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

state: generation 25291 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-10-16 05:26:40 +00:00
parent 20276ec8bf
commit c9b0e0c907
7 changed files with 1975 additions and 1797 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2394,7 +2394,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-16T04:52:15.258687+00:00", "generatedAt": "2026-10-16T05:23:48.912651+00:00",
"summary": { "summary": {
"activeBlockCount": 119, "activeBlockCount": 119,
"byGpuFramework": { "byGpuFramework": {

302
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-10-16T04:53:31.868074+00:00", "communityAttemptedAt": "2026-10-16T05:25:25.261143+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-10-16T04:53:31.868074+00:00", "communityUpdatedAt": "2026-10-16T05:25:25.261143+00:00",
"frameworkAttemptedAt": "2026-10-16T04:26:52.157172+00:00", "frameworkAttemptedAt": "2026-10-16T04:26:52.157172+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -443,121 +443,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-16T04:53:31.868074+00:00", "generatedAt": "2026-10-16T05:25:25.261143+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 822.0295566502463, "backlogHours": 826.0396039603961,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b3", "gpu": "Ascend_910-b3",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 1.4346009911173652, "qualityFactor": 1.448801773925343,
"queueFactor": 1.0028370495352907, "queueFactor": 0.9885734861417033,
"queueWeight": 1.0028370495352907, "queueWeight": 0.9885734861417033,
"recentSuccess": 45, "recentSuccess": 46,
"recentSuccessRate": 0.22167487684729065, "recentSuccessRate": 0.22772277227722773,
"recentTerminal": 203, "recentTerminal": 202,
"recentWilsonLowerBound": 0.1700008376734527, "recentWilsonLowerBound": 0.17528926912266887,
"running": 8, "running": 8,
"selectionWeight": 1.4386710251925423, "selectionWeight": 1.43224702037766,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 33.833333333333336, "throughputPerHour": 33.666666666666664,
"waiting": 27812 "waiting": 27810
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1251.1788079470198, "backlogHours": 1218.5806451612905,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b4", "gpu": "Ascend_910-b4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.9415981107877459, "queueFactor": 0.9325689413648052,
"queueWeight": 0.9415981107877459, "queueWeight": 0.9325689413648052,
"recentSuccess": 43, "recentSuccess": 45,
"recentSuccessRate": 0.2847682119205298, "recentSuccessRate": 0.2903225806451613,
"recentTerminal": 151, "recentTerminal": 155,
"recentWilsonLowerBound": 0.218822241459768, "recentWilsonLowerBound": 0.22462146597970195,
"running": 9, "running": 9,
"selectionWeight": 2.3539952769693646, "selectionWeight": 2.331422353412013,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.166666666666668, "throughputPerHour": 25.833333333333332,
"waiting": 31488 "waiting": 31480
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 126.15384615384616, "backlogHours": 130.85333333333332,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.27716474140231456, "qualityFactor": 0.3766247255522104,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 27, "recentSuccess": 30,
"recentSuccessRate": 0.11538461538461539, "recentSuccessRate": 0.13333333333333333,
"recentTerminal": 234, "recentTerminal": 225,
"recentWilsonLowerBound": 0.08052091900983047, "recentWilsonLowerBound": 0.095016870162921,
"running": 8, "running": 9,
"selectionWeight": 0.36031416382300896, "selectionWeight": 0.4896121432178735,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 39.0, "throughputPerHour": 37.5,
"waiting": 4920 "waiting": 4907
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1031.8799999999999, "backlogHours": 1121.8695652173913,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x4", "gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.7312405290899603, "qualityFactor": 0.8342015591339378,
"queueFactor": 0.9692127222143008, "queueFactor": 0.9442081263526299,
"queueWeight": 0.9692127222143008, "queueWeight": 0.9442081263526299,
"recentSuccess": 19, "recentSuccess": 19,
"recentSuccessRate": 0.19, "recentSuccessRate": 0.20652173913043478,
"recentTerminal": 100, "recentTerminal": 92,
"recentWilsonLowerBound": 0.12514653992704258, "recentWilsonLowerBound": 0.13639031262233317,
"running": 7, "running": 7,
"selectionWeight": 0.708727623792706, "selectionWeight": 0.787659891150298,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.666666666666668, "throughputPerHour": 15.333333333333334,
"waiting": 17198 "waiting": 17202
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 304.6077348066298, "backlogHours": 322.42105263157896,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x8", "gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.36056535859669664, "qualityFactor": 0.4310464869955491,
"queueFactor": 1.1638642984170307, "queueFactor": 1.1384018166147412,
"queueWeight": 1.1638642984170307, "queueWeight": 1.1384018166147412,
"recentSuccess": 24, "recentSuccess": 25,
"recentSuccessRate": 0.13259668508287292, "recentSuccessRate": 0.14619883040935672,
"recentTerminal": 181, "recentTerminal": 171,
"recentWilsonLowerBound": 0.09074834863853101, "recentWilsonLowerBound": 0.10102852924009678,
"running": 7, "running": 8,
"selectionWeight": 0.4196491481166294, "selectionWeight": 0.4907041038411355,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 30.166666666666668, "throughputPerHour": 28.5,
"waiting": 9189 "waiting": 9189
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 53.54569190600522, "backlogHours": 60.19469026548673,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -567,196 +567,196 @@
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 7, "recentSuccess": 7,
"recentSuccessRate": 0.018276762402088774, "recentSuccessRate": 0.02064896755162242,
"recentTerminal": 383, "recentTerminal": 339,
"recentWilsonLowerBound": 0.008880737496294117, "recentWilsonLowerBound": 0.010037453114853875,
"running": 25, "running": 26,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 63.833333333333336, "throughputPerHour": 56.5,
"waiting": 3418 "waiting": 3401
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 116.19740259740259, "backlogHours": 123.51381215469613,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-150", "gpu": "Iluvatar_bi-150",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 50, "maxConcurrentTasks": 50,
"qualityFactor": 0.11023776413573937, "qualityFactor": 0.13036973781586633,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 29, "recentSuccess": 30,
"recentSuccessRate": 0.07532467532467532, "recentSuccessRate": 0.08287292817679558,
"recentTerminal": 385, "recentTerminal": 362,
"recentWilsonLowerBound": 0.05295479301439614, "recentWilsonLowerBound": 0.058664728888757324,
"running": 15, "running": 8,
"selectionWeight": 0.1433090933764612, "selectionWeight": 0.16948065916062624,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 64.16666666666667, "throughputPerHour": 60.333333333333336,
"waiting": 7456 "waiting": 7452
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2922.5454545454545, "backlogHours": 2836.235294117647,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_mrv-100", "gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.5154985915396488, "qualityFactor": 0.45452759504119644,
"queueFactor": 0.8290854513265647, "queueFactor": 0.8215760116754359,
"queueWeight": 0.8290854513265647, "queueWeight": 0.8215760116754359,
"recentSuccess": 7, "recentSuccess": 7,
"recentSuccessRate": 0.21212121212121213, "recentSuccessRate": 0.20588235294117646,
"recentTerminal": 33, "recentTerminal": 34,
"recentWilsonLowerBound": 0.10675886566436177, "recentWilsonLowerBound": 0.10349396022351322,
"running": 2, "running": 2,
"selectionWeight": 0.4273923824248582, "selectionWeight": 0.37342896873037384,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 5.5, "throughputPerHour": 5.666666666666667,
"waiting": 16074 "waiting": 16072
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 321.9146341463415, "backlogHours": 336.0,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.8849246517114894, "qualityFactor": 1.0019813686316872,
"queueFactor": 1.1542566290547287, "queueFactor": 1.131379218484214,
"queueWeight": 1.1542566290547287, "queueWeight": 1.131379218484214,
"recentSuccess": 31, "recentSuccess": 32,
"recentSuccessRate": 0.18902439024390244, "recentSuccessRate": 0.20382165605095542,
"recentTerminal": 164, "recentTerminal": 157,
"recentWilsonLowerBound": 0.13648223861567546, "recentWilsonLowerBound": 0.14823821725554062,
"running": 8, "running": 8,
"selectionWeight": 1.0214301454519337, "selectionWeight": 1.1336208977782614,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 27.333333333333332, "throughputPerHour": 26.166666666666668,
