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

state: generation 18848 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-30 16:31:07 +00:00
parent f409f60579
commit c34ea1f982
8 changed files with 1594 additions and 1595 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -3320,7 +3320,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-30T16:16:04.464262+00:00", "generatedAt": "2026-09-30T16:28:39.055495+00:00",
"summary": { "summary": {
"activeBlockCount": 167, "activeBlockCount": 167,
"byGpuFramework": { "byGpuFramework": {

294
.modelhub_state/market_intelligence.json
View File

@@ -434,55 +434,55 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-30T16:27:35.873806+00:00", "generatedAt": "2026-09-30T16:30:31.875190+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1041.8076923076924, "backlogHours": 1009.3788819875776,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b3", "gpu": "Ascend_910-b3",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 1.5549654742613472, "qualityFactor": 1.6316929758970087,
"queueFactor": 1.0090118525165737, "queueFactor": 0.9739022187043024,
"queueWeight": 1.0090118525165737, "queueWeight": 0.9739022187043024,
"recentSuccess": 62, "recentSuccess": 63,
"recentSuccessRate": 0.3974358974358974, "recentSuccessRate": 0.391304347826087,
"recentTerminal": 156, "recentTerminal": 161,
"recentWilsonLowerBound": 0.323995015158663, "recentWilsonLowerBound": 0.319290340263488,
"running": 8, "running": 8,
"selectionWeight": 1.5689785937837546, "selectionWeight": 1.5891094094703226,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.0, "throughputPerHour": 26.833333333333332,
"waiting": 27087 "waiting": 27085
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1398.096, "backlogHours": 1444.0661157024792,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b4", "gpu": "Ascend_910-b4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 2.5, "qualityFactor": 2.344567788331588,
"queueFactor": 0.9654590386238259, "queueFactor": 0.9229654109841681,
"queueWeight": 0.9654590386238259, "queueWeight": 0.9229654109841681,
"recentSuccess": 61, "recentSuccess": 56,
"recentSuccessRate": 0.488, "recentSuccessRate": 0.4628099173553719,
"recentTerminal": 125, "recentTerminal": 121,
"recentWilsonLowerBound": 0.4020447124457442, "recentWilsonLowerBound": 0.37648034032327066,
"running": 9, "running": 8,
"selectionWeight": 2.4136475965595645, "selectionWeight": 2.1639549723377063,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.833333333333332, "throughputPerHour": 20.166666666666668,
"waiting": 29127 "waiting": 29122
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 24.277386934673366, "backlogHours": 24.13213213213213,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
@@ -492,63 +492,63 @@
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 26, "recentSuccess": 26,
"recentSuccessRate": 0.02613065326633166, "recentSuccessRate": 0.026026026026026026,
"recentTerminal": 995, "recentTerminal": 999,
"recentWilsonLowerBound": 0.01789358778583658, "recentWilsonLowerBound": 0.01782169770719021,
"running": 8, "running": 8,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 165.83333333333334, "throughputPerHour": 166.5,
"waiting": 4026 "waiting": 4018
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1315.8, "backlogHours": 188.25766871165644,
"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": 0.4987177052031724, "qualityFactor": 0.05,
"queueFactor": 0.9742847828136458, "queueFactor": 1.2528832003812487,
"queueWeight": 0.9742847828136458, "queueWeight": 1.2528832003812487,
"recentSuccess": 20, "recentSuccess": 21,
"recentSuccessRate": 0.2857142857142857, "recentSuccessRate": 0.04294478527607362,
"recentTerminal": 70, "recentTerminal": 489,
"recentWilsonLowerBound": 0.19322076591803128, "recentWilsonLowerBound": 0.028257430375584647,
"running": 7, "running": 7,
"selectionWeight": 0.48589307109919266, "selectionWeight": 0.06264416001906244,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": false,
"throughputPerHour": 11.666666666666666, "throughputPerHour": 81.5,
"waiting": 15351 "waiting": 15343
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 489.72222222222223, "backlogHours": 467.5221238938053,
"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": 0.41572005348226915, "qualityFactor": 0.44761764792553327,
"queueFactor": 1.1299830525864079, "queueFactor": 1.0930830559473408,
"queueWeight": 1.1299830525864079, "queueWeight": 1.0930830559473408,
"recentSuccess": 27, "recentSuccess": 28,
"recentSuccessRate": 0.25, "recentSuccessRate": 0.24778761061946902,
"recentTerminal": 108, "recentTerminal": 113,
"recentWilsonLowerBound": 0.17787718518702555, "recentWilsonLowerBound": 0.17735906738422746,
"running": 7, "running": 7,
"selectionWeight": 0.4697566150552792, "selectionWeight": 0.48928326649040277,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.0, "throughputPerHour": 18.833333333333332,
"waiting": 8815 "waiting": 8805
