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

state: generation 21906 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 15:59:18 +00:00
parent 0267dfd07c
commit 92a5b6df81
10 changed files with 2018 additions and 2019 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2777,7 +2777,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-07T15:45:26.248350+00:00", "generatedAt": "2026-10-07T15:52:49.258010+00:00",
"summary": { "summary": {
"activeBlockCount": 140, "activeBlockCount": 140,
"byGpuFramework": { "byGpuFramework": {

274
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-10-07T15:38:02.565344+00:00", "communityAttemptedAt": "2026-10-07T15:57:04.262702+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-10-07T15:38:02.565344+00:00", "communityUpdatedAt": "2026-10-07T15:57:04.262702+00:00",
"frameworkAttemptedAt": "2026-10-07T14:52:53.254460+00:00", "frameworkAttemptedAt": "2026-10-07T14:52:53.254460+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -434,121 +434,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-07T15:51:46.564157+00:00", "generatedAt": "2026-10-07T15:57:04.262702+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1089.8543046357615, "backlogHours": 1127.0958904109589,
"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": 1.1884158002091414, "qualityFactor": 0.9928259697594066,
"queueFactor": 0.997470083716135, "queueFactor": 0.9899985142292587,
"queueWeight": 0.997470083716135, "queueWeight": 0.9899985142292587,
"recentSuccess": 37, "recentSuccess": 35,
"recentSuccessRate": 0.24503311258278146, "recentSuccessRate": 0.23972602739726026,
"recentTerminal": 151, "recentTerminal": 146,
"recentWilsonLowerBound": 0.1833173565388925, "recentWilsonLowerBound": 0.1777170167737743,
"running": 9, "running": 8,
"selectionWeight": 1.1854092077241898, "selectionWeight": 0.9828962349500354,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.166666666666668, "throughputPerHour": 24.333333333333332,
"waiting": 27428 "waiting": 27426
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1257.986013986014, "backlogHours": 1232.054794520548,
"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": 0.9762336509659156, "queueFactor": 0.976864144594243,
"queueWeight": 0.9762336509659156, "queueWeight": 0.976864144594243,
"recentSuccess": 47, "recentSuccess": 50,
"recentSuccessRate": 0.32867132867132864, "recentSuccessRate": 0.3424657534246575,
"recentTerminal": 143, "recentTerminal": 146,
"recentWilsonLowerBound": 0.2570448191429695, "recentWilsonLowerBound": 0.27041584886057934,
"running": 8, "running": 8,
"selectionWeight": 2.4405841274147893, "selectionWeight": 2.4421603614856076,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.833333333333332, "throughputPerHour": 24.333333333333332,
"waiting": 29982 "waiting": 29980
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 152.6860465116279, "backlogHours": 157.2574850299401,
"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": 0.8845060767058067, "qualityFactor": 0.8457817540852562,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 37, "recentSuccess": 37,
"recentSuccessRate": 0.21511627906976744, "recentSuccessRate": 0.2215568862275449,
"recentTerminal": 172, "recentTerminal": 167,
"recentWilsonLowerBound": 0.16028767638500904, "recentWilsonLowerBound": 0.1652288635924317,
"running": 8, "running": 8,
"selectionWeight": 1.1498578997175488, "selectionWeight": 1.0995162803108331,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 28.666666666666668, "throughputPerHour": 27.833333333333332,
"waiting": 4377 "waiting": 4377
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1079.5578947368422, "backlogHours": 1035.6969696969697,
"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": 0.3591671909229472, "qualityFactor": 0.3460219891089481,
"queueFactor": 0.9988913562552175, "queueFactor": 1.0026370916930805,
"queueWeight": 0.9988913562552175, "queueWeight": 1.0026370916930805,
"recentSuccess": 16, "recentSuccess": 17,
"recentSuccessRate": 0.16842105263157894, "recentSuccessRate": 0.1717171717171717,
"recentTerminal": 95, "recentTerminal": 99,
"recentWilsonLowerBound": 0.10641164331368241, "recentWilsonLowerBound": 0.11006570016266973,
"running": 7, "running": 7,
"selectionWeight": 0.3587690024633994, "selectionWeight": 0.3469344808220505,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.833333333333334, "throughputPerHour": 16.5,
"waiting": 17093 "waiting": 17089
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 408.3478260869565, "backlogHours": 408.17391304347825,
"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": 1.2618676440538272, "qualityFactor": 1.0462289998567718,
"queueFactor": 1.1557146234797242, "queueFactor": 1.152927202092229,
"queueWeight": 1.1557146234797242, "queueWeight": 1.152927202092229,
"recentSuccess": 35, "recentSuccess": 34,
"recentSuccessRate": 0.2536231884057971, "recentSuccessRate": 0.2463768115942029,
"recentTerminal": 138, "recentTerminal": 138,
"recentWilsonLowerBound": 0.18838329918622307, "recentWilsonLowerBound": 0.18200007681875943,
"running": 7, "running": 7,