"waiting": 8799 "waiting": 8792
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 204.92879256965944, "backlogHours": 209.373417721519,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "MetaX_c-500", "gpu": "MetaX_c-500",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 0.1779625757923736, "qualityFactor": 0.13391338445207873,
"queueFactor": 1.2351594864828621, "queueFactor": 1.2145652671831433,
"queueWeight": 1.2351594864828621, "queueWeight": 1.2145652671831433,
"recentSuccess": 30, "recentSuccess": 27,
"recentSuccessRate": 0.09287925696594428, "recentSuccessRate": 0.08544303797468354,
"recentTerminal": 323, "recentTerminal": 316,
"recentWilsonLowerBound": 0.06583395566337273, "recentWilsonLowerBound": 0.05938424607219421,
"running": 4, "running": 4,
"selectionWeight": 0.2198121637288756, "selectionWeight": 0.16264654556643798,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 53.833333333333336, "throughputPerHour": 52.666666666666664,
"waiting": 11032 "waiting": 11027
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2430.28125, "backlogHours": 2592.1,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Mthreads_s4000", "gpu": "Mthreads_s4000",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 0.7005739118674827, "qualityFactor": 0.47489625894812304,
"queueFactor": 0.8523441897587273, "queueFactor": 0.8327436429353924,
"queueWeight": 0.8523441897587273, "queueWeight": 0.8327436429353924,
"recentSuccess": 13, "recentSuccess": 11,
"recentSuccessRate": 0.203125, "recentSuccessRate": 0.18333333333333332,
"recentTerminal": 64, "recentTerminal": 60,
"recentWilsonLowerBound": 0.12273302562695813, "recentWilsonLowerBound": 0.10557689037136128,
"running": 4, "running": 5,
"selectionWeight": 0.5971301032767916, "selectionWeight": 0.39546684069284943,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.666666666666666, "throughputPerHour": 10.0,
"waiting": 25923 "waiting": 25921
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 1307.642857142857, "backlogHours": 704.1923076923077,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Sunrise_pt-200-x1", "gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.13162478778738423, "qualityFactor": 0.05,
"queueFactor": 0.9353843804905697, "queueFactor": 1.0125241659400825,
"queueWeight": 0.9353843804905697, "queueWeight": 1.0125241659400825,
"recentSuccess": 9, "recentSuccess": 10,
"recentSuccessRate": 0.10714285714285714, "recentSuccessRate": 0.0641025641025641,
"recentTerminal": 84, "recentTerminal": 156,
"recentWilsonLowerBound": 0.057399563195232366, "recentWilsonLowerBound": 0.03518820211332016,
"running": 2, "running": 2,
"selectionWeight": 0.1231197705817051, "selectionWeight": 0.05062620829700413,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": false,
"throughputPerHour": 14.0, "throughputPerHour": 26.0,
"waiting": 18307 "waiting": 18309
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 911.7247706422017, "backlogHours": 974.9411764705883,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Vastai_va16", "gpu": "Vastai_va16",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 16, "maxConcurrentTasks": 16,
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 0.9873790820353235, "queueFactor": 0.9643003554896702,
"queueWeight": 0.9873790820353235, "queueWeight": 0.9643003554896702,
"recentSuccess": 4, "recentSuccess": 4,
"recentSuccessRate": 0.03669724770642202, "recentSuccessRate": 0.0392156862745098,
"recentTerminal": 109, "recentTerminal": 102,
"recentWilsonLowerBound": 0.014361469198727864, "recentWilsonLowerBound": 0.015353823095438892,
"running": 16, "running": 17,
"selectionWeight": 0.04936895410176618, "selectionWeight": 0.04821501777448351,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 18.166666666666668, "throughputPerHour": 17.0,
"waiting": 16563 "waiting": 16574
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 853.3757961783439, "backlogHours": 917.7534246575343,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "hygon_k100-ai", "gpu": "hygon_k100-ai",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 6, "maxConcurrentTasks": 6,
"qualityFactor": 0.9765674815272629, "qualityFactor": 1.1811584785613254,
"queueFactor": 0.9972233461634232, "queueFactor": 0.9730836752646295,
"queueWeight": 0.9972233461634232, "queueWeight": 0.9730836752646295,
"recentSuccess": 31, "recentSuccess": 32,
"recentSuccessRate": 0.19745222929936307, "recentSuccessRate": 0.2191780821917808,
"recentTerminal": 157, "recentTerminal": 146,
"recentWilsonLowerBound": 0.14273446406922466, "recentWilsonLowerBound": 0.1597484989176162,
"running": 6, "running": 6,
"selectionWeight": 0.9738558916830041, "selectionWeight": 1.1493660333884326,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.166666666666668, "throughputPerHour": 24.333333333333332,
"waiting": 22330 "waiting": 22332
} }
}, },
"queueAttemptedAt": "2026-10-16T04:53:31.868074+00:00", "queueAttemptedAt": "2026-10-16T05:25:25.261143+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-16T04:53:31.868074+00:00", "queueUpdatedAt": "2026-10-16T05:25:25.261143+00:00",
"supportedGpus": [ "supportedGpus": [
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",
"Vastai_va16", "Vastai_va16",

3173
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

255
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-16T04:25:26.546571+00:00", "generatedAt": "2026-10-16T05:23:48.814463+00:00",
"lastSyncTime": "2026-10-16T04:25:26.240633+00:00", "lastSyncTime": "2026-10-16T05:23:47.560351+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -4570,42 +4570,42 @@
"unresolvedFailureCount": 296 "unresolvedFailureCount": 296
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 136, "attributableFailureCount": 137,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 136, "decisionTotal": 137,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 3, "ambiguous_runtime": 3,
"backend_operator": 11, "backend_operator": 11,
"framework_architecture_unsupported": 28, "framework_architecture_unsupported": 29,
"platform_infrastructure": 31, "platform_infrastructure": 32,
"tokenizer_compatibility": 97, "tokenizer_compatibility": 97,
"参数/模板问题": 9 "参数/模板问题": 9
}, },
"failureCount": 179, "failureCount": 181,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 31, "platformFailureCount": 32,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 179, "total": 181,
"unresolvedFailureCount": 12 "unresolvedFailureCount": 12
}, },
"Sunrise_pt-200-x1|vllm|text-generation": { "Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 628, "attributableFailureCount": 629,
"decisionFailureRate": 0.9843, "decisionFailureRate": 0.9828,
"decisionSuccessRate": 0.0157, "decisionSuccessRate": 0.0172,
"decisionTotal": 638, "decisionTotal": 640,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 109, "ambiguous_runtime": 109,
"architecture_compatibility": 43, "architecture_compatibility": 43,
"backend_operator": 30, "backend_operator": 30,
"context_length": 34, "context_length": 34,
"framework_architecture_unsupported": 150, "framework_architecture_unsupported": 151,
"memory_capacity": 113, "memory_capacity": 113,
"platform_infrastructure": 221, "platform_infrastructure": 221,
"repository_structure": 75, "repository_structure": 75,
@@ -4613,17 +4613,17 @@
"tokenizer_compatibility": 182, "tokenizer_compatibility": 182,
"参数/模板问题": 9 "参数/模板问题": 9
}, },
"failureCount": 967, "failureCount": 968,
"failureRate": 0.9898, "failureRate": 0.9888,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 221, "platformFailureCount": 221,
"successCount": 10, "successCount": 11,
"successRate": 0.0102, "successRate": 0.0112,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 977, "total": 979,
"unresolvedFailureCount": 118 "unresolvedFailureCount": 118
}, },
"Sunrise_pt-200-x1|vllm|unknown": { "Sunrise_pt-200-x1|vllm|unknown": {
@@ -5126,17 +5126,17 @@
"unresolvedFailureCount": 6552 "unresolvedFailureCount": 6552
}, },
"vllm": { "vllm": {
"attributableFailureCount": 3699, "attributableFailureCount": 3700,
"decisionFailureRate": 0.9711, "decisionFailureRate": 0.9709,
"decisionSuccessRate": 0.0289, "decisionSuccessRate": 0.0291,
"decisionTotal": 3809, "decisionTotal": 3811,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1606, "ambiguous_runtime": 1606,
"architecture_compatibility": 112, "architecture_compatibility": 112,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 95, "backend_operator": 95,
"context_length": 161, "context_length": 161,
"framework_architecture_unsupported": 1414, "framework_architecture_unsupported": 1415,
"memory_capacity": 725, "memory_capacity": 725,
"model_load": 228, "model_load": 228,
"platform_infrastructure": 885, "platform_infrastructure": 885,
@@ -5145,14 +5145,14 @@
