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

state: generation 21992 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 22:49:56 +00:00
parent 4a580f3139
commit 0e11ec6d21
8 changed files with 2310 additions and 1766 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2876,7 +2876,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-07T22:24:11.363488+00:00", "generatedAt": "2026-10-07T22:42:35.203757+00:00",
"summary": { "summary": {
"activeBlockCount": 145, "activeBlockCount": 145,
"byGpuFramework": { "byGpuFramework": {

270
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-10-07T22:25:31.762853+00:00", "communityAttemptedAt": "2026-10-07T22:44:02.054525+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-10-07T22:25:31.762853+00:00", "communityUpdatedAt": "2026-10-07T22:44:02.054525+00:00",
"frameworkAttemptedAt": "2026-10-07T20:58:42.772583+00:00", "frameworkAttemptedAt": "2026-10-07T20:58:42.772583+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -434,121 +434,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-07T22:39:04.850396+00:00", "generatedAt": "2026-10-07T22:44:02.054525+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 910.9, "backlogHours": 900.8571428571429,
"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": 0.5102863592697803, "qualityFactor": 0.4806723077770344,
"queueFactor": 0.9761392887736855, "queueFactor": 0.9763729733650891,
"queueWeight": 0.9761392887736855, "queueWeight": 0.9763729733650891,
"recentSuccess": 44, "recentSuccess": 43,
"recentSuccessRate": 0.24444444444444444, "recentSuccessRate": 0.23626373626373626,
"recentTerminal": 180, "recentTerminal": 182,
"recentWilsonLowerBound": 0.18743177857666718, "recentWilsonLowerBound": 0.18039889357479763,
"running": 8, "running": 8,
"selectionWeight": 0.49811056380851665, "selectionWeight": 0.46931545035852235,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 30.0, "throughputPerHour": 30.333333333333332,
"waiting": 27327 "waiting": 27326
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 821.6697247706421, "backlogHours": 806.8918918918919,
"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": 0.4131910436582119, "qualityFactor": 0.4740866155210215,
"queueFactor": 0.9913518140443913, "queueFactor": 0.9926401458331542,
"queueWeight": 0.9913518140443913, "queueWeight": 0.9926401458331542,
"recentSuccess": 48, "recentSuccess": 51,
"recentSuccessRate": 0.22018348623853212, "recentSuccessRate": 0.22972972972972974,
"recentTerminal": 218, "recentTerminal": 222,
"recentWilsonLowerBound": 0.17028570787929576, "recentWilsonLowerBound": 0.17927119039026004,
"running": 8, "running": 8,
"selectionWeight": 0.4096176906774637, "selectionWeight": 0.47059740716833326,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 36.333333333333336, "throughputPerHour": 37.0,
"waiting": 29854 "waiting": 29855
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 161.11111111111111, "backlogHours": 166.2420382165605,
"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": 0.33242123225582365, "qualityFactor": 0.33823665054151464,
"queueFactor": 1.265795579008244, "queueFactor": 1.2580647967932863,
"queueWeight": 1.265795579008244, "queueWeight": 1.2580647967932863,
"recentSuccess": 34, "recentSuccess": 33,
"recentSuccessRate": 0.20987654320987653, "recentSuccessRate": 0.21019108280254778,
"recentTerminal": 162, "recentTerminal": 157,
"recentWilsonLowerBound": 0.15425557210629545, "recentWilsonLowerBound": 0.1537649343190204,
"running": 8, "running": 8,
"selectionWeight": 0.42077732615789426, "selectionWeight": 0.4255236230315524,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 27.0, "throughputPerHour": 26.166666666666668,
"waiting": 4350 "waiting": 4350
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 830.6829268292682, "backlogHours": 824.0806451612902,
"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": 0.06865611309773165, "qualityFactor": 0.08258315853696135,
"queueFactor": 0.9897308460800707, "queueFactor": 0.9895065678786946,
"queueWeight": 0.9897308460800707, "queueWeight": 0.9895065678786946,
"recentSuccess": 15, "recentSuccess": 16,
"recentSuccessRate": 0.12195121951219512, "recentSuccessRate": 0.12903225806451613,
"recentTerminal": 123, "recentTerminal": 124,
"recentWilsonLowerBound": 0.07531350974500774, "recentWilsonLowerBound": 0.08100761827143554,
"running": 7, "running": 7,
"selectionWeight": 0.06795107290478697, "selectionWeight": 0.08171657776849076,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.5, "throughputPerHour": 20.666666666666668,
"waiting": 17029 "waiting": 17031
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 289.0880829015544, "backlogHours": 289.119170984456,
"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": 0.17596917231849082, "qualityFactor": 0.1654758260850891,
"queueFactor": 1.1595190016761285, "queueFactor": 1.1578508127292795,
"queueWeight": 1.1595190016761285, "queueWeight": 1.1578508127292795,
"recentSuccess": 31, "recentSuccess": 30,
"recentSuccessRate": 0.16062176165803108, "recentSuccessRate": 0.15544041450777202,
"recentTerminal": 193, "recentTerminal": 193,
"recentWilsonLowerBound": 0.11552386104400723, "recentWilsonLowerBound": 0.11110337669376555,
"running": 7, "running": 7,
"selectionWeight": 0.20403959901251112, "selectionWeight": 0.1915963197196693,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 32.166666666666664, "throughputPerHour": 32.166666666666664,
"waiting": 9299 "waiting": 9300
