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

state: generation 24214 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-13 06:42:51 +00:00
parent 063c43eae5
commit 0469363527
7 changed files with 2562 additions and 2564 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2769,7 +2769,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-13T06:20:04.743095+00:00", "generatedAt": "2026-10-13T06:36:23.302959+00:00",
"summary": { "summary": {
"activeBlockCount": 138, "activeBlockCount": 138,
"byGpuFramework": { "byGpuFramework": {

258
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-10-13T06:21:07.953851+00:00", "communityAttemptedAt": "2026-10-13T06:37:34.761272+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-10-13T06:21:07.953851+00:00", "communityUpdatedAt": "2026-10-13T06:37:34.761272+00:00",
"frameworkAttemptedAt": "2026-10-13T03:01:45.166994+00:00", "frameworkAttemptedAt": "2026-10-13T03:01:45.166994+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -414,99 +414,99 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-13T06:32:42.389860+00:00", "generatedAt": "2026-10-13T06:37:34.761272+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1202.3829787234042, "backlogHours": 1169.0068965517241,
"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": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.9663671272773877, "queueFactor": 0.9663691869109047,
"queueWeight": 0.9663671272773877, "queueWeight": 0.9663691869109047,
"recentSuccess": 46, "recentSuccess": 48,
"recentSuccessRate": 0.3262411347517731, "recentSuccessRate": 0.3310344827586207,
"recentTerminal": 141, "recentTerminal": 145,
"recentWilsonLowerBound": 0.25435688113492116, "recentWilsonLowerBound": 0.25966796165988626,
"running": 8, "running": 9,
"selectionWeight": 2.4159178181934693, "selectionWeight": 2.4159229672772615,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.5, "throughputPerHour": 24.166666666666668,
"waiting": 28256 "waiting": 28251
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 128.97540983606558, "backlogHours": 128.87704918032787,
"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": 0.8451716729836098, "qualityFactor": 0.8076072364612313,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 49, "recentSuccess": 49,
"recentSuccessRate": 0.20081967213114754, "recentSuccessRate": 0.20081967213114754,
"recentTerminal": 244, "recentTerminal": 244,
"recentWilsonLowerBound": 0.15536558342232454, "recentWilsonLowerBound": 0.15536558342232454,
"running": 8, "running": 9,
"selectionWeight": 1.0987231748786928, "selectionWeight": 1.0498894073996008,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 40.666666666666664, "throughputPerHour": 40.666666666666664,
"waiting": 5245 "waiting": 5241
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 957.173076923077, "backlogHours": 930.6168224299066,
"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": 0.48050826203053776, "qualityFactor": 0.495108007525965,
"queueFactor": 1.0, "queueFactor": 1.0,
"queueWeight": 1.0, "queueWeight": 1.0,
"recentSuccess": 19, "recentSuccess": 20,
"recentSuccessRate": 0.18269230769230768, "recentSuccessRate": 0.18691588785046728,
"recentTerminal": 104, "recentTerminal": 107,
"recentWilsonLowerBound": 0.12019329509173257, "recentWilsonLowerBound": 0.12438379319362988,
"running": 7, "running": 7,
"selectionWeight": 0.48050826203053776, "selectionWeight": 0.495108007525965,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.333333333333332, "throughputPerHour": 17.833333333333332,
"waiting": 16591 "waiting": 16596
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 396.6716417910448, "backlogHours": 393.68888888888887,
"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": 0.40328262017883143, "qualityFactor": 0.3789536589590297,
"queueFactor": 1.1412581661626628, "queueFactor": 1.137739041503393,
"queueWeight": 1.1412581661626628, "queueWeight": 1.137739041503393,
"recentSuccess": 22, "recentSuccess": 22,
"recentSuccessRate": 0.16417910447761194, "recentSuccessRate": 0.16296296296296298,
"recentTerminal": 134, "recentTerminal": 135,
"recentWilsonLowerBound": 0.11099240521268962, "recentWilsonLowerBound": 0.11015006965726473,
"running": 7, "running": 7,
"selectionWeight": 0.46024958355056683, "selectionWeight": 0.43115037271825013,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.333333333333332, "throughputPerHour": 22.5,
"waiting": 8859 "waiting": 8858
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 39.340336134453786, "backlogHours": 39.56448202959831,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -515,197 +515,197 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 23, "recentSuccess": 22,
"recentSuccessRate": 0.04831932773109244, "recentSuccessRate": 0.046511627906976744,
"recentTerminal": 476, "recentTerminal": 473,
"recentWilsonLowerBound": 0.03241041547357142, "recentWilsonLowerBound": 0.03091325796884337,
"running": 25, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 79.33333333333333, "throughputPerHour": 78.83333333333333,
"waiting": 3121 "waiting": 3119
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 178.18487394957984, "backlogHours": 175.11570247933884,
"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": 0.2989693667071629, "qualityFactor": 0.2981399716021876,
"queueFactor": 1.286820426281448, "queueFactor": 1.2847448079125328,
"queueWeight": 1.286820426281448, "queueWeight": 1.2847448079125328,
"recentSuccess": 32, "recentSuccess": 33,
"recentSuccessRate": 0.13445378151260504, "recentSuccessRate": 0.13636363636363635,
"recentTerminal": 238, "recentTerminal": 242,
"recentWilsonLowerBound": 0.09687465416891401, "recentWilsonLowerBound": 0.09877263510344331,
"running": 1, "running": 1,
"selectionWeight": 0.3847198879112059, "selectionWeight": 0.38303378054710047,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 39.666666666666664, "throughputPerHour": 40.333333333333336,
"waiting": 7068 "waiting": 7063
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2272.0975609756097, "backlogHours": 2272.5365853658536,