"tokenizer_compatibility": 425, "tokenizer_compatibility": 425,
"参数/模板问题": 87 "参数/模板问题": 87
}, },
"failureCount": 6277, "failureCount": 6278,
"failureRate": 0.9828, "failureRate": 0.9826,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 885, "platformFailureCount": 885,
"successCount": 110, "successCount": 111,
"successRate": 0.0172, "successRate": 0.0174,
"total": 6387, "total": 6389,
"unresolvedFailureCount": 1693 "unresolvedFailureCount": 1693
}, },
"vllm-customized": { "vllm-customized": {
@@ -5250,28 +5250,28 @@
"unresolvedFailureCount": 57 "unresolvedFailureCount": 57
}, },
"vllm_fix_tokenizer": { "vllm_fix_tokenizer": {
"attributableFailureCount": 185, "attributableFailureCount": 186,
"decisionFailureRate": 0.9737, "decisionFailureRate": 0.9738,
"decisionSuccessRate": 0.0263, "decisionSuccessRate": 0.0262,
"decisionTotal": 190, "decisionTotal": 191,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 422, "ambiguous_runtime": 422,
"backend_operator": 11, "backend_operator": 11,
"framework_architecture_unsupported": 54, "framework_architecture_unsupported": 55,
"memory_capacity": 10, "memory_capacity": 10,
"model_load": 13, "model_load": 13,
"platform_infrastructure": 31, "platform_infrastructure": 32,
"tokenizer_compatibility": 97, "tokenizer_compatibility": 97,
"参数/模板问题": 23 "参数/模板问题": 23
}, },
"failureCount": 661, "failureCount": 663,
"failureRate": 0.9925, "failureRate": 0.9925,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 31, "platformFailureCount": 32,
"successCount": 5, "successCount": 5,
"successRate": 0.0075, "successRate": 0.0075,
"total": 666, "total": 668,
"unresolvedFailureCount": 445 "unresolvedFailureCount": 445
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
@@ -5303,7 +5303,7 @@
"unresolvedFailureCount": 336 "unresolvedFailureCount": 336
} }
}, },
"generatedAt": "2026-10-16T04:25:26.533417+00:00", "generatedAt": "2026-10-16T05:23:48.800921+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 130, "attributableFailureCount": 130,
@@ -5639,32 +5639,32 @@
"unresolvedFailureCount": 331 "unresolvedFailureCount": 331
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"attributableFailureCount": 783, "attributableFailureCount": 785,
"decisionFailureRate": 0.8837, "decisionFailureRate": 0.883,
"decisionSuccessRate": 0.1163, "decisionSuccessRate": 0.117,
"decisionTotal": 886, "decisionTotal": 889,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 165, "ambiguous_runtime": 165,
"architecture_compatibility": 44, "architecture_compatibility": 44,
"backend_operator": 41, "backend_operator": 41,
"context_length": 39, "context_length": 39,
"framework_architecture_unsupported": 180, "framework_architecture_unsupported": 182,
"memory_capacity": 113, "memory_capacity": 113,
"platform_infrastructure": 252, "platform_infrastructure": 253,
"repository_structure": 83, "repository_structure": 83,
"runtime_memory": 1, "runtime_memory": 1,
"tokenizer_compatibility": 282, "tokenizer_compatibility": 282,
"参数/模板问题": 231, "参数/模板问题": 231,
"验证失败": 32 "验证失败": 32
}, },
"failureCount": 1463, "failureCount": 1466,
"failureRate": 0.9342, "failureRate": 0.9338,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 252, "platformFailureCount": 253,
"successCount": 103, "successCount": 104,
"successRate": 0.0658, "successRate": 0.0662,
"total": 1566, "total": 1570,
"unresolvedFailureCount": 428 "unresolvedFailureCount": 428
}, },
"Vastai_va16": { "Vastai_va16": {
@@ -22771,14 +22771,15 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4|none": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4|none": {
"attributableFailureCount": 0, "attributableFailureCount": 1,
"decisionFailureRate": 0.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 2 "platform_infrastructure": 2
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelType": "gemma4", "modelType": "gemma4",
@@ -22790,7 +22791,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors": {
@@ -23024,6 +23025,29 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|prism_hadamard_qwen35|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"platform_infrastructure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "prism_hadamard_qwen35",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen2|none": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen2|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -23649,15 +23673,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none": { "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none": {
"attributableFailureCount": 5, "attributableFailureCount": 6,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 5, "decisionTotal": 6,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 5, "framework_architecture_unsupported": 6,
"platform_infrastructure": 7 "platform_infrastructure": 7
}, },
"failureCount": 12, "failureCount": 13,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "qwen3_5", "modelType": "qwen3_5",
@@ -23669,14 +23693,14 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 12, "total": 13,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|qwen3|none": { "Sunrise_pt-200-x1|vllm|text-generation|qwen3|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0, "decisionSuccessRate": 1.0,
"decisionTotal": 8, "decisionTotal": 9,
"failureBreakdown": {}, "failureBreakdown": {},
"failureCount": 0, "failureCount": 0,
"failureRate": 0.0, "failureRate": 0.0,
@@ -23686,11 +23710,11 @@
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"quantizationMethod": "none", "quantizationMethod": "none",
"successCount": 8, "successCount": 9,
"successRate": 1.0, "successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 8, "total": 9,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none": { "Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none": {
@@ -54094,14 +54118,15 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4|none|32": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4|none|32": {
"attributableFailureCount": 0, "attributableFailureCount": 1,
"decisionFailureRate": 0.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 1,
"platform_infrastructure": 1 "platform_infrastructure": 1
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32, "loadSizeLog2Bucket": 32,
@@ -54114,7 +54139,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4|none|34": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma4|none|34": {
@@ -54549,6 +54574,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|prism_hadamard_qwen35|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"platform_infrastructure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33,
"modelType": "prism_hadamard_qwen35",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen2|none|31": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen2|none|31": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -55486,6 +55535,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|33": { "Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 2, "attributableFailureCount": 2,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -55580,6 +55653,28 @@
"total": 7, "total": 7,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|qwen3|none|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0,
"decisionTotal": 1,
"failureBreakdown": {},
"failureCount": 0,
"failureRate": 0.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "qwen3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 1,
"successRate": 1.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none|31": { "Sunrise_pt-200-x1|vllm|text-generation|rwkv7|none|31": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -59116,23 +59211,23 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17871, "terminalRecords": 17875,
"totalRecords": 18400, "totalRecords": 18404,
"totals": { "totals": {
"attributableFailureCount": 6328, "attributableFailureCount": 6330,
"decisionFailureRate": 0.8655, "decisionFailureRate": 0.8655,
"decisionSuccessRate": 0.1345, "decisionSuccessRate": 0.1345,
"decisionTotal": 7311, "decisionTotal": 7314,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4640, "ambiguous_runtime": 4640,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 132, "backend_operator": 132,
"context_length": 327, "context_length": 327,
"framework_architecture_unsupported": 2338, "framework_architecture_unsupported": 2340,
"memory_capacity": 1206, "memory_capacity": 1206,
"model_load": 571, "model_load": 571,
"platform_infrastructure": 964, "platform_infrastructure": 965,
"repository_structure": 742, "repository_structure": 742,
"runtime_memory": 101, "runtime_memory": 101,
"tokenizer_compatibility": 696, "tokenizer_compatibility": 696,
@@ -59140,14 +59235,14 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16888, "failureCount": 16891,