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 100.7872340425532, "backlogHours": 99.09375,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -558,196 +558,196 @@
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 6, "recentSuccess": 6,
"recentSuccessRate": 0.031914893617021274, "recentSuccessRate": 0.03125,
"recentTerminal": 188, "recentTerminal": 192,
"recentWilsonLowerBound": 0.01470714631681868, "recentWilsonLowerBound": 0.014399085841634563,
"running": 16, "running": 18,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 31.333333333333332, "throughputPerHour": 32.0,
"waiting": 3158 "waiting": 3171
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 239.59006211180125, "backlogHours": 249.0193548387097,
"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": 0.2429097361026568, "qualityFactor": 0.29558822210683783,
"queueFactor": 1.1926474347642146, "queueFactor": 1.1840748938154155,
"queueWeight": 1.1926474347642146, "queueWeight": 1.1840748938154155,
"recentSuccess": 30, "recentSuccess": 31,
"recentSuccessRate": 0.18633540372670807, "recentSuccessRate": 0.2,
"recentTerminal": 161, "recentTerminal": 155,
"recentWilsonLowerBound": 0.1337555605830833, "recentWilsonLowerBound": 0.1446275910955794,
"running": 5, "running": 5,
"selectionWeight": 0.28970567364208594, "selectionWeight": 0.34999859270424144,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.833333333333332, "throughputPerHour": 25.833333333333332,
"waiting": 6429 "waiting": 6433
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2446.5789473684213, "backlogHours": 2446.7368421052633,
"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": 0.6699591646565988, "qualityFactor": 0.6864739485420357,
"queueFactor": 0.8416829180607596, "queueFactor": 0.840477417645268,
"queueWeight": 0.8416829180607596, "queueWeight": 0.840477417645268,
"recentSuccess": 13, "recentSuccess": 13,
"recentSuccessRate": 0.34210526315789475, "recentSuccessRate": 0.34210526315789475,
"recentTerminal": 38, "recentTerminal": 38,
"recentWilsonLowerBound": 0.21212220026458956, "recentWilsonLowerBound": 0.21212220026458956,
"running": 2, "running": 2,
"selectionWeight": 0.5638931846897149, "selectionWeight": 0.5769658515513607,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.333333333333333, "throughputPerHour": 6.333333333333333,
"waiting": 15495 "waiting": 15496
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 387.2307692307692, "backlogHours": 374.02702702702703,
"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": 0.264723292897894, "qualityFactor": 0.3010641568196222,
"queueFactor": 1.109780065700231, "queueFactor": 1.1139833263170802,
"queueWeight": 1.109780065700231, "queueWeight": 1.1139833263170802,
"recentSuccess": 28, "recentSuccess": 30,
"recentSuccessRate": 0.1958041958041958, "recentSuccessRate": 0.20270270270270271,
"recentTerminal": 143, "recentTerminal": 148,
"recentWilsonLowerBound": 0.1390874232541636, "recentWilsonLowerBound": 0.14583936224518,
"running": 8, "running": 8,
"selectionWeight": 0.2937846333846063, "selectionWeight": 0.3353804508487698,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.833333333333332, "throughputPerHour": 24.666666666666668,
"waiting": 9229 "waiting": 9226
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 491.05263157894734, "backlogHours": 476.67153284671537,
"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": 0.06887220530165053, "qualityFactor": 0.07800719585185797,
"queueFactor": 1.0709351965555014, "queueFactor": 1.074190373005016,
"queueWeight": 1.0709351965555014, "queueWeight": 1.074190373005016,
"recentSuccess": 16, "recentSuccess": 17,
"recentSuccessRate": 0.12030075187969924, "recentSuccessRate": 0.12408759124087591,
"recentTerminal": 133, "recentTerminal": 137,
"recentWilsonLowerBound": 0.07542116562091343, "recentWilsonLowerBound": 0.07893557234581082,
"running": 4, "running": 4,
"selectionWeight": 0.07375766872193396, "selectionWeight": 0.08379457880918265,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.166666666666668, "throughputPerHour": 22.833333333333332,
"waiting": 10885 "waiting": 10884
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1866.1714285714286, "backlogHours": 1789.4794520547946,
"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": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.8765761860870709, "queueFactor": 0.8808564340997205,
"queueWeight": 0.8765761860870709, "queueWeight": 0.8808564340997205,
"recentSuccess": 35, "recentSuccess": 36,
"recentSuccessRate": 0.5, "recentSuccessRate": 0.4931506849315068,
"recentTerminal": 70, "recentTerminal": 73,
"recentWilsonLowerBound": 0.3859551898733622, "recentWilsonLowerBound": 0.38170665864691183,
"running": 4, "running": 4,
"selectionWeight": 2.1914404652176773, "selectionWeight": 2.202141085249301,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.666666666666666, "throughputPerHour": 12.166666666666666,
"waiting": 21772 "waiting": 21772
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 2773.297297297297, "backlogHours": 2773.459459459459,
"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": 0.05, "qualityFactor": 0.05,
"queueFactor": 0.8260054905927059, "queueFactor": 0.8248231944178874,
"queueWeight": 0.8260054905927059, "queueWeight": 0.8248231944178874,
"recentSuccess": 5, "recentSuccess": 5,
"recentSuccessRate": 0.13513513513513514, "recentSuccessRate": 0.13513513513513514,
"recentTerminal": 37, "recentTerminal": 37,
"recentWilsonLowerBound": 0.059132072625076235, "recentWilsonLowerBound": 0.059132072625076235,
"running": 2, "running": 2,