"selectionWeight": 1.4583588891289156, "selectionWeight": 1.206225873552619,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.0, "throughputPerHour": 23.0,
"waiting": 9392 "waiting": 9388
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 78.7764705882353, "backlogHours": 87.37991266375546,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -557,104 +557,104 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 8, "recentSuccess": 7,
"recentSuccessRate": 0.03137254901960784, "recentSuccessRate": 0.03056768558951965,
"recentTerminal": 255, "recentTerminal": 229,
"recentWilsonLowerBound": 0.015980822787297944, "recentWilsonLowerBound": 0.014884149314845559,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 42.5, "throughputPerHour": 38.166666666666664,
"waiting": 3348 "waiting": 3335
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 152.01581027667984, "backlogHours": 171.66964285714283,
"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": 0.6128846727410032, "qualityFactor": 0.7210057744548042,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 45, "recentSuccess": 45,
"recentSuccessRate": 0.17786561264822134, "recentSuccessRate": 0.20089285714285715,
"recentTerminal": 253, "recentTerminal": 224,
"recentWilsonLowerBound": 0.13566912211916946, "recentWilsonLowerBound": 0.15366572909674223,
"running": 2, "running": 3,
"selectionWeight": 0.7967500745633043, "selectionWeight": 0.9373075067912454,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 42.166666666666664, "throughputPerHour": 37.333333333333336,
"waiting": 6410 "waiting": 6409
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 1724.6666666666667, "backlogHours": 1757.2075471698113,
"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": 0.5765567340975877, "qualityFactor": 0.5382424343779434,
"queueFactor": 0.9311065253287378, "queueFactor": 0.9262009322214696,
"queueWeight": 0.9311065253287378, "queueWeight": 0.9262009322214696,
"recentSuccess": 12, "recentSuccess": 12,
"recentSuccessRate": 0.2222222222222222, "recentSuccessRate": 0.22641509433962265,
"recentTerminal": 54, "recentTerminal": 53,
"recentWilsonLowerBound": 0.13195287989578958, "recentWilsonLowerBound": 0.13454499977265524,
"running": 2, "running": 2,
"selectionWeight": 0.5368357373404898, "selectionWeight": 0.49852064448200434,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 9.0, "throughputPerHour": 8.833333333333334,
"waiting": 15522 "waiting": 15522
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 381.041095890411, "backlogHours": 389.03496503496507,
"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": 0.32485339270936175, "qualityFactor": 0.3044557950948112,
"queueFactor": 1.167775536533156, "queueFactor": 1.161262434597684,
"queueWeight": 1.167775536533156, "queueWeight": 1.161262434597684,
"recentSuccess": 22, "recentSuccess": 22,
"recentSuccessRate": 0.1506849315068493, "recentSuccessRate": 0.15384615384615385,
"recentTerminal": 146, "recentTerminal": 143,
"recentWilsonLowerBound": 0.1016638993381026, "recentWilsonLowerBound": 0.103845722608873,
"running": 8, "running": 8,
"selectionWeight": 0.37935584496579094, "selectionWeight": 0.35355307783917406,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.333333333333332, "throughputPerHour": 23.833333333333332,
"waiting": 9272 "waiting": 9272
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 586.9821428571428, "backlogHours": 566.4827586206897,
"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": 1.237963512954311, "qualityFactor": 1.2194046342220963,
"queueFactor": 1.0944890281972648, "queueFactor": 1.0976166044820659,
"queueWeight": 1.0944890281972648, "queueWeight": 1.0976166044820659,
"recentSuccess": 29, "recentSuccess": 31,
"recentSuccessRate": 0.25892857142857145, "recentSuccessRate": 0.2672413793103448,
"recentTerminal": 112, "recentTerminal": 116,
"recentWilsonLowerBound": 0.18675273129699618, "recentWilsonLowerBound": 0.19512298408590828,
"running": 4, "running": 4,
"selectionWeight": 1.354937482237036, "selectionWeight": 1.338438774104553,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.666666666666668, "throughputPerHour": 19.333333333333332,
"waiting": 10957 "waiting": 10952
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
@@ -664,15 +664,15 @@
"gpu": "Mthreads_s4000", "gpu": "Mthreads_s4000",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 1.1703142038887768, "qualityFactor": 1.1811712603640234,
"queueFactor": 0.9441549102290453, "queueFactor": 0.9418175592035312,
"queueWeight": 0.9441549102290453, "queueWeight": 0.9418175592035312,
"recentSuccess": 22, "recentSuccess": 23,
"recentSuccessRate": 0.26506024096385544, "recentSuccessRate": 0.27710843373493976,
"recentTerminal": 83, "recentTerminal": 83,
"recentWilsonLowerBound": 0.18204284443216528, "recentWilsonLowerBound": 0.1923179435941366,
"running": 4, "running": 4,
"selectionWeight": 1.1049579021123848, "selectionWeight": 1.112447833437403,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 13.833333333333334, "throughputPerHour": 13.833333333333334,
@@ -680,74 +680,74 @@
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 2503.609756097561, "backlogHours": 2773.945945945946,