"failureRate": 0.945, "failureRate": 0.945,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 964, "platformFailureCount": 965,
"successCount": 983, "successCount": 984,
"successRate": 0.055, "successRate": 0.055,
"total": 17871, "total": 17875,
"unresolvedFailureCount": 9596 "unresolvedFailureCount": 9596
}, },
"warnings": [ "warnings": [
@@ -59210,6 +59305,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 18400, "summarizedRecords": 18404,
"version": 1 "version": 1
} }

12
.modelhub_state/recovery_intents.jsonl
View File

@@ -3628,6 +3628,18 @@
{"batchId": "0c5bdecc2ea74891b2a8857412ca837b", "completedAt": "2026-10-15T21:59:18.744644+00:00", "configFingerprint": "009fc97a918caf620bbf7e2f303f8358c81f71f6acbbaccb4b07beb42ed53fef", "configSource": "modelhub_live", "createdAt": "2026-10-15T21:40:45.759803+00:00", "framework": "llamacpp", "intentId": "dfa4c58702074a3593ebb0f1d5d72c83", "lastModified": "2026-10-15T13:20:15+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "reason": null, "reconciledAt": "2026-10-16T05:18:39.121330+00:00", "repoId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5570020", "taskType": "text-generation"} {"batchId": "0c5bdecc2ea74891b2a8857412ca837b", "completedAt": "2026-10-15T21:59:18.744644+00:00", "configFingerprint": "009fc97a918caf620bbf7e2f303f8358c81f71f6acbbaccb4b07beb42ed53fef", "configSource": "modelhub_live", "createdAt": "2026-10-15T21:40:45.759803+00:00", "framework": "llamacpp", "intentId": "dfa4c58702074a3593ebb0f1d5d72c83", "lastModified": "2026-10-15T13:20:15+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "reason": null, "reconciledAt": "2026-10-16T05:18:39.121330+00:00", "repoId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5570020", "taskType": "text-generation"}
{"batchId": "4f111eebb42f4d41a30644b1f83a8e8f", "completedAt": "2026-10-16T00:38:37.615391+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-16T00:19:35.667368+00:00", "framework": "vllm_tokenizer_patch", "intentId": "92784d4097d24f36b44d2f0a828bab88", "lastModified": "2026-10-15T14:13:15+00:00", "modelAddress": "https://modelscope.cn/models/castorini/gaggle-nanochat-pretrained-climbmix-20260924", "reason": null, "reconciledAt": "2026-10-16T05:18:39.117659+00:00", "repoId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5572093", "taskType": "text-generation"} {"batchId": "4f111eebb42f4d41a30644b1f83a8e8f", "completedAt": "2026-10-16T00:38:37.615391+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-16T00:19:35.667368+00:00", "framework": "vllm_tokenizer_patch", "intentId": "92784d4097d24f36b44d2f0a828bab88", "lastModified": "2026-10-15T14:13:15+00:00", "modelAddress": "https://modelscope.cn/models/castorini/gaggle-nanochat-pretrained-climbmix-20260924", "reason": null, "reconciledAt": "2026-10-16T05:18:39.117659+00:00", "repoId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5572093", "taskType": "text-generation"}
{"batchId": "29836839f014447d89961a66093bc606", "completedAt": "2026-10-16T04:48:00.737557+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T04:28:15.287005+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5cb8a52aa10a45dca34a87430fff749a", "lastModified": "2026-10-15T11:41:45+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2", "reason": null, "reconciledAt": "2026-10-16T05:18:39.119216+00:00", "repoId": "DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5575924", "taskType": "text-generation"} {"batchId": "29836839f014447d89961a66093bc606", "completedAt": "2026-10-16T04:48:00.737557+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T04:28:15.287005+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5cb8a52aa10a45dca34a87430fff749a", "lastModified": "2026-10-15T11:41:45+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2", "reason": null, "reconciledAt": "2026-10-16T05:18:39.119216+00:00", "repoId": "DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5575924", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "228b6bc2745650abd95687d8da71c138b5e7b7e9cbd7ff60115887f5ff13ac2c", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.656628+00:00", "framework": "llamacpp", "intentId": "fdd38ce2d99b43799a6bd589edac9d45", "lastModified": "2026-10-15T11:37:55+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B-GGUF", "repoId": "DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "f15ba589f8fc347b06d694c47e50f0ec39eb094f4731fb654c6ecbc9c8faac9b", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.656741+00:00", "framework": "llamacpp", "intentId": "e6709c309c284f429e79507bbdd1ba35", "lastModified": "2026-10-15T23:18:06+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/microsoft-UserRepGen-4B-GGUF", "repoId": "prithivMLmods/microsoft-UserRepGen-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "e9c4f4f15802a39a57c6e07956c53755f75fc438be43d1164a8a2eda32456b1e", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.656802+00:00", "framework": "llamacpp", "intentId": "4a6baff32e2240cd85db5ebabe7461b4", "lastModified": "2026-10-15T13:20:15+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "repoId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "61898f295f143f06988745beef05f856402c5162f007122829060f3694145199", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.656860+00:00", "framework": "llamacpp", "intentId": "3bee5ca438b441d3a7074b7b7014a4c2", "lastModified": "2026-10-15T14:56:28+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "repoId": "DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.656915+00:00", "framework": "vllm_tokenizer_patch", "intentId": "b8ad3b52d2fa433393f7e958b9fff2b7", "lastModified": "2026-10-15T14:13:15+00:00", "modelAddress": "https://modelscope.cn/models/castorini/gaggle-nanochat-pretrained-climbmix-20260924", "repoId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.656969+00:00", "framework": "vllm_tokenizer_patch", "intentId": "7a9e3eff095845c896ab6a69a10220fe", "lastModified": "2026-10-15T08:32:12+00:00", "modelAddress": "https://modelscope.cn/models/mrm8488/mistral-7b-ft-h4-no_robots_instructions", "repoId": "mrm8488/mistral-7b-ft-h4-no_robots_instructions", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.657018+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1bc7cd91a3c4445c8370d41314040bd5", "lastModified": "2026-10-15T13:48:47+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/Qwen3-Great-Bowels-Of-Horror-FREAKSTORM-6B", "repoId": "DavidAU/Qwen3-Great-Bowels-Of-Horror-FREAKSTORM-6B", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.657067+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bd93f5c4dd684a9daf0596e128b76639", "lastModified": "2026-10-15T23:21:49+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-3.7B-FP8", "repoId": "IFM/Jais-3-3.7B-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.657115+00:00", "framework": "vllm_tokenizer_patch", "intentId": "c41622314e4b4e2fb9bf89db502e1808", "lastModified": "2026-10-15T23:24:49+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-7B-FP8", "repoId": "IFM/Jais-3-7B-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.657164+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e170a04aa8794153b1fe6fbd5017837c", "lastModified": "2026-10-15T14:01:42+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "repoId": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.657222+00:00", "framework": "vllm_tokenizer_patch", "intentId": "47bab08683774217bb9147ea90f347e1", "lastModified": "2026-10-15T14:05:57+00:00", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Diplodocus-preview-JANG_6M", "repoId": "OsaurusAI/Diplodocus-preview-JANG_6M", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "28f29efa87104c56926e79f29fead68c", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:26:40.657270+00:00", "framework": "vllm_tokenizer_patch", "intentId": "a254e80aa06f4cb284532f13a9de5908", "lastModified": "2026-10-15T15:33:45+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "repoId": "DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "296f3eb635384474be03ba19e9c964fe", "completedAt": "2026-10-16T05:18:31.217737+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T04:54:58.900377+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9c9ea45e8967477d82dc0af96d8c1496", "repoId": "DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "296f3eb635384474be03ba19e9c964fe", "completedAt": "2026-10-16T05:18:31.217737+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T04:54:58.900377+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9c9ea45e8967477d82dc0af96d8c1496", "repoId": "DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "296f3eb635384474be03ba19e9c964fe", "completedAt": "2026-10-16T05:18:31.217734+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T04:54:58.900328+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bd0db128e4074878a0a32ef46cddba09", "repoId": "OsaurusAI/Diplodocus-preview-JANG_6M", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "296f3eb635384474be03ba19e9c964fe", "completedAt": "2026-10-16T05:18:31.217734+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T04:54:58.900328+00:00", "framework": "vllm_tokenizer_patch", "intentId": "bd0db128e4074878a0a32ef46cddba09", "repoId": "OsaurusAI/Diplodocus-preview-JANG_6M", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "296f3eb635384474be03ba19e9c964fe", "completedAt": "2026-10-16T05:18:31.217731+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T04:54:58.900279+00:00", "framework": "vllm_tokenizer_patch", "intentId": "03b6d17b8a6242798ac6d88cb049c6bc", "repoId": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "296f3eb635384474be03ba19e9c964fe", "completedAt": "2026-10-16T05:18:31.217731+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T04:54:58.900279+00:00", "framework": "vllm_tokenizer_patch", "intentId": "03b6d17b8a6242798ac6d88cb049c6bc", "repoId": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "9afcfdb2eb7774dbfebcdf5a9d95f436393fcf886115c919e1f73a96360a5603", ".modelhub_state/account_capacity.json": "9afcfdb2eb7774dbfebcdf5a9d95f436393fcf886115c919e1f73a96360a5603",