"selectionWeight": 0.0413002745296353, "selectionWeight": 0.04124115972089437,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.166666666666667, "throughputPerHour": 6.166666666666667,
"waiting": 17102 "waiting": 17103
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 729.2142857142858, "backlogHours": 729.3428571428572,
"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": 1.0092624679825277, "queueFactor": 1.0078000561469054,
"queueWeight": 1.0092624679825277, "queueWeight": 1.0078000561469054,
"recentSuccess": 2, "recentSuccess": 3,
"recentSuccessRate": 0.014285714285714285, "recentSuccessRate": 0.02142857142857143,
"recentTerminal": 140, "recentTerminal": 140,
"recentWilsonLowerBound": 0.003926358459994088, "recentWilsonLowerBound": 0.007313870780766548,
"running": 16, "running": 16,
"selectionWeight": 0.05046312339912639, "selectionWeight": 0.05039000280734527,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 23.333333333333332, "throughputPerHour": 23.333333333333332,
"waiting": 17015 "waiting": 17018
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 1169.1743119266055, "backlogHours": 1202.1509433962262,
"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": 0.32491619395381943, "qualityFactor": 0.35475350297888075,
"queueFactor": 0.9402655158484792, "queueFactor": 0.9350186814982492,
"queueWeight": 0.9402655158484792, "queueWeight": 0.9350186814982492,
"recentSuccess": 24, "recentSuccess": 24,
"recentSuccessRate": 0.22018348623853212, "recentSuccessRate": 0.22641509433962265,
"recentTerminal": 109, "recentTerminal": 106,
"recentWilsonLowerBound": 0.1526627048081528, "recentWilsonLowerBound": 0.1571336279648038,
"running": 6, "running": 6,
"selectionWeight": 0.30550749271551253, "selectionWeight": 0.3317011526121983,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.166666666666668, "throughputPerHour": 17.666666666666668,
"waiting": 21240 "waiting": 21238
} }
}, },
"queueAttemptedAt": "2026-10-07T22:33:32.483978+00:00", "queueAttemptedAt": "2026-10-07T22:44:02.054525+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-07T22:33:32.483978+00:00", "queueUpdatedAt": "2026-10-07T22:44:02.054525+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",

3667
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

113
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-07T22:06:14.844664+00:00", "generatedAt": "2026-10-07T22:42:35.105319+00:00",
"lastSyncTime": "2026-10-07T22:06:14.776284+00:00", "lastSyncTime": "2026-10-07T22:42:34.871334+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -4547,10 +4547,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 168, "ambiguous_runtime": 169,
"参数/模板问题": 3 "参数/模板问题": 3
}, },
"failureCount": 171, "failureCount": 172,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -4560,8 +4560,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 171, "total": 172,
"unresolvedFailureCount": 171 "unresolvedFailureCount": 172
}, },
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 61, "attributableFailureCount": 61,
@@ -5733,7 +5733,7 @@
"decisionSuccessRate": 0.0275, "decisionSuccessRate": 0.0275,
"decisionTotal": 182, "decisionTotal": 182,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 380, "ambiguous_runtime": 381,
"backend_operator": 9, "backend_operator": 9,
"framework_architecture_unsupported": 49, "framework_architecture_unsupported": 49,
"memory_capacity": 10, "memory_capacity": 10,
@@ -5742,15 +5742,15 @@
"tokenizer_compatibility": 96, "tokenizer_compatibility": 96,
"参数/模板问题": 13 "参数/模板问题": 13
}, },
"failureCount": 597, "failureCount": 598,
"failureRate": 0.9917, "failureRate": 0.9917,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 27, "platformFailureCount": 27,
"successCount": 5, "successCount": 5,
"successRate": 0.0083, "successRate": 0.0083,
"total": 602, "total": 603,
"unresolvedFailureCount": 393 "unresolvedFailureCount": 394
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"attributableFailureCount": 158, "attributableFailureCount": 158,
@@ -5781,7 +5781,7 @@
"unresolvedFailureCount": 257 "unresolvedFailureCount": 257
} }
}, },
"generatedAt": "2026-10-07T22:06:14.826753+00:00", "generatedAt": "2026-10-07T22:42:35.089294+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 120, "attributableFailureCount": 120,
@@ -6013,7 +6013,7 @@
"decisionSuccessRate": 0.066, "decisionSuccessRate": 0.066,
"decisionTotal": 106, "decisionTotal": 106,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 257, "ambiguous_runtime": 258,
"backend_operator": 23, "backend_operator": 23,
"framework_architecture_unsupported": 37, "framework_architecture_unsupported": 37,
"memory_capacity": 3, "memory_capacity": 3,
@@ -6026,15 +6026,15 @@
"日志缺失": 1, "日志缺失": 1,
"验证失败": 23 "验证失败": 23
}, },
"failureCount": 428, "failureCount": 429,
"failureRate": 0.9839, "failureRate": 0.9839,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 7, "successCount": 7,
"successRate": 0.0161, "successRate": 0.0161,
"total": 435, "total": 436,
"unresolvedFailureCount": 328 "unresolvedFailureCount": 329
}, },
"Kunlunxin_r-200-8f": { "Kunlunxin_r-200-8f": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -18661,9 +18661,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 2 "ambiguous_runtime": 3
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelType": "mini_k3", "modelType": "mini_k3",
@@ -18675,8 +18675,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 3
}, },