"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": 0.3296475965503226, "qualityFactor": 0.37283572065067505,
"queueFactor": 0.8804813278377704, "queueFactor": 0.8648961694440166,
"queueWeight": 0.8804813278377704, "queueWeight": 0.8648961694440166,
"recentSuccess": 8, "recentSuccess": 8,
"recentSuccessRate": 0.1951219512195122, "recentSuccessRate": 0.21621621621621623,
"recentTerminal": 41, "recentTerminal": 37,
"recentWilsonLowerBound": 0.1023431574920593, "recentWilsonLowerBound": 0.11386376851955585,
"running": 2, "running": 2,
"selectionWeight": 0.2902485535291577, "selectionWeight": 0.3224641866226683,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.833333333333333, "throughputPerHour": 6.166666666666667,
"waiting": 17108 "waiting": 17106
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1330.6753246753246, "backlogHours": 1365.76,
"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": 0.9680422895612887, "queueFactor": 0.9618835873051075,
"queueWeight": 0.9680422895612887, "queueWeight": 0.9618835873051075,
"recentSuccess": 0, "recentSuccess": 0,
"recentSuccessRate": 0.0, "recentSuccessRate": 0.0,
"recentTerminal": 77, "recentTerminal": 75,
"recentWilsonLowerBound": 3.3045785251705595e-18, "recentWilsonLowerBound": 0.0,
"running": 17, "running": 16,
"selectionWeight": 0.04840211447806444, "selectionWeight": 0.048094179365255375,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 12.833333333333334, "throughputPerHour": 12.5,
"waiting": 17077 "waiting": 17072
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 1063.65, "backlogHours": 1072.3865546218487,
"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": 1.0576577443709105, "qualityFactor": 0.7975352012528389,
"queueFactor": 1.0011181475914241, "queueFactor": 0.9974151687782413,
"queueWeight": 1.0011181475914241, "queueWeight": 0.9974151687782413,
"recentSuccess": 29, "recentSuccess": 27,
"recentSuccessRate": 0.24166666666666667, "recentSuccessRate": 0.226890756302521,
"recentTerminal": 120, "recentTerminal": 119,
"recentWilsonLowerBound": 0.1738573324150334, "recentWilsonLowerBound": 0.16087596514594535,
"running": 7, "running": 6,
"selectionWeight": 1.05884036183033, "selectionWeight": 0.795473707364189,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.0, "throughputPerHour": 19.833333333333332,
"waiting": 21273 "waiting": 21269
} }
}, },
"queueAttemptedAt": "2026-10-07T15:42:08.281724+00:00", "queueAttemptedAt": "2026-10-07T15:57:04.262702+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-07T15:42:08.281724+00:00", "queueUpdatedAt": "2026-10-07T15:57:04.262702+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{ {
"catalogUpdatedAt": "2026-10-07T15:51:46.564157+00:00", "catalogUpdatedAt": "2026-10-07T15:57:04.262702+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-10-07T15:51:46.564157+00:00", "generatedAt": "2026-10-07T15:57:04.262702+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6971,6 +6971,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-10-07T15:51:46.564157+00:00", "taskTreeUpdatedAt": "2026-10-07T15:57:04.262702+00:00",
"version": 1 "version": 1
} }

100
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-07T15:15:58.431781+00:00", "generatedAt": "2026-10-07T15:52:49.143323+00:00",
"lastSyncTime": "2026-10-07T15:15:58.161969+00:00", "lastSyncTime": "2026-10-07T15:52:48.873111+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -4083,10 +4083,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 9, "decisionTotal": 9,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 49, "ambiguous_runtime": 50,
"memory_capacity": 9 "memory_capacity": 9
}, },
"failureCount": 58, "failureCount": 59,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -4096,8 +4096,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 58, "total": 59,
"unresolvedFailureCount": 49 "unresolvedFailureCount": 50
}, },
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": { "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 10, "attributableFailureCount": 10,
@@ -5633,7 +5633,7 @@
"decisionSuccessRate": 0.0278, "decisionSuccessRate": 0.0278,
"decisionTotal": 180, "decisionTotal": 180,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 370, "ambiguous_runtime": 371,
"backend_operator": 9, "backend_operator": 9,
"framework_architecture_unsupported": 48, "framework_architecture_unsupported": 48,
"memory_capacity": 10, "memory_capacity": 10,
@@ -5642,15 +5642,15 @@
"tokenizer_compatibility": 95, "tokenizer_compatibility": 95,
"参数/模板问题": 13 "参数/模板问题": 13
}, },
"failureCount": 583, "failureCount": 584,
"failureRate": 0.9915, "failureRate": 0.9915,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 25, "platformFailureCount": 25,
"successCount": 5, "successCount": 5,
"successRate": 0.0085, "successRate": 0.0085,
"total": 588, "total": 589,
"unresolvedFailureCount": 383 "unresolvedFailureCount": 384
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"attributableFailureCount": 155, "attributableFailureCount": 155,
@@ -5681,7 +5681,7 @@
"unresolvedFailureCount": 257 "unresolvedFailureCount": 257
} }
}, },
"generatedAt": "2026-10-07T15:15:58.415601+00:00", "generatedAt": "2026-10-07T15:52:49.127412+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 119, "attributableFailureCount": 119,