".modelhub_state/architecture_compatibility_blacklist.json": "5c06597c4a330731179190fec036d23eecaa569840df9c918f892442b077f30d", ".modelhub_state/architecture_compatibility_blacklist.json": "531c8b03ae06a5591998715af00b8ba2580855433550fb08e171d344ebc2f2bf",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "904c0d836423cae5401be2be463e8a8ee75abb4a6fde3fa843be633e710e614b", ".modelhub_state/market_intelligence.json": "c9f2fc30e55bc6c4127e47011a13b9d6f8785a118d1b953fda4f061fa13c100a",
".modelhub_state/official_capabilities.json": "8bb9f1c6e0dd6fa49f7e4198db46108a399b9bdb2318e5d6cdfef697dccfdea0", ".modelhub_state/official_capabilities.json": "d17f8669474f2f3c3fb9263dfe89a8bf11470adb3196a45b51901d4821f0d7d0",
".modelhub_state/outcome_checkpoint.json": "5245e10ab23f961516cba50d0bad450f166f53ba872dbee1dc3cab41beebf8c8", ".modelhub_state/outcome_checkpoint.json": "01e87297c4920c0ece15c94c91f1a4c3334d35f56c7bf042b32bc42b08e4b11b",
".modelhub_state/queue_cleanup_latest.json": "7c0b1b5520f4b6a7571c7e40b71037196e6382971bfb5973626e31489b4fd6ff", ".modelhub_state/queue_cleanup_latest.json": "7c0b1b5520f4b6a7571c7e40b71037196e6382971bfb5973626e31489b4fd6ff",
".modelhub_state/recent_outcomes.jsonl": "530c3f3f681469cb91364456a0b40c6fcc13b4df04b6e2659e523f96bbbc2ce5", ".modelhub_state/recent_outcomes.jsonl": "530c3f3f681469cb91364456a0b40c6fcc13b4df04b6e2659e523f96bbbc2ce5",
".modelhub_state/recovery_active_tasks.jsonl": "1f0b5123e00156ac7bc2bd9de642748c5f1206b6fd18b04f355009db28275d8b", ".modelhub_state/recovery_active_tasks.jsonl": "1f0b5123e00156ac7bc2bd9de642748c5f1206b6fd18b04f355009db28275d8b",
".modelhub_state/recovery_intents.jsonl": "d89ca0a8435ef63e2cf05bad206c5bebaaa9b04dc6499ec436866f95ce6c4884", ".modelhub_state/recovery_intents.jsonl": "54ea7d93a17cd78310614e1870dff767ef55d69ef275d9dc02f6eca9ce99b736",
".modelhub_state/routing_intelligence.json": "c60abd300ed33b1c7e9c67d487deae89efc0bf5f8cf3ce3fef53ac9be55355f3", ".modelhub_state/routing_intelligence.json": "c60abd300ed33b1c7e9c67d487deae89efc0bf5f8cf3ce3fef53ac9be55355f3",
".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b", ".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b",
".modelhub_state/worker_crashes.jsonl": "c6b627ba4bfe6f0f89b6dfc017d052f3b1717feac7f9dd06d3003f04166819a9", ".modelhub_state/worker_crashes.jsonl": "c6b627ba4bfe6f0f89b6dfc017d052f3b1717feac7f9dd06d3003f04166819a9",
"ledger/submissions.jsonl": "927946e35dc3e3dfc424659c1341a26f0a0d5d94c313f2f3c2273161add6f787", "ledger/submissions.jsonl": "927946e35dc3e3dfc424659c1341a26f0a0d5d94c313f2f3c2273161add6f787",
"outcomes/submissions.jsonl": "c29fb7705bfabba6cee9bba3918064bea9714aa7d9c20446fde4e6ba382ecc55" "outcomes/submissions.jsonl": "ae6808044d40ec76f6188b44e05088869d208a2598c2fa2ae6b314e081bdf21f"
}, },
"generation": 25290, "generation": 25291,
"phase": "cycle", "phase": "intent",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-16T05:18:39.335522+00:00", "updatedAt": "2026-10-16T05:26:40.861074+00:00",
"writerId": "9b5b3ed8772344608455c7e3b71f5c9f" "writerId": "9b5b3ed8772344608455c7e3b71f5c9f"
} }

10
outcomes/submissions.jsonl
View File

@@ -11,7 +11,6 @@
{"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": "2026-09-06T22:04:22.613082+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": "2026-09-06T22:04:22.613054+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": "2026-09-06T22:43:37.806846+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": "2026-09-06T22:43:37.806846+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", "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": "2026-09-07T05:31:35.012291+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": "2026-09-07T05:31:35.012291+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": "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": "2026-09-07T17:31:43.302628+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": "2026-09-07T18:00:51.826326+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}
@@ -85,7 +84,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T19:09:56.106587+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "f0079c5722ce37ff9d929e5e96de8925a4670b711936f17faab5f7565f2ecb43", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 32173498806, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496536}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T10:59:43.480777+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4847964", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T19:09:56.106587+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "f0079c5722ce37ff9d929e5e96de8925a4670b711936f17faab5f7565f2ecb43", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 32173498806, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496536}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T10:59:43.480777+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4847964", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T20:39:18.216494+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "327b4fcce82afa7c692364047b27c53d2b6ae7a0f2522806938c3c935ae9a735", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 33955496529, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T12:34:59.173731+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849005", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T20:39:18.216494+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "327b4fcce82afa7c692364047b27c53d2b6ae7a0f2522806938c3c935ae9a735", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 33955496529, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T12:34:59.173731+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849005", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-16T21:51:28.830527+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T13:48:53.545119+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4893637", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-16T21:51:28.830527+00:00", "modelId": "Edge0/Edge0-8B-A1B-preview", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4563913288, "estimatedRequiredGiB": 5.138, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4597698253, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1268239776, "modelscopeTags": ["license:apache-2.0", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4597698253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T13:48:53.545119+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4893637", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-17T00:01:16.498610+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7276346365, "estimatedRequiredGiB": 8.156, "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": 7298158256, "modelscopeLicense": null, "modelscopeParams": 