"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": 0.22568781884735437, "qualityFactor": 0.2156569150487957,
"queueFactor": 0.8783842193457866, "queueFactor": 0.8746594692874617,
"queueWeight": 0.8783842193457866, "queueWeight": 0.8746594692874617,
"recentSuccess": 7, "recentSuccess": 7,
"recentSuccessRate": 0.17073170731707318, "recentSuccessRate": 0.17073170731707318,
"recentTerminal": 41, "recentTerminal": 41,
"recentWilsonLowerBound": 0.08525143995273898, "recentWilsonLowerBound": 0.08525143995273898,
"running": 2, "running": 2,
"selectionWeight": 0.19824061857408667, "selectionWeight": 0.18862636286475087,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.833333333333333, "throughputPerHour": 6.833333333333333,
"waiting": 15526 "waiting": 15529
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 325.31612903225806, "backlogHours": 309.23926380368096,
"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": 0.5016231911997383, "qualityFactor": 0.38724142502679193,
"queueFactor": 1.1757168211857747, "queueFactor": 1.1796996219053322,
"queueWeight": 1.1757168211857747, "queueWeight": 1.1796996219053322,
"recentSuccess": 27, "recentSuccess": 26,
"recentSuccessRate": 0.17419354838709677, "recentSuccessRate": 0.15950920245398773,
"recentTerminal": 155, "recentTerminal": 163,
"recentWilsonLowerBound": 0.12256590380244957, "recentWilsonLowerBound": 0.11123860940055755,
"running": 8, "running": 9,
"selectionWeight": 0.5897668237904204, "selectionWeight": 0.45682856269018846,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.833333333333332, "throughputPerHour": 27.166666666666668,
"waiting": 8404 "waiting": 8401
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 540.3559322033898, "backlogHours": 535.6638655462185,
"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": 0.7575385622031537, "qualityFactor": 0.7885513582330068,
"queueFactor": 1.0895485388364718, "queueFactor": 1.086380051093226,
"queueWeight": 1.0895485388364718, "queueWeight": 1.086380051093226,
"recentSuccess": 25, "recentSuccess": 26,
"recentSuccessRate": 0.211864406779661, "recentSuccessRate": 0.2184873949579832,
"recentTerminal": 118, "recentTerminal": 119,
"recentWilsonLowerBound": 0.14782423635341965, "recentWilsonLowerBound": 0.15368839845214263,
"running": 4, "running": 5,
"selectionWeight": 0.8253750335607279, "selectionWeight": 0.8566664648468068,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 19.666666666666668, "throughputPerHour": 19.833333333333332,
"waiting": 10627 "waiting": 10624
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1966.421052631579, "backlogHours": 1992.56,
"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": 0.2713179443060585, "qualityFactor": 0.26713885311326735,
"queueFactor": 0.8976294523397006, "queueFactor": 0.8920802482549256,
"queueWeight": 0.8976294523397006, "queueWeight": 0.8920802482549256,
"recentSuccess": 12, "recentSuccess": 12,
"recentSuccessRate": 0.15789473684210525, "recentSuccessRate": 0.16,
"recentTerminal": 76, "recentTerminal": 75,
"recentWilsonLowerBound": 0.09269405994267452, "recentWilsonLowerBound": 0.09396421323774289,
"running": 4, "running": 4,
"selectionWeight": 0.24354297775738068, "selectionWeight": 0.23830929440381965,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.666666666666666, "throughputPerHour": 12.5,
"waiting": 24908 "waiting": 24907
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 1558.1470588235293, "backlogHours": 1513.5428571428572,
"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": 0.10742107181620263, "qualityFactor": 0.09617775080595899,
"queueFactor": 0.9295169304486397, "queueFactor": 0.9296434771270286,
"queueWeight": 0.9295169304486397, "queueWeight": 0.9296434771270286,
"recentSuccess": 8, "recentSuccess": 8,
"recentSuccessRate": 0.11764705882352941, "recentSuccessRate": 0.11428571428571428,
"recentTerminal": 68, "recentTerminal": 70,
"recentWilsonLowerBound": 0.06083419938921196, "recentWilsonLowerBound": 0.05906058386702606,
"running": 2, "running": 2,
"selectionWeight": 0.09984970494009955, "selectionWeight": 0.08941101868150858,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.333333333333334, "throughputPerHour": 11.666666666666666,
"waiting": 17659 "waiting": 17658
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1047.6923076923076, "backlogHours": 1036.0434782608695,
"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": 0.9865372948369783, "queueFactor": 0.9840313566011969,
"queueWeight": 0.9865372948369783, "queueWeight": 0.9840313566011969,
"recentSuccess": 6, "recentSuccess": 6,
"recentSuccessRate": 0.06593406593406594, "recentSuccessRate": 0.06521739130434782,
"recentTerminal": 91, "recentTerminal": 92,
"recentWilsonLowerBound": 0.030565869950639868, "recentWilsonLowerBound": 0.030229791373983947,
"running": 16, "running": 16,
"selectionWeight": 0.049326864741848914, "selectionWeight": 0.04920156783005985,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 15.166666666666666, "throughputPerHour": 15.333333333333334,
"waiting": 15890 "waiting": 15886
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 974.4090909090909, "backlogHours": 989.4923076923077,
"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": 0.9531278861328223, "qualityFactor": 0.7856412451460268,
"queueFactor": 0.9973265304121876, "queueFactor": 0.9908405494564788,
"queueWeight": 0.9973265304121876, "queueWeight": 0.9908405494564788,
"recentSuccess": 30, "recentSuccess": 28,
"recentSuccessRate": 0.22727272727272727, "recentSuccessRate": 0.2153846153846154,
"recentTerminal": 132, "recentTerminal": 130,
"recentWilsonLowerBound": 0.1640910639205752, "recentWilsonLowerBound": 0.15343032935030532,
"running": 6, "running": 6,
"selectionWeight": 0.9505797277159502, "selectionWeight": 0.7784452030161614,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.0, "throughputPerHour": 21.666666666666668,
"waiting": 21437 "waiting": 21439
} }
}, },
"queueAttemptedAt": "2026-10-13T06:27:03.067934+00:00", "queueAttemptedAt": "2026-10-13T06:37:34.761272+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-13T06:27:03.067934+00:00", "queueUpdatedAt": "2026-10-13T06:37:34.761272+00:00",