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none": { "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -25826,10 +25826,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 16, "ambiguous_runtime": 15,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 17, "failureCount": 16,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-customized", "framework": "vllm-customized",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -25841,8 +25841,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 17, "total": 16,
"unresolvedFailureCount": 17 "unresolvedFailureCount": 16
}, },
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 3, "attributableFailureCount": 3,
@@ -26062,9 +26062,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 9 "ambiguous_runtime": 10
}, },
"failureCount": 9, "failureCount": 10,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -26076,8 +26076,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 9, "total": 10,
"unresolvedFailureCount": 9 "unresolvedFailureCount": 10
}, },
"Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 16, "attributableFailureCount": 16,
@@ -27247,31 +27247,6 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|awq": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-customized",
"lastTerminalAt": "2026-09-22T21:50:30.559334+00:00",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors": { "Cambricon_mlu-370-x8|vllm-customized|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"consecutiveFailures": 0, "consecutiveFailures": 0,
@@ -28430,9 +28405,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 2 "ambiguous_runtime": 3
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-07T22:01:50.158710+00:00", "lastTerminalAt": "2026-10-07T22:01:50.158710+00:00",
@@ -28445,8 +28420,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 3
}, },
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|compressed-tensors": { "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -48532,9 +48507,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 2 "ambiguous_runtime": 3
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30, "loadSizeLog2Bucket": 30,
@@ -48547,8 +48522,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 3
}, },
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none|33": { "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|minicpm|none|33": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -59044,15 +59019,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17434, "terminalRecords": 17435,
"totalRecords": 17816, "totalRecords": 17817,
"totals": { "totals": {
"attributableFailureCount": 6260, "attributableFailureCount": 6260,
"decisionFailureRate": 0.8648, "decisionFailureRate": 0.8648,
"decisionSuccessRate": 0.1352, "decisionSuccessRate": 0.1352,
"decisionTotal": 7239, "decisionTotal": 7239,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4579, "ambiguous_runtime": 4580,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 130, "backend_operator": 130,
@@ -59068,15 +59043,15 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16455, "failureCount": 16456,
"failureRate": 0.9438, "failureRate": 0.9438,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 955, "platformFailureCount": 955,
"successCount": 979, "successCount": 979,
"successRate": 0.0562, "successRate": 0.0562,
"total": 17434, "total": 17435,
"unresolvedFailureCount": 9240 "unresolvedFailureCount": 9241
}, },
"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。",
@@ -59085,14 +59060,14 @@
"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 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。",
"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 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。",
"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。",
@@ -59138,6 +59113,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17816, "summarizedRecords": 17817,
"version": 1 "version": 1
} }

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -117,6 +117,7 @@
{"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": "2026-10-07T13:06:44.750866+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "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": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "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": 35256868927}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.848154+00:00", "targetGpu": "Biren_166m", "taskId": "5006202", "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": "2026-10-07T13:06:44.750866+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "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": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "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": 35256868927}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.848154+00:00", "targetGpu": "Biren_166m", "taskId": "5006202", "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": "2026-10-07T22:01:50.158710+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": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-21T19:21:51.640501+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006192", "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": "2026-10-07T22:01:50.158710+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": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-21T19:21:51.640501+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006192", "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": "2026-10-07T22:01:50.158742+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": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-21T19:21:51.639396+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006187", "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": "2026-10