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 32.640586797066014, "backlogHours": 32.45255474452555,
"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": 5, "recentSuccess": 5,
"recentSuccessRate": 0.012224938875305624, "recentSuccessRate": 0.012165450121654502,
"recentTerminal": 409, "recentTerminal": 411,
"recentWilsonLowerBound": 0.0052326823065035845, "recentWilsonLowerBound": 0.005207165634551282,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 68.16666666666667, "throughputPerHour": 68.5,
"waiting": 2225 "waiting": 2223
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 102.93687707641196, "backlogHours": 102.13861386138613,
"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": 0.11486510588355008, "qualityFactor": 0.11494020522427122,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 40, "recentSuccess": 39,
"recentSuccessRate": 0.132890365448505, "recentSuccessRate": 0.12871287128712872,
"recentTerminal": 301, "recentTerminal": 303,
"recentWilsonLowerBound": 0.09913004726379647, "recentWilsonLowerBound": 0.09560348973436855,
"running": 5, "running": 7,
"selectionWeight": 0.14932463764861512, "selectionWeight": 0.1494222667915526,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 50.166666666666664, "throughputPerHour": 50.5,
"waiting": 5164 "waiting": 5158
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2700.342857142857, "backlogHours": 2863.818181818182,
"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": 0.4559601970214495, "qualityFactor": 0.7325632959442947,
"queueFactor": 0.8746847714207402, "queueFactor": 0.8328785378831888,
"queueWeight": 0.8746847714207402, "queueWeight": 0.8328785378831888,
"recentSuccess": 11, "recentSuccess": 12,
"recentSuccessRate": 0.3142857142857143, "recentSuccessRate": 0.36363636363636365,
"recentTerminal": 35, "recentTerminal": 33,
"recentWilsonLowerBound": 0.18550658059782457, "recentWilsonLowerBound": 0.22186966167959873,
"running": 2, "running": 2,
"selectionWeight": 0.3988214407086622, "selectionWeight": 0.6101362468329738,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 5.833333333333333, "throughputPerHour": 5.5,
"waiting": 15752 "waiting": 15751
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 392.6842105263158, "backlogHours": 421.92452830188677,
"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": 0.36749291139417684, "qualityFactor": 0.38266295575354875,
"queueFactor": 1.1680404579304888, "queueFactor": 1.110039086451751,
"queueWeight": 1.1680404579304888, "queueWeight": 1.110039086451751,
"recentSuccess": 27, "recentSuccess": 25,
"recentSuccessRate": 0.23684210526315788, "recentSuccessRate": 0.2358490566037736,
"recentTerminal": 114, "recentTerminal": 106,
"recentWilsonLowerBound": 0.16818157933444355, "recentWilsonLowerBound": 0.16515930334184276,
"running": 8, "running": 8,
"selectionWeight": 0.42924658851106284, "selectionWeight": 0.4247708378235961,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 19.0, "throughputPerHour": 17.666666666666668,
"waiting": 7461 "waiting": 7454
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 641.3877551020408, "backlogHours": 683.0869565217391,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "MetaX_c-500", "gpu": "MetaX_c-500",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 1.1154530199293509, "qualityFactor": 1.2033146023722368,
"queueFactor": 1.0851663096323259, "queueFactor": 1.0326474774382923,
"queueWeight": 1.0851663096323259, "queueWeight": 1.0326474774382923,
"recentSuccess": 36, "recentSuccess": 34,
"recentSuccessRate": 0.3673469387755102, "recentSuccessRate": 0.3695652173913043,
"recentTerminal": 98, "recentTerminal": 92,
"recentWilsonLowerBound": 0.27858728951874556, "recentWilsonLowerBound": 0.27801481252642296,
"running": 4, "running": 4,
"selectionWeight": 1.210452037204967, "selectionWeight": 1.242599788704352,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.333333333333332, "throughputPerHour": 15.333333333333334,
"waiting": 10476 "waiting": 10474
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2062.59375, "backlogHours": 2095.1428571428573,
"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": 2.2213588983056347, "qualityFactor": 2.5,
"queueFactor": 0.9107566419202197, "queueFactor": 0.8728536679579739,
"queueWeight": 0.9107566419202197, "queueWeight": 0.8728536679579739,
"recentSuccess": 32, "recentSuccess": 32,
"recentSuccessRate": 0.5, "recentSuccessRate": 0.5079365079365079,
"recentTerminal": 64, "recentTerminal": 63,
"recentWilsonLowerBound": 0.3810188849321495, "recentWilsonLowerBound": 0.38762677115387556,
"running": 4, "running": 4,
"selectionWeight": 2.0231173707204384, "selectionWeight": 2.182134169894935,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.666666666666666, "throughputPerHour": 10.5,
"waiting": 22001 "waiting": 21999
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 4402.173913043478, "backlogHours": 4600.909090909091,
"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": 0.19294534316404716, "qualityFactor": 0.3747793114855431,