@@ -5851,7 +5851,7 @@
"decisionSuccessRate": 0.1639, "decisionSuccessRate": 0.1639,
"decisionTotal": 915, "decisionTotal": 915,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 662, "ambiguous_runtime": 663,
"architecture_compatibility": 15, "architecture_compatibility": 15,
"backend_operator": 12, "backend_operator": 12,
"context_length": 29, "context_length": 29,
@@ -5866,15 +5866,15 @@
"日志缺失": 155, "日志缺失": 155,
"验证失败": 30 "验证失败": 30
}, },
"failureCount": 1954, "failureCount": 1955,
"failureRate": 0.9287, "failureRate": 0.9287,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 21, "platformFailureCount": 21,
"successCount": 150, "successCount": 150,
"successRate": 0.0713, "successRate": 0.0713,
"total": 2104, "total": 2105,
"unresolvedFailureCount": 1168 "unresolvedFailureCount": 1169
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"attributableFailureCount": 984, "attributableFailureCount": 984,
@@ -16465,9 +16465,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1 "ambiguous_runtime": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelType": "mini_k3", "modelType": "mini_k3",
@@ -16479,8 +16479,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 2
}, },
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors": { "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -25496,11 +25496,11 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 18, "ambiguous_runtime": 17,
"framework_architecture_unsupported": 1, "framework_architecture_unsupported": 1,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 20, "failureCount": 19,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-customized", "framework": "vllm-customized",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -25512,8 +25512,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 20, "total": 19,
"unresolvedFailureCount": 19 "unresolvedFailureCount": 18
}, },
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -25600,14 +25600,14 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 2,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 16, "ambiguous_runtime": 17,
"memory_capacity": 2 "memory_capacity": 2
}, },
"failureCount": 18, "failureCount": 19,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-07T13:29:11.757302+00:00", "lastTerminalAt": "2026-10-07T15:52:48.873111+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -25615,8 +25615,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 18, "total": 19,
"unresolvedFailureCount": 16 "unresolvedFailureCount": 17
}, },
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": { "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 7, "attributableFailureCount": 7,
@@ -26875,9 +26875,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 2 "ambiguous_runtime": 1
}, },
"failureCount": 2, "failureCount": 1,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-customized", "framework": "vllm-customized",
"lastTerminalAt": "2026-09-25T01:41:30.953868+00:00", "lastTerminalAt": "2026-09-25T01:41:30.953868+00:00",
@@ -26890,8 +26890,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 1,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 1
}, },
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|awq": { "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|awq": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -27575,12 +27575,12 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1 "ambiguous_runtime": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-07T13:29:11.757302+00:00", "lastTerminalAt": "2026-10-07T15:52:48.873111+00:00",
"modelType": "mini_k3", "modelType": "mini_k3",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
@@ -27590,8 +27590,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 2
}, },
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": { "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -45183,9 +45183,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1 "ambiguous_runtime": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30, "loadSizeLog2Bucket": 30,
@@ -45198,8 +45198,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 2
}, },
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors|34": { "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors|34": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -58305,15 +58305,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17407, "terminalRecords": 17408,
"totalRecords": 17664, "totalRecords": 17665,
"totals": { "totals": {
"attributableFailureCount": 6249, "attributableFailureCount": 6249,
"decisionFailureRate": 0.8647, "decisionFailureRate": 0.8647,
"decisionSuccessRate": 0.1353, "decisionSuccessRate": 0.1353,
"decisionTotal": 7227, "decisionTotal": 7227,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4567, "ambiguous_runtime": 4568,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 129, "backend_operator": 129,
@@ -58329,15 +58329,15 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16429, "failureCount": 16430,
"failureRate": 0.9438, "failureRate": 0.9438,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 952, "platformFailureCount": 952,
