166m", "taskId": "4794242", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-12T14:23:18.821537+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "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": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T06:19:56.330927+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4795478", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-12T14:41:33.434314+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "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": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T06:36:56.396629+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4795634", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T14:59:07.400101+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T06:53:56.898337+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4795839", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T18:59:53.316548+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "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": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:00:25.508497+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T10:58:56.807180+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800525", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-12T18:59:53.316560+00:00", "modelId": "unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65827374264, "estimatedRequiredGiB": 73.588, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 65845719365, "modelscopeLicense": "other", "modelscopeParams": 32913266240, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 65845719365}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T10:58:56.798553+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800526", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T22:16:38.428761+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "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": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T14:09:52.635448+00:00", "targetGpu": "Biren_166m", "taskId": "4803464", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T00:10:37.716551+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T16:07:22.080195+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4804755", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-13T01:02:56.601934+00:00", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c21a8c5b2598ee6aec1301e1dba618e3f68c70a7ab35b6b215134aa6e6b9a3eb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2405581632, "estimatedRequiredGiB": 17.589, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 15737975890, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark-x2.5", "custom_tag:long-context", "custom_tag:1m-context", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15737975890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T16:59:17.247535+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4805292", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-13T01:20:19.415485+00:00", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8a404c56481bc57c46ceeb762de172692775aca5bd1f8ef53c0e95ef96b93e6a", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2405581632, "estimatedRequiredGiB": 17.589, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 15737975890, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark-x2.5", "custom_tag:long-context", "custom_tag:1m-context", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15737975890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T17:16:39.306865+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4805471", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-13T01:37:55.613775+00:00", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "29d7b6bec2440988a150b8d521c28df4707bcfe119f537490a5dfe23b9f8d11f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2405581632, "estimatedRequiredGiB": 17.589, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 15737975890, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark-x2.5", "custom_tag:long-context", "custom_tag:1m-context", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15737975890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T17:35:57.210723+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4805660", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-13T01:55:03.245431+00:00", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1e79b01d449f51953bad4aed5c8fa69cb99c8886275d952e7bc8585bd98fa275", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2405581632, "estimatedRequiredGiB": 17.589, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 15737975890, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark-x2.5", "custom_tag:long-context", "custom_tag:1m-context", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15737975890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T17:53:40.152278+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4805869", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-13T12:45:24.349519+00:00", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "79ee05d2f9945abf429c945f84a314444c4004617b3dd41343d3404019c31d6c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2405581632, "estimatedRequiredGiB": 17.589, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 15737975890, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark-x2.5", "custom_tag:long-context", "custom_tag:1m-context", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15737975890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T04:41:29.954503+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4817350", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-13T12:45:24.349544+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T04:41:29.963690+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4817349", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-13T12:45:24.349554+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T04:41:29.962163+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4817348", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-13T13:00:14.407763+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T04:51:53.062775+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4817454", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-13T13:17:31.149592+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:10:44.864092+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4817675", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T13:34:15.409837+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:29:18.044774+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4817992", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T13:43:30.144236+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:34:18.006195+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4818284", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-13T13:52:07.006302+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:44:36.060924+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4818885", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-13T14:08:03.641274+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T06:03:08.407319+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4819935", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T09:53:52.905331+00:00", "targetGpu": "MetaX_c-500", "taskId": "4823778", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T10:16:13.410881+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4824251", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T12:09:15.680573+00:00", "targetGpu": "Vastai_va16", "taskId": "4827491", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T14:02:33.487789+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4829151", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-13T14:24:08.911334+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4829350", "taskType": "text-generation", "verifyResult": null}