-07T22:01:50.158742+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": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-21T19:21:51.639396+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006187", "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": "2026-10-07T22:42:34.871334+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.583521+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006188", "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": "2026-10-07T14:46:46.372736+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "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": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35256868927}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:05:50.963205+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006057", "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": "2026-10-07T14:46:46.372736+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "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": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 35256868927}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:05:50.963205+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006057", "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": "2026-10-07T14:24:51.661617+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": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:05:50.745520+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006056", "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": "2026-10-07T14:24:51.661617+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": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:05:50.745520+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006056", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T17:46:09.953381+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "2026-09-21T19:05:50.437924+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5006050", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T17:46:09.953381+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "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": "2026-09-21T19:05:50.437924+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5006050", "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_tokenizer_patch", "lastSyncTime": "2026-09-30T15:29:22.559046+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013064, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197403, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093197403}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:40:34.490655+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4998300", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-30T15:29:22.559046+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-Dyn-Per-Token", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013064, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093197403, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093197403}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:40:34.490655+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4998300", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T09:55:55.960246+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1047023664, "estimatedRequiredGiB": 1.172, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1048871402, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1048871402}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:40:34.489077+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4998299", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T09:55:55.960246+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1047023664, "estimatedRequiredGiB": 1.172, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1048871402, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1048871402}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:40:34.489077+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4998299", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T09:54:21.980336+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T09:35:50+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969372", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T09:54:21.980336+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T09:35:50+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969372", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-22T21:50:30.559334+00:00", "modelId": "solidrust/Llama-3-16B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10261168632, "estimatedRequiredGiB": 11.478, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 10270608122, "modelscopeLicense": "other", "modelscopeParams": 16754741248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible - mergekit - merge - facebook - meta - pytorch - llama - llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 10270608122}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:33:26.659264+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4998167", "taskType": "text-generation", "verifyResult": -1}

1
.modelhub_state/recovery_intents.jsonl
View File

@@ -3238,6 +3238,7 @@