"supportedGpus": [ "supportedGpus": [
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",
"Vastai_va16", "Vastai_va16",

1518
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

1404
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1894
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

16
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "677b85568903dea095ca17b3f8e5ffd0ce5e168a7022026e27848574daa8a433", ".modelhub_state/architecture_compatibility_blacklist.json": "27769d30f3b844acb39b4859abbe89e24e9d445031dfcccd1f45991944092d60",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "14f601adf4eebb533d66075ac5a4e14874baf003819c2f052be625eef897cfab", ".modelhub_state/market_intelligence.json": "189fc78da32b9d7893b0443f16f6542e3c4b62ed0ec92c515ee6914cf7171523",
".modelhub_state/official_capabilities.json": "704f14295adf6154ff0191ee4f798f2f7e262323b5301b66d3d8b30e3f00a426", ".modelhub_state/official_capabilities.json": "df021d9c2f28c534116c17ee7d1946c61ae2b0b617f729393c8da91cfd0b40fa",
".modelhub_state/outcome_checkpoint.json": "1eb98d127eca02b41be09323863d8d5c0102cb4926b3f3e7cd1da06f2a79fcca", ".modelhub_state/outcome_checkpoint.json": "1eb98d127eca02b41be09323863d8d5c0102cb4926b3f3e7cd1da06f2a79fcca",
".modelhub_state/queue_cleanup_latest.json": "bc7e56c9d1a333f4bf796226c2496765a92f9d4ceb25f0ccd845d6f32075d0de", ".modelhub_state/queue_cleanup_latest.json": "bc7e56c9d1a333f4bf796226c2496765a92f9d4ceb25f0ccd845d6f32075d0de",
".modelhub_state/recent_outcomes.jsonl": "d5f3321c7c835be11fc790c6b04936eee563f577da3818cfa5dc8aa7c8332239", ".modelhub_state/recent_outcomes.jsonl": "d5f3321c7c835be11fc790c6b04936eee563f577da3818cfa5dc8aa7c8332239",
".modelhub_state/recovery_active_tasks.jsonl": "2e35581dffb88211e3435433118084d0aaf21d0753acec89bda5c46e4668c266", ".modelhub_state/recovery_active_tasks.jsonl": "9475456bc22f0631901742a4d76d206070e07dcc23ceb3ebef64f141dfebf04f",
".modelhub_state/recovery_intents.jsonl": "f0d2f0fcd792ff73826191d14a33076af3a5f68a7d1bf293071814387fd690a7", ".modelhub_state/recovery_intents.jsonl": "4c6c98423cb07d1aa40674b7cd48bac7ab5bcc5bea7712f0a7b62234d4b9da30",
".modelhub_state/routing_intelligence.json": "9dcfd476228791ce32b15a949c59e9dca1dd6ad861ec373ceada1f326223bd22", ".modelhub_state/routing_intelligence.json": "9dcfd476228791ce32b15a949c59e9dca1dd6ad861ec373ceada1f326223bd22",
".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b", ".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b",
".modelhub_state/worker_crashes.jsonl": "a6b56caed5c7afeb803f8701393cf4660f7e9799eb5ff84af826a142e16d9b00", ".modelhub_state/worker_crashes.jsonl": "a6b56caed5c7afeb803f8701393cf4660f7e9799eb5ff84af826a142e16d9b00",
"ledger/submissions.jsonl": "b555e0b9021a1b3a3cd8dc793093435e96a7adc9e5af62d8c9078dd7135c56b5", "ledger/submissions.jsonl": "b555e0b9021a1b3a3cd8dc793093435e96a7adc9e5af62d8c9078dd7135c56b5",
"outcomes/submissions.jsonl": "12cc137aa8b6dbd8bd4fb768bf8823528516b7d4448c1d9f42762645b08b4698" "outcomes/submissions.jsonl": "6e4ee79703984d29cddeb5c1910a12e0ce9b1a359adfb612486f790d93f10bed"
}, },
"generation": 24213, "generation": 24214,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-13T06:35:21.401395+00:00", "updatedAt": "2026-10-13T06:42:51.599276+00:00",
"writerId": "0b4d13138a434e929040a457f5ff8e93" "writerId": "0b4d13138a434e929040a457f5ff8e93"
} }

34
outcomes/submissions.jsonl
View File

@@ -926,23 +926,23 @@
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-13T05:20:08.353083+00:00", "modelId": "mlx-community/plamo-2-translate-bf16", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19056520807, "estimatedRequiredGiB": 21.309, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 19067261675, "modelscopeLicense": "other", "modelscopeParams": 9528235008, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:bf16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19067261675}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T21:18:07.078534+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5496561", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-13T05:20:08.353083+00:00", "modelId": "mlx-community/plamo-2-translate-bf16", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19056520807, "estimatedRequiredGiB": 21.309, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 19067261675, "modelscopeLicense": "other", "modelscopeParams": 9528235008, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:bf16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19067261675}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T21:18:07.078534+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5496561", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-13T05:40:32.155877+00:00", "modelId": "mlx-community/plamo-2-translate-8bit", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10124903941, "estimatedRequiredGiB": 11.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 10135674640, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10135674640}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T21:37:03.264403+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5496882", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-13T05:40:32.155877+00:00", "modelId": "mlx-community/plamo-2-translate-8bit", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10124903941, "estimatedRequiredGiB": 11.327, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 10135674640, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10135674640}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T21:37:03.264403+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5496882", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-13T05:40:32.155893+00:00", "modelId": "mlx-community/plamo-2-translate-bf16", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19056520807, "estimatedRequiredGiB": 21.309, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 19067261675, "modelscopeLicense": "other", "modelscopeParams": 