"queueFactor": 0.8128573225003293, "queueFactor": 0.7757056228920453,
"queueWeight": 0.8128573225003293, "queueWeight": 0.7757056228920453,
"recentSuccess": 6, "recentSuccess": 7,
"recentSuccessRate": 0.2608695652173913, "recentSuccessRate": 0.3181818181818182,
"recentTerminal": 23, "recentTerminal": 22,
"recentWilsonLowerBound": 0.1254844588924897, "recentWilsonLowerBound": 0.16360387354692477,
"running": 2, "running": 2,
"selectionWeight": 0.15683703503323457, "selectionWeight": 0.29071841926294506,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": true,
"throughputPerHour": 3.8333333333333335, "throughputPerHour": 3.6666666666666665,
"waiting": 16875 "waiting": 16870
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1170.2307692307693, "backlogHours": 1249.9726027397262,
"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": 0.07287649391568675, "qualityFactor": 0.06966532568535944,
"queueFactor": 0.9915706760568904, "queueFactor": 0.9431666008596973,
"queueWeight": 0.9915706760568904, "queueWeight": 0.9431666008596973,
"recentSuccess": 11, "recentSuccess": 10,
"recentSuccessRate": 0.14102564102564102, "recentSuccessRate": 0.136986301369863,
"recentTerminal": 78, "recentTerminal": 73,
"recentWilsonLowerBound": 0.08060961324830107, "recentWilsonLowerBound": 0.07614307799620812,
"running": 16, "running": 16,
"selectionWeight": 0.07226219434063337, "selectionWeight": 0.06570600842444423,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 13.0, "throughputPerHour": 12.166666666666666,
"waiting": 15213 "waiting": 15208
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 1232.7692307692307, "backlogHours": 1289.5172413793102,
"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": 0.7454859251467351, "qualityFactor": 0.8963739013522426,
"queueFactor": 0.9838573486823318, "queueFactor": 0.9387704579578573,
"queueWeight": 0.9838573486823318, "queueWeight": 0.9387704579578573,
"recentSuccess": 29, "recentSuccess": 29,
"recentSuccessRate": 0.31868131868131866, "recentSuccessRate": 0.3333333333333333,
"recentTerminal": 91, "recentTerminal": 87,
"recentWilsonLowerBound": 0.2319585919157763, "recentWilsonLowerBound": 0.2431846311443509,
"running": 6, "running": 6,
"selectionWeight": 0.733451805794862, "selectionWeight": 0.841489337873916,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.166666666666666, "throughputPerHour": 14.5,
"waiting": 18697 "waiting": 18698
} }
}, },
"queueAttemptedAt": "2026-09-30T16:18:07.589352+00:00", "queueAttemptedAt": "2026-09-30T16:30:31.875190+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-30T16:18:07.589352+00:00", "queueUpdatedAt": "2026-09-30T16:30:31.875190+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{ {
"catalogUpdatedAt": "2026-09-30T16:27:35.873806+00:00", "catalogUpdatedAt": "2026-09-30T16:30:31.875190+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-09-30T16:27:35.873806+00:00", "generatedAt": "2026-09-30T16:30:31.875190+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6346,6 +6346,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-09-30T16:27:35.873806+00:00", "taskTreeUpdatedAt": "2026-09-30T16:30:31.875190+00:00",
"version": 1 "version": 1
} }

76
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-30T16:05:33.255448+00:00", "generatedAt": "2026-09-30T16:28:38.969292+00:00",
"lastSyncTime": "2026-09-30T16:05:32.942739+00:00", "lastSyncTime": "2026-09-30T16:28:38.651952+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -3448,25 +3448,25 @@
"decisionSuccessRate": 0.093, "decisionSuccessRate": 0.093,
"decisionTotal": 43, "decisionTotal": 43,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 75, "ambiguous_runtime": 76,
"context_length": 8, "context_length": 8,
"framework_architecture_unsupported": 30, "framework_architecture_unsupported": 30,
"memory_capacity": 1, "memory_capacity": 1,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"参数/模板问题": 8 "参数/模板问题": 8
}, },
"failureCount": 123, "failureCount": 124,
"failureRate": 0.9685, "failureRate": 0.9688,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 4, "successCount": 4,
"successRate": 0.0315, "successRate": 0.0312,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 127, "total": 128,
"unresolvedFailureCount": 83 "unresolvedFailureCount": 84
}, },
"Ascend_910-b3|vllm|text-generation": { "Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 69, "attributableFailureCount": 69,
@@ -6173,7 +6173,7 @@
"decisionSuccessRate": 0.068, "decisionSuccessRate": 0.068,
"decisionTotal": 147, "decisionTotal": 147,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 187, "ambiguous_runtime": 188,
"backend_operator": 15, "backend_operator": 15,
"context_length": 8, "context_length": 8,
"framework_architecture_unsupported": 81, "framework_architecture_unsupported": 81,
@@ -6185,18 +6185,18 @@
"tokenizer_compatibility": 2, "tokenizer_compatibility": 2,
"参数/模板问题": 29 "参数/模板问题": 29
}, },
"failureCount": 356, "failureCount": 