{"batchId": "9051f07a8dcd4bc3a217cfcc3f596181", "completedAt": "2026-10-07T20:33:04.415547+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T20:31:40.597505+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1dd491bc7b024fe897c9822d8efd4cf2", "lastModified": "2026-09-05T14:06:16+00:00", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-4.2-30b", "reason": null, "reconciledAt": "2026-10-07T22:30:52.279264+00:00", "repoId": "ibm-granite/granite-4.2-30b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5361267", "taskType": "text-generation"} {"batchId": "9051f07a8dcd4bc3a217cfcc3f596181", "completedAt": "2026-10-07T20:33:04.415547+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T20:31:40.597505+00:00", "framework": "vllm_fix_tokenizer", "intentId": "1dd491bc7b024fe897c9822d8efd4cf2", "lastModified": "2026-09-05T14:06:16+00:00", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-4.2-30b", "reason": null, "reconciledAt": "2026-10-07T22:30:52.279264+00:00", "repoId": "ibm-granite/granite-4.2-30b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5361267", "taskType": "text-generation"}
{"batchId": "9051f07a8dcd4bc3a217cfcc3f596181", "completedAt": "2026-10-07T20:33:04.415550+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T20:31:40.597548+00:00", "framework": "vllm_fix_tokenizer", "intentId": "425c318457ea4288a1698a30e4787ee0", "lastModified": "2026-09-15T15:06:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-9B-OptiQ-4bit", "reason": null, "reconciledAt": "2026-10-07T22:30:52.281066+00:00", "repoId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5361261", "taskType": "text-generation"} {"batchId": "9051f07a8dcd4bc3a217cfcc3f596181", "completedAt": "2026-10-07T20:33:04.415550+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T20:31:40.597548+00:00", "framework": "vllm_fix_tokenizer", "intentId": "425c318457ea4288a1698a30e4787ee0", "lastModified": "2026-09-15T15:06:14+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-9B-OptiQ-4bit", "reason": null, "reconciledAt": "2026-10-07T22:30:52.281066+00:00", "repoId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5361261", "taskType": "text-generation"}
{"batchId": "db73439bbd07499cb98b7842d424608b", "completedAt": "2026-10-07T21:43:55.329566+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-10-07T21:42:15.517760+00:00", "framework": "vllm", "intentId": "27173d26a8cf4a749bea9ec1dcf092d6", "lastModified": "2026-10-07T17:37:13+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "reason": null, "reconciledAt": "2026-10-07T22:30:52.278908+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5362155", "taskType": "text-generation"} {"batchId": "db73439bbd07499cb98b7842d424608b", "completedAt": "2026-10-07T21:43:55.329566+00:00", "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configSource": "modelhub_live", "createdAt": "2026-10-07T21:42:15.517760+00:00", "framework": "vllm", "intentId": "27173d26a8cf4a749bea9ec1dcf092d6", "lastModified": "2026-10-07T17:37:13+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "reason": null, "reconciledAt": "2026-10-07T22:30:52.278908+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5362155", "taskType": "text-generation"}
{"batchId": "f2bc60a09f214be6942517a4e455ed82", "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configSource": "modelhub_live", "createdAt": "2026-10-07T22:49:55.689819+00:00", "framework": "vllm_0_17_0_corex_4_4_0", "intentId": "7a5c5e77cb244e6abedde1e588aaaa1f", "lastModified": "2026-10-07T17:37:13+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848910+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.784067+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2f0cb6ccdecc4316b55609675cbdd668", "repoId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848910+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.784067+00:00", "framework": "vllm_fix_tokenizer", "intentId": "2f0cb6ccdecc4316b55609675cbdd668", "repoId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848903+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.783981+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e743bd075d9a4fef818c147bbe312063", "repoId": "ibm-granite/granite-4.2-30b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848903+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.783981+00:00", "framework": "vllm_fix_tokenizer", "intentId": "e743bd075d9a4fef818c147bbe312063", "repoId": "ibm-granite/granite-4.2-30b", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848900+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.783937+00:00", "framework": "vllm_fix_tokenizer", "intentId": "55a1a393950e454a964334b9ea2f0089", "repoId": "danish-foundation-models/DFM-Mimir-v1.5", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "6aa7248a7b3546dba73bdb92d9a77079", "completedAt": "2026-10-07T20:18:36.848900+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-07T19:40:31.783937+00:00", "framework": "vllm_fix_tokenizer", "intentId": "55a1a393950e454a964334b9ea2f0089", "repoId": "danish-foundation-models/DFM-Mimir-v1.5", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}

20
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": "2155fddbc430d96ce57cb103ff74a366d974a1573572657d6559c2921ba85a7f", ".modelhub_state/architecture_compatibility_blacklist.json": "5ce8c9afa101018c881d8f982d028e40d111709dbddd5a51d3a7140c1661f435",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "a40638fac801b1b36853bd42389b6a9c01d8640cdce5a2c0a80a2f423cb77f01", ".modelhub_state/market_intelligence.json": "77331b1ae260a817c9cdc995ac48a1769ae35a97473485321892d9e83fc2be77",
".modelhub_state/official_capabilities.json": "773fb91f05e6b0d218f39411c164ca3ca23012a11e3eea9f10f94e9eda2a6d06", ".modelhub_state/official_capabilities.json": "063c65fb0c7b117a5755a2cb7839af5d36b80ad74b5bea8f5f579cc02ea0f005",
".modelhub_state/outcome_checkpoint.json": "d177340290aeecc47e318fa088135a2730f45caea8baca15871d9a72bb3f5bb3", ".modelhub_state/outcome_checkpoint.json": "ac10773243bc833567e2bc5e17b2198f7d693117e6d9df6fd0c737f07c8bb397",