9528235008, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:bf16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19067261675}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T21:37:03.262993+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5496883", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-13T05:40:32.155893+00:00", "modelId": "mlx-community/plamo-2-translate-bf16", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19056520807, "estimatedRequiredGiB": 21.309, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 19067261675, "modelscopeLicense": "other", "modelscopeParams": 9528235008, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:bf16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19067261675}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T21:37:03.262993+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5496883", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24604826824, "estimatedRequiredGiB": 27.524, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 24628378853, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20349011824, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:ascend", "custom_tag:ascend310p", "custom_tag:w4a8", "custom_tag:mtp", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"参数/模板问题": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-12T18:40:58.271114+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 24628378853}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.266627+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497673", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254843+00:00", "modelId": "ychy7001/Qwen3.6-35B-A3B-W4A8-SSZ-MTP-310P", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24604826824, "estimatedRequiredGiB": 27.524, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 24628378853, "modelscopeLicense": "apache-2.0", "modelscopeParams": 20349011824, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:ascend", "custom_tag:ascend310p", "custom_tag:w4a8", "custom_tag:mtp", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"参数/模板问题": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-12T18:40:58.271114+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 24628378853}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.266627+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497673", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/plamo-2-translate-8bit", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10124903941, "estimatedRequiredGiB": 11.327, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 10135674640, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10135674640}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.251467+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497669", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254872+00:00", "modelId": "mlx-community/plamo-2-translate-8bit", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10124903941, "estimatedRequiredGiB": 11.327, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 10135674640, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10135674640}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.251467+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497669", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/plamo-2-translate-bf16", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19056520807, "estimatedRequiredGiB": 21.309, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 19067261675, "modelscopeLicense": "other", "modelscopeParams": 9528235008, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:bf16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19067261675}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.263306+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497674", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254792+00:00", "modelId": "mlx-community/plamo-2-translate-bf16", "modelProfile": {"architectures": ["Plamo2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19056520807, "estimatedRequiredGiB": 21.309, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo2", "modelscopeFileSize": 19067261675, "modelscopeLicense": "other", "modelscopeParams": 9528235008, "modelscopeTags": ["license:other", "model_type:plamo2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:plamo", "custom_tag:translation", "custom_tag:custom_code", "custom_tag:bf16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19067261675}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.263306+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497674", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ManniX-ITA/Qwen3.6-27B-A3B-Coder", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53319307872, "estimatedRequiredGiB": 59.615, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 53342531046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26659587952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:code", "custom_tag:expert-pruning", "custom_tag:qwen3.6"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"参数/模板问题": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-12T18:40:58.271114+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 53342531046}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.256576+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497668", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254849+00:00", "modelId": "ManniX-ITA/Qwen3.6-27B-A3B-Coder", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53319307872, "estimatedRequiredGiB": 59.615, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 53342531046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26659587952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:code", "custom_tag:expert-pruning", "custom_tag:qwen3.6"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"参数/模板问题": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-12T18:40:58.271114+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 53342531046}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.256576+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497668", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/humanizer-12b-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8964644930, "estimatedRequiredGiB": 