"successCount": 978, "successCount": 978,
"successRate": 0.0562, "successRate": 0.0562,
"total": 17407, "total": 17408,
"unresolvedFailureCount": 9228 "unresolvedFailureCount": 9229
}, },
"warnings": [ "warnings": [
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -58346,14 +58346,14 @@
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -58398,6 +58398,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17664, "summarizedRecords": 17665,
"version": 1 "version": 1
} }

14
.modelhub_state/queue_cleanup_latest.json
View File

@@ -14,13 +14,13 @@
100 100
], ],
"accounts": 12, "accounts": 12,
"activeScanned": 1134, "activeScanned": 1148,
"ageCleanupMode": "admission_only", "ageCleanupMode": "admission_only",
"agePolicySkipped": { "agePolicySkipped": {
"cleanupDisabled": true, "cleanupDisabled": true,
"reason": "admission_only" "reason": "admission_only"
}, },
"architectureBlockCount": 143, "architectureBlockCount": 140,
"architectureFrameworkCatalog": { "architectureFrameworkCatalog": {
"ascend_910-b3|text-generation": [ "ascend_910-b3|text-generation": [
"llamacpp", "llamacpp",
@@ -118,8 +118,8 @@
"architecturePolicySkipped": { "architecturePolicySkipped": {
"frameworkCatalogUnknown": 0, "frameworkCatalogUnknown": 0,
"frameworkContextUnknown": 44, "frameworkContextUnknown": 44,
"modelArchitectureUnknown": 159, "modelArchitectureUnknown": 163,
"noMatchingBlock": 959, "noMatchingBlock": 969,
"partiallyBlockedFrameworkSet": 16, "partiallyBlockedFrameworkSet": 16,
"runningMatchedProtected": 0, "runningMatchedProtected": 0,
"submissionContextMismatch": 0, "submissionContextMismatch": 0,
@@ -160,12 +160,12 @@
"recentModelDays": 7, "recentModelDays": 7,
"recentModelReserveSlots": 5, "recentModelReserveSlots": 5,
"repositorySizeErrors": {}, "repositorySizeErrors": {},
"repositorySizesComplete": 310, "repositorySizesComplete": 303,
"skipped": { "skipped": {
"fitsKnownCapacity": 1134, "fitsKnownCapacity": 1148,
"gpuCapacityUnknown": 0, "gpuCapacityUnknown": 0,
"repositorySizeUnknown": 0 "repositorySizeUnknown": 0
}, },
"stopErrors": [], "stopErrors": [],
"uniqueModels": 310 "uniqueModels": 303
} }

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -97,6 +97,7 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082798+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:32+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4850852", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082798+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:32+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4850852", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082807+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:32+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4881076", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082807+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:32+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4881076", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082789+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:31+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4925021", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082789+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:31+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4925021", "taskType": "text-generation", "verifyResult": null}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T15:52:48.873111+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:16:38.547857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006761", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T13:29:11.757302+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:12:49.394711+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006730", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T13:29:11.757302+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T20:12:49.394711+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006730", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-25T01:41:30.953868+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 4, "model_load": 1}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:49:53.770533+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-25T01:41:30.953868+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 4, "model_load": 1}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:49:53.770533+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164621+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.653471+00:00", "targetGpu": "Biren_166m", "taskId": "5006368", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164621+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:37:12.653471+00:00", "targetGpu": "Biren_166m", "taskId": "5006368", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-22T21:35:04.154848+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195521, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018195521}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:39:50.946521+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997284", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-22T21:35:04.154848+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