1959473664, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7298158256}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T15:56:24.313012+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4897428", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-17T02:10:59.211438+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T18:09:58.859804+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4900532", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-17T02:10:59.211438+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-16T18:09:58.859804+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4900532", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T17:21:23.552173+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "bb269a9a8b4c1eeb18e3ef78bedcf638c3d1821a581b2f17113cde2fcd8be6c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "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": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:19:02.317218+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4912678", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T17:21:23.552173+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "bb269a9a8b4c1eeb18e3ef78bedcf638c3d1821a581b2f17113cde2fcd8be6c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "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": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:19:02.317218+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4912678", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T17:42:14.260331+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7df61fc66119e362f4b324c308b44e18bd70c6e8415d3cf79ad822bc9e6377c3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "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": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:36:01.072109+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4912861", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-17T17:42:14.260331+00:00", "modelId": "RentedNoodle/Qwen3.8-27B-OrcaRouter-GSQ-RCO-IQ3_XXS-GGUF", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "7df61fc66119e362f4b324c308b44e18bd70c6e8415d3cf79ad822bc9e6377c3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629247648, "estimatedRequiredGiB": 25.142, "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": 22496243465, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27320697856, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:gguf", "task:text-generation", "custom_tag:qwen3", "custom_tag:qwen3.8", "custom_tag:orcarouter", "custom_tag:gsq", "custom_tag:rco", "custom_tag:gguf", "custom_tag:quantized", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-use", "custom_tag:16gb-vram", "custom_tag:image-text-to-text", "custom_tag:vision", "custom_tag:multimodal", "custom_tag:mmproj", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22496243465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-17T09:36:01.072109+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4912861", "taskType": "text-generation", "verifyResult": null}
@@ -101,7 +99,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T22:02:17.790796+00:00", "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "ec890c5fa72ce5b6a2dc821183a5c5a4672e35039ad1cfdbb4ec3edd6dfa8870", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T13:59:45.181269+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4935796", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-18T22:02:17.790796+00:00", "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "ec890c5fa72ce5b6a2dc821183a5c5a4672e35039ad1cfdbb4ec3edd6dfa8870", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-18T13:59:45.181269+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4935796", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T08:29:40.588024+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "6f6eecfdce8cb92ba7646b68356f539b9e3b22165c56b20ad43debc6f5797b02", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:19:16.727802+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4942012", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T08:29:40.588024+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "6f6eecfdce8cb92ba7646b68356f539b9e3b22165c56b20ad43debc6f5797b02", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:19:16.727802+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4942012", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T08:40:17.761417+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "27037ea4923276909ffec48c4aaf432c445fc1dc3338331f7fc62f1a8b8c7449", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:38:36.958172+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4942203", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T08:40:17.761417+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "27037ea4923276909ffec48c4aaf432c445fc1dc3338331f7fc62f1a8b8c7449", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:38:36.958172+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4942203", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-19T08:54:50.387340+00:00", "modelId": "prism-ml/Ternary-Bonsai-2-27B-mlx-2bit", "modelProfile": {"architectures": [], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8595477990, "estimatedRequiredGiB": 9.621, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "prism_hadamard_qwen35", "modelscopeFileSize": 8608734989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2589078768, "modelscopeTags": ["license:apache-2.0", "model_type:prism_hadamard_qwen35", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:mlx", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8608734989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:52:10.648321+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4942333", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-19T08:54:50.387371+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "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": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:52:10.650329+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4942335", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-19T08:54:50.387371+00:00", "modelId": "barozp/Qwen3.8-Whittle-MoE-27B-MLX-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15155811051, "estimatedRequiredGiB": 16.961, "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": 15176196372, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4210722304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-lm", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:reasoning", "custom_tag:opus-distill", "custom_tag:whittle", "custom_tag:expert-pruning", "custom_tag:moe", "custom_tag:router-healing", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15176196372}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:52:10.650329+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4942335", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T09:05:14.592097+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "542d431820ab22236d94f13de518d5b298cdcf7ff50b3161b528640bca46f3cb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:56:39.197981+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4942377", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T09:05:14.592097+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "542d431820ab22236d94f13de518d5b298cdcf7ff50b3161b528640bca46f3cb", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T00:56:39.197981+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4942377", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T09:47:25.992989+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "28c8d3558c2c4f5aa7066e89457573be5bb7c439ae2f59b7240a1c80c37520c2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T01:39:17.100253+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4943097", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T09:47:25.992989+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "28c8d3558c2c4f5aa7066e89457573be5bb7c439ae2f59b7240a1c80c37520c2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T01:39:17.100253+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4943097", "taskType": "text-generation", "verifyResult": null}
@@ -128,7 +125,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191874+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.636731+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981863", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191874+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.636731+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981863", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191909+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.639728+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981864", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191909+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 955857175}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.639728+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981864", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.192066+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.670108+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981870", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.192066+00:00", "modelId": "mlx-community/gemma-4-12B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9003966484, "estimatedRequiredGiB": 10.099, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 