10.055, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 8997071286, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1009125399, "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:apple-silicon", "custom_tag:gemma4", "custom_tag:humanizer", "custom_tag:text-rewriting", "custom_tag:style-transfer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8997071286}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.249315+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497676", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254837+00:00", "modelId": "mlx-community/humanizer-12b-OptiQ-4bit", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8964644930, "estimatedRequiredGiB": 10.055, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 8997071286, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1009125399, "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:apple-silicon", "custom_tag:gemma4", "custom_tag:humanizer", "custom_tag:text-rewriting", "custom_tag:style-transfer"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8997071286}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.249315+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497676", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "yiku233/qwen2.5-coder-7b-nl2sql", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15715871392, "estimatedRequiredGiB": 17.582, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 15731820910, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:nl2sql", "custom_tag:text-to-sql", "custom_tag:lora", "custom_tag:distillation", "custom_tag:dpo", "custom_tag:qwen2_5_coder", "custom_tag:mysql", "custom_tag:agent"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15731820910}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.255444+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497672", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254825+00:00", "modelId": "yiku233/qwen2.5-coder-7b-nl2sql", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15715871392, "estimatedRequiredGiB": 17.582, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 15731820910, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:nl2sql", "custom_tag:text-to-sql", "custom_tag:lora", "custom_tag:distillation", "custom_tag:dpo", "custom_tag:qwen2_5_coder", "custom_tag:mysql", "custom_tag:agent"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15731820910}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.255444+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497672", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6627366288, "estimatedRequiredGiB": 7.43, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6648353931, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1727664128, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:finance", "custom_tag:k2_horizon", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6648353931}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.261756+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497677", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254831+00:00", "modelId": "OsaurusAI/Diplodocus-preview-7B-JANGH7", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6627366288, "estimatedRequiredGiB": 7.43, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6648353931, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1727664128, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:finance", "custom_tag:k2_horizon", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6648353931}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.261756+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497677", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "Akahsizrr/Cyber-Prime-1.2", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427448, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412820060, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-10T09:26:43.784462+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 5412820060}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.259469+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497678", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254799+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.2", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427448, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412820060, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-10T09:26:43.784462+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 5412820060}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.259469+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497678", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ConwayResearch/Underdog-Woof-2B-1.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426023876}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.264187+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497670", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254769+00:00", "modelId": "ConwayResearch/Underdog-Woof-2B-1.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426023876}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.264187+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497670", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ConwayResearch/woof-2B-mlx-4bit-v1.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:browser-use", "custom_tag:tool-use", "custom_tag:fine-tuned", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426024706}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.253896+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497675", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254812+00:00", "modelId": "ConwayResearch/woof-2B-mlx-4bit-v1.