195521, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018195521}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:39:50.946521+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997284", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T17:41:26.757140+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "5227b42f4cdd7539bb62412569c7d9c8b3cc2e321cdbac3654c73c95c5bc8a7b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:39:42.289781+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4997241", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-21T17:41:26.757140+00:00", "modelId": "aisingapore/SEA-LION-v1-7B-IT-GPTQ", "modelProfile": {"architectures": ["MPTForCausalLM"], "configFingerprint": "5227b42f4cdd7539bb62412569c7d9c8b3cc2e321cdbac3654c73c95c5bc8a7b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5469228368, "estimatedRequiredGiB": 6.118, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mpt", "modelscopeFileSize": 5473985594, "modelscopeLicense": "mit", "modelscopeParams": 1922048000, "modelscopeTags": ["license:mit", "model_type:mpt", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5473985594}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:39:42.289781+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4997241", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm-customized", "lastSyncTime": "2026-09-22T13:37:53.563484+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20628596944, "estimatedRequiredGiB": 23.076, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20647674585, "modelscopeLicense": "other", "modelscopeParams": 33943909952, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:int4", "custom_tag:int8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:mamba", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20647674585}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:37:39.043820+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4997240", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm-customized", "lastSyncTime": "2026-09-22T13:37:53.563484+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20628596944, "estimatedRequiredGiB": 23.076, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 20647674585, "modelscopeLicense": "other", "modelscopeParams": 33943909952, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:int4", "custom_tag:int8", "custom_tag:mixed-precision", "custom_tag:quantized", "custom_tag:moe", "custom_tag:mamba", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20647674585}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:37:39.043820+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4997240", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-23T20:20:35.755015+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T02:15:17.867294+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 663548868}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:37:38.921478+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4997218", "taskType": "text-generation", "verifyResult": -1}

1528
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2088
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

22
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": "f1b5f736632dcb74724b8e280efbd4d343843d0df2f717f79d6eac0cfefb4bbb", ".modelhub_state/architecture_compatibility_blacklist.json": "47564212b44ddc1cc17f9aee5e19557771bb2a11b0e3ea30f3bd01202696f080",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "b0f056d8b3c5efa451ea16fe22f15b85ed91ad924917fbd3c040e931fc96973c", ".modelhub_state/market_intelligence.json": "7a45522d5455f028cd62a682f6cccb5ade131132b872038b654d82af79a3c3fa",
".modelhub_state/official_capabilities.json": "f911afdb774799e436af54e338cf3722ebb65d5f13fe43d0456147fef9b1a465", ".modelhub_state/official_capabilities.json": "f8c96bb293605e771a89b36900873b2ed974f97274768750a3b8ca83a0a395f1",
".modelhub_state/outcome_checkpoint.json": "3a6e9143672cff023de7d9112c425ebeca55fe593e0317d151bb33a4d51f9e3c", ".modelhub_state/outcome_checkpoint.json": "824f31a16ae15a6cce52f879812e765ca65bfa66949d9538d6ad8fa7b13f2083",
".modelhub_state/queue_cleanup_latest.json": "7f569be3fbe746570a2cdb33f54784d130294aa154d93e9ad9102b01386bc4cf", ".modelhub_state/queue_cleanup_latest.json": "81db69056896fcc0282a683fe01164f1de86b8b4ba0258960890ab24480ee020",
".modelhub_state/recent_outcomes.jsonl": "05d617380af7c092742264100a493f9999568b46e43624a7370266e3fbdfbcf3", ".modelhub_state/recent_outcomes.jsonl": "9b5c9c191d8b07c797372b3a410151b196023d64e0997df5324139448143b794",
".modelhub_state/recovery_active_tasks.jsonl": "db1a9b131c972b1563dc3a78372a226e4d37564424b2da4fa2f953c05e3e1c04", ".modelhub_state/recovery_active_tasks.jsonl": "21a1b65dede28cfc2816a7815b9dd71cc7e69c6a7dcda6ee94d1d5728fa5ac41",
".modelhub_state/recovery_intents.jsonl": "d40942b9a96658d904d8ba7c9b95214bda0bbeaf728e262e99b5c52676e97513", ".modelhub_state/recovery_intents.jsonl": "8f5ac54afd45724b3527087cfdda4d190a61817346357ad997edc72d2b7b4349",
".modelhub_state/routing_intelligence.json": "e3daffbfe2a3390cee9130d34c9be6e58dc21d0039e08726c2eb991348872a68", ".modelhub_state/routing_intelligence.json": "e3daffbfe2a3390cee9130d34c9be6e58dc21d0039e08726c2eb991348872a68",