9036402901, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2463563824, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9036402901}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.670108+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981870", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191922+00:00", "modelId": "mlx-community/gemma-4-e2b-it-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5226595850, "estimatedRequiredGiB": 5.878, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 5259113427, "modelscopeLicense": "gemma", "modelscopeParams": 1141165347, "modelscopeTags": ["license:gemma", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5259113427}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.641997+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981867", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.192054+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37184031394, "estimatedRequiredGiB": 41.579, "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": 37204398600, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10061358960, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:mixed-precision", "custom_tag:qwen3.6", "custom_tag:agentic-search"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37204398600}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.613984+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981862", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.192054+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37184031394, "estimatedRequiredGiB": 41.579, "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": 37204398600, "modelscopeLicense": "apache-2.0", "modelscopeParams": 10061358960, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:mixed-precision", "custom_tag:qwen3.6", "custom_tag:agentic-search"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37204398600}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.613984+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981862", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191935+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.664252+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981866", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191935+00:00", "modelId": "mlx-community/gemma-4-31B-it-qat-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23524076260, "estimatedRequiredGiB": 26.327, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 23556606333, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6649116524, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:qat", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:image-text-to-text", "custom_tag:gemma-4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 23556606333}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.664252+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981866", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191969+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25593158704, "estimatedRequiredGiB": 28.626, "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": 25613691403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7626590448, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25613691403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.612449+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981865", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T00:08:58.191969+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25593158704, "estimatedRequiredGiB": 28.626, "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": 25613691403, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7626590448, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25613691403}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T15:58:54.612449+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4981865", "taskType": "text-generation", "verifyResult": null}
@@ -1099,9 +1095,9 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-15T03:47:59.040100+00:00", "modelId": "bartowski/morriszjm_Tacit-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1c250a594d113141f46957bb17f760946db8515ce4008372f6e127c649570540", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1071921632, "estimatedRequiredGiB": 29.547, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 26438010496, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:decision-making", "custom_tag:self-distillation", "custom_tag:anyjev"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26438010496}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-14T19:38:29.050226+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5543365", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-15T03:47:59.040100+00:00", "modelId": "bartowski/morriszjm_Tacit-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1c250a594d113141f46957bb17f760946db8515ce4008372f6e127c649570540", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1071921632, "estimatedRequiredGiB": 29.547, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 26438010496, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:decision-making", "custom_tag:self-distillation", "custom_tag:anyjev"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 26438010496}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-14T19:38:29.050226+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5543365", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-16T04:25:26.240608+00:00", "modelId": "BananaMind/Picolo-BananaMind", "modelProfile": {"architectures": ["PicoloForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 912, "estimatedRequiredGiB": 0.001, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "picolo", "modelscopeFileSize": 638936, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:picolo", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:custom_code", "custom_tag:transformer", "custom_tag:tiny", "custom_tag:bananamind", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 638936}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T19:52:31.960607+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5568494", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-16T04:25:26.240608+00:00", "modelId": "BananaMind/Picolo-BananaMind", "modelProfile": {"architectures": ["PicoloForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 912, "estimatedRequiredGiB": 0.001, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "picolo", "modelscopeFileSize": 638936, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:picolo", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:custom_code", "custom_tag:transformer", "custom_tag:tiny", "custom_tag:bananamind", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 638936}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T19:52:31.960607+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5568494", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "DavidAU/DarkSapling-V2-Ultra-Quality-7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "a7159961e1848fd33948f09e6020f02399009945e81bc356b0f9fcd8e43bdd29", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8080881376, "estimatedRequiredGiB": 55.473, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 49636846090, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:creative", "custom_tag:story", "custom_tag:roleplay", "custom_tag:rp", "custom_tag:32 bit upscale", "custom_tag:remastered", "custom_tag:writing", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 49636846090}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-15T20:46:16.830124+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5569369", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "DavidAU/DarkSapling-V2-Ultra-Quality-7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "a7159961e1848fd33948f09e6020f02399009945e81bc356b0f9fcd8e43bdd29", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8080881376, "estimatedRequiredGiB": 55.473, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 49636846090, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:creative", "custom_tag:story", "custom_tag:roleplay", "custom_tag:rp", "custom_tag:32 bit upscale", "custom_tag:remastered", "custom_tag:writing", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 49636846090}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-15T20:46:16.830124+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5569369", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "DavidAU/Qwen3-4B-NEO-Imatrix-Max-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "500aac2acca120ff27483a2e8af08c8fa9158e7c0243b8c4d8959c0767ee5aa8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4645051776, "estimatedRequiredGiB": 59.323, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 53081207807, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:NEO Imatrix", "custom_tag:32 k context", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:qwen3", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53081207807}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-15T21:05:38.663754+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5569446", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-16T05:23:47.560344+00:00", "modelId": "DavidAU/Qwen3-4B-NEO-Imatrix-Max-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "500aac2acca120ff27483a2e8af08c8fa9158e7c0243b8c4d8959c0767ee5aa8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4645051776, "estimatedRequiredGiB": 59.323, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 53081207807, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:NEO Imatrix", "custom_tag:32 k context", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:qwen3", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53081207807}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T21:05:38.663754+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5569446", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "24a2d6b7ec33b5b33490e8c32fc08d8f540fe0fc4a02ad4f6b5454302b27d53e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5058317248, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 27199896379, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:256k context", "custom_tag:Qwen3", "custom_tag:All use cases", "custom_tag:creative", "custom_tag:creative writing", "custom_tag:fiction writing", "custom_tag:plot generation", "custom_tag:sub-plot generation", "custom_tag:story generation", "custom_tag:scene continue", "custom_tag:storytelling", "custom_tag:fiction story", "custom_tag:science fiction", "custom_tag:romance", "custom_tag:all genres", "custom_tag:story", "custom_tag:writing", "custom_tag:vivid prosing", "custom_tag:vivid writing", "custom_tag:fiction", "custom_tag:roleplaying", "custom_tag:bfloat16", "custom_tag:Neo Imatrix Max", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 27199896379}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-15T21:05:38.661525+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5569445", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-16T05:23:47.560303+00:00", "modelId": "DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "24a2d6b7ec33b5b33490e8c32fc08d8f540fe0fc4a02ad4f6b5454302b27d53e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5058317248, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 27199896379, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:256k context", "custom_tag:Qwen3", "custom_tag:All use cases", "custom_tag:creative", "custom_tag:creative writing", "custom_tag:fiction writing", "custom_tag:plot generation", "custom_tag:sub-plot generation", "custom_tag:story generation", "custom_tag:scene continue", "custom_tag:storytelling", "custom_tag:fiction story", "custom_tag:science fiction", "custom_tag:romance", "custom_tag:all genres", "custom_tag:story", "custom_tag:writing", "custom_tag:vivid prosing", "custom_tag:vivid writing", "custom_tag:fiction", "custom_tag:roleplaying", "custom_tag:bfloat16", "custom_tag:Neo Imatrix Max", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 27199896379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T21:05:38.661525+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5569445", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "primitive-ai/LFM2.5-24B-A2B-NVFP4A16", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14953608064, "estimatedRequiredGiB": 16.734, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 14973587440, "modelscopeLicense": "other", "modelscopeParams": 8153731584, "modelscopeTags": ["license:other", "model_type:lfm2_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:lfm2.5", "custom_tag:liquid", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14973587440}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-15T21:10:23.852106+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5569464", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-16T05:23:47.560327+00:00", "modelId": "primitive-ai/LFM2.5-24B-A2B-NVFP4A16", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14953608064, "estimatedRequiredGiB": 16.734, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 14973587440, "modelscopeLicense": "other", "modelscopeParams": 8153731584, "modelscopeTags": ["license:other", "model_type:lfm2_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:lfm2.5", "custom_tag:liquid", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14973587440}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T21:10:23.852106+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5569464", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "primitive-ai/LFM2.5-24B-A2B-NVFP4A16", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14953608064, "estimatedRequiredGiB": 16.734, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 14973587440, "modelscopeLicense": "other", "modelscopeParams": 8153731584, "modelscopeTags": ["license:other", "model_type:lfm2_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:lfm2.5", "custom_tag:liquid", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14973587440}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-15T21:35:37.282510+00:00", "targetGpu": "MetaX_c-500", "taskId": "5569757", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "primitive-ai/LFM2.5-24B-A2B-NVFP4A16", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14953608064, "estimatedRequiredGiB": 16.734, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 14973587440, "modelscopeLicense": "other", "modelscopeParams": 8153731584, "modelscopeTags": ["license:other", "model_type:lfm2_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:lfm2.5", "custom_tag:liquid", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14973587440}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-15T21:35:37.282510+00:00", "targetGpu": "MetaX_c-500", "taskId": "5569757", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "009fc97a918caf620bbf7e2f303f8358c81f71f6acbbaccb4b07beb42ed53fef", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3120573152, "estimatedRequiredGiB": 21.793, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 19499943240, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:12 reasoning modes", "custom_tag:12 instruct modes", "custom_tag:Turbo-Brilliance", "custom_tag:NEO Imatrix", "custom_tag:Max Quants", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19499943240}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-15T21:40:46.965193+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5570020", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "009fc97a918caf620bbf7e2f303f8358c81f71f6acbbaccb4b07beb42ed53fef", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3120573152, "estimatedRequiredGiB": 21.793, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 19499943240, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:12 reasoning modes", "custom_tag:12 instruct modes", "custom_tag:Turbo-Brilliance", "custom_tag:NEO Imatrix", "custom_tag:Max Quants", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19499943240}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-15T21:40:46.965193+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5570020", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "modelProfile": {"architectures": ["GaggleForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10579649968, "estimatedRequiredGiB": 23.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gaggle", "modelscopeFileSize": 21162857476, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:gaggle", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nanochat", "custom_tag:pretraining", "custom_tag:climbmix", "custom_tag:d34", "custom_tag:base-model", "custom_tag:custom_code", "custom_tag:vllm", "custom_tag:gaggle"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21162857476}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-16T00:19:38.082196+00:00", "targetGpu": "MetaX_c-500", "taskId": "5572093", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "modelProfile": {"architectures": ["GaggleForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10579649968, "estimatedRequiredGiB": 23.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gaggle", "modelscopeFileSize": 21162857476, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:gaggle", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nanochat", "custom_tag:pretraining", "custom_tag:climbmix", "custom_tag:d34", "custom_tag:base-model", "custom_tag:custom_code", "custom_tag:vllm", "custom_tag:gaggle"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21162857476}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-16T00:19:38.082196+00:00", "targetGpu": "MetaX_c-500", "taskId": "5572093", "taskType": "text-generation", "verifyResult": null}