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1416035216, "estimatedRequiredGiB": 1.594, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:browser-use", "custom_tag:tool-use", "custom_tag:fine-tuned", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1426024706}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.253896+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497675", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ManniX-ITA/Qwen3.6-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429184344, "estimatedRequiredGiB": 58.619, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe_text", "modelscopeFileSize": 52451782841, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26213016704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:expert-pruning", "custom_tag:code", "custom_tag:mtp", "custom_tag:omnimergekit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 52451782841}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.250082+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497671", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254860+00:00", "modelId": "ManniX-ITA/Qwen3.6-27B-A3B-CoderX", "modelProfile": {"architectures": ["Qwen3_5MoeForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 52429184344, "estimatedRequiredGiB": 58.619, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe_text", "modelscopeFileSize": 52451782841, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26213016704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:expert-pruning", "custom_tag:code", "custom_tag:mtp", "custom_tag:omnimergekit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 52451782841}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.250082+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497671", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "h2oai/h2o-lightning-4b-nemotron-nano", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7947142672, "estimatedRequiredGiB": 8.901, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 7964754709, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-making", "custom_tag:calibration", "custom_tag:jevbench", "custom_tag:nemotron"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7964754709}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:27:23.252718+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497667", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254883+00:00", "modelId": "h2oai/h2o-lightning-4b-nemotron-nano", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7947142672, "estimatedRequiredGiB": 8.901, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 7964754709, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-making", "custom_tag:calibration", "custom_tag:jevbench", "custom_tag:nemotron"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7964754709}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:27:23.252718+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497667", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "JetBrains/Mellum2.1-12B-A2.5B-Thinking", "modelProfile": {"architectures": ["MellumForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24300538808, "estimatedRequiredGiB": 27.167, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mellum", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:mellum", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24308363631}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:28:35.950404+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497680", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254854+00:00", "modelId": "JetBrains/Mellum2.1-12B-A2.5B-Thinking", "modelProfile": {"architectures": ["MellumForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24300538808, "estimatedRequiredGiB": 27.167, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mellum", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:mellum", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24308363631}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:28:35.950404+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497680", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "JavaFamily/corvus-gov-3B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6425529048, "estimatedRequiredGiB": 7.2, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6442887386, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 3212749824, "modelscopeTags": ["license:Apache License 2.0", "model_type:llama3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:政衡", "custom_tag:政企大模型", "custom_tag:政务 AI 大模型", "custom_tag:JavaFamily", "custom_tag:微调", "custom_tag:LLaMA-Factory", "custom_tag:LoRA", "custom_tag:SFT", "custom_tag:政务领域", "custom_tag:中文对话"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6442887386}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:28:35.954524+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497679", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254867+00:00", "modelId": "JavaFamily/corvus-gov-3B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6425529048, "estimatedRequiredGiB": 7.2, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6442887386, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": 3212749824, "modelscopeTags": ["license:Apache License 2.0", "model_type:llama3", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:政衡", "custom_tag:政企大模型", "custom_tag:政务 AI 大模型", "custom_tag:JavaFamily", "custom_tag:微调", "custom_tag:LLaMA-Factory", "custom_tag:LoRA", "custom_tag:SFT", "custom_tag:政务领域", "custom_tag:中文对话"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6442887386}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:28:35.954524+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497679", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "ddalcu/Qwen3.6-35B-A3B-MLX-Serve-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20877335295, "estimatedRequiredGiB": 23.362, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20904301636, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5_moe", "custom_tag:moe", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"参数/模板问题": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-12T18:40:58.271114+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 