".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b", ".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f", ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "e3c6cfed4f11a26c05ff651ac81a8412c366303ee4cc87e5b11e2ce12fc7320a", "ledger/submissions.jsonl": "e3c6cfed4f11a26c05ff651ac81a8412c366303ee4cc87e5b11e2ce12fc7320a",
"outcomes/submissions.jsonl": "fefab8237731780019029ee74b5a8144c3368171ff98eaed689f0488dd179560" "outcomes/submissions.jsonl": "b55a6912411fc2e2ea3f602f8015ef9ba36b2170416784914dbfc38cdc90923d"
}, },
"generation": 21905, "generation": 21906,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-07T15:51:47.658130+00:00", "updatedAt": "2026-10-07T15:59:18.246510+00:00",
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2" "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
} }

1
outcomes/submissions.jsonl
View File

@@ -283,7 +283,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:53:42.966032+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030685704, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039047610}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:52:49.746330+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006515", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:53:42.966032+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g1-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030685704, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039047610}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:52:49.746330+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006515", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:57:41.559488+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2038896936, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042511760}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:57:33.047886+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006584", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:57:41.559488+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-32-v2_D", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2038896936, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042511760}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:57:33.047886+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006584", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:57:41.559509+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034915504, "estimatedRequiredGiB": 2.278, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2038530279}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:57:33.049384+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006585", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T03:57:41.559509+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-8-v2_D", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034915504, "estimatedRequiredGiB": 2.278, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2038530279}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:57:33.049384+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006585", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T04:17:30.357344+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:16:38.547857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006761", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T04:23:42.965205+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {"architectures": [], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2044205392, "estimatedRequiredGiB": 2.469, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2168994941, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2209448692}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:22:32.043790+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5006826", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T04:23:42.965205+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {"architectures": [], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2044205392, "estimatedRequiredGiB": 2.469, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2168994941, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2209448692}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:22:32.043790+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5006826", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T04:23:42.965223+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:22:32.047761+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006825", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T04:23:42.965223+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:22:32.047761+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006825", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T04:24:59.055270+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:24:44.145520+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006850", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T04:24:59.055270+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T20:24:44.145520+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5006850", "taskType": "text-generation", "verifyResult": null}