".modelhub_state/queue_cleanup_latest.json": "568ae8813ea4bc8c494aef8be02f77b1c9756ab49dd7d307b81483e6cca30468", ".modelhub_state/queue_cleanup_latest.json": "568ae8813ea4bc8c494aef8be02f77b1c9756ab49dd7d307b81483e6cca30468",
".modelhub_state/recent_outcomes.jsonl": "670b1e95d1a0951a1f4fdcc1a75f7b64efb6bfc0b13303aae1c9e50a554180c2", ".modelhub_state/recent_outcomes.jsonl": "1ff095378a0bdb1f59490c72eceec8c65190a696f12272f3cdebd4e0d1cb3510",
".modelhub_state/recovery_active_tasks.jsonl": "82cb29955fdf0fec6d57945f4cb7236bef89a89a1cd66196b4c2612e196cc60c", ".modelhub_state/recovery_active_tasks.jsonl": "82cb29955fdf0fec6d57945f4cb7236bef89a89a1cd66196b4c2612e196cc60c",
".modelhub_state/recovery_intents.jsonl": "b50b53520fbd4aa7c649a468d4cf7b0e2cff5a7adebc5f3caa4e4b34eced21f2", ".modelhub_state/recovery_intents.jsonl": "dd59265d3a01770d552bfa00e61564425deaee1dcd6204ed4e9546c7c850da76",
".modelhub_state/routing_intelligence.json": "7d46c7d0e7323a8a8993a23666c4c3f0da5eb4aed310f64b160071b6aca2a73d", ".modelhub_state/routing_intelligence.json": "7d46c7d0e7323a8a8993a23666c4c3f0da5eb4aed310f64b160071b6aca2a73d",
".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": "c68fb10c40e36336c64322fa633a176741466604d64f3e5a96ca81103c0d6cd6", "ledger/submissions.jsonl": "c68fb10c40e36336c64322fa633a176741466604d64f3e5a96ca81103c0d6cd6",
"outcomes/submissions.jsonl": "9454cfe80b4081c9e0a2ecfa90cf5d3057f4d87871cc2edc68e2aa845b04399e" "outcomes/submissions.jsonl": "7f6f02417d7510e6b0e64555faacc038e050c9869d12c6b2245b4d13be26466b"
}, },
"generation": 21991, "generation": 21992,
"phase": "cycle", "phase": "intent",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-07T22:41:32.425737+00:00", "updatedAt": "2026-10-07T22:49:55.932562+00:00",
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2" "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
} }

1
outcomes/submissions.jsonl
View File

@@ -220,7 +220,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563212+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:51.057293+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006049", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563212+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:51.057293+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006049", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563180+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "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": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:50.750203+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006047", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:05:58.563180+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "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": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:05:50.750203+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006047", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057492+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": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-21T19:21:51.636493+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006190", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057492+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": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": "2026-09-21T19:21:51.636493+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006190", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057509+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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": 2039076183}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.583521+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006188", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057389+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.641656+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006191", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057389+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n128-g8-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2037838088, "estimatedRequiredGiB": 2.281, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2041445091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.641656+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006191", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057480+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.26, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2022478516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.638009+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006194", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057480+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.26, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "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:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2022478516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.638009+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5006194", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600714+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-21T19:37:12.388268+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006357", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600714+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "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": "2026-09-21T19:37:12.388268+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006357", "taskType": "text-generation", "verifyResult": null}