20904301636}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:28:36.043520+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497683", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254819+00:00", "modelId": "ddalcu/Qwen3.6-35B-A3B-MLX-Serve-4bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20877335295, "estimatedRequiredGiB": 23.362, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20904301636, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5_moe", "custom_tag:moe", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"参数/模板问题": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-12T18:40:58.271114+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 20904301636}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:28:36.043520+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497683", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "tsinghua-sigs-robot-lab/VeriLoop-E2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 55655301924, "estimatedRequiredGiB": 62.227, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 55679383091, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27872753616, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "task:text-generation", "custom_tag:conversational", "custom_tag:veriloop", "custom_tag:post-training", "custom_tag:coding-agent", "custom_tag:software-engineering", "custom_tag:mathematical-reasoning", "custom_tag:scientific-reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:safetensors", "custom_tag:vllm", "custom_tag:apache-2.0"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 55679383091}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:28:35.975428+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497681", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254805+00:00", "modelId": "tsinghua-sigs-robot-lab/VeriLoop-E2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 55655301924, "estimatedRequiredGiB": 62.227, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 55679383091, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27872753616, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "task:text-generation", "custom_tag:conversational", "custom_tag:veriloop", "custom_tag:post-training", "custom_tag:coding-agent", "custom_tag:software-engineering", "custom_tag:mathematical-reasoning", "custom_tag:scientific-reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:safetensors", "custom_tag:vllm", "custom_tag:apache-2.0"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 55679383091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:28:35.975428+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497681", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "jialinyyzz/humanizer", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23919549408, "estimatedRequiredGiB": 97.901, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 11959730224, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:transformer", "library:gguf", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:humanizer", "custom_tag:transformers", "custom_tag:safetensors", "custom_tag:text-rewriting", "custom_tag:rewriting", "custom_tag:paraphrase", "custom_tag:style-transfer", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:gemma4", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 87599900314}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-12T22:28:35.966416+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497682", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-13T06:36:23.254878+00:00", "modelId": "jialinyyzz/humanizer", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23919549408, "estimatedRequiredGiB": 97.901, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 11959730224, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:transformer", "library:gguf", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:humanizer", "custom_tag:transformers", "custom_tag:safetensors", "custom_tag:text-rewriting", "custom_tag:rewriting", "custom_tag:paraphrase", "custom_tag:style-transfer", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:gemma4", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 87599900314}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-12T22:28:35.966416+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5497682", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "juspay/Xor-26B-A4B", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51612009332, "estimatedRequiredGiB": 57.717, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 51644403765, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144311217, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-model", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 51644403765}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T00:12:55.754334+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5499070", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "juspay/Xor-26B-A4B", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 51612009332, "estimatedRequiredGiB": 57.717, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 51644403765, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144311217, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-model", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 51644403765}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T00:12:55.754334+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5499070", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T00:12:55.758955+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5499072", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T00:12:55.758955+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5499072", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "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": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T00:12:55.762998+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5499071", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "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": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-13T00:12:55.762998+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5499071", "taskType": "text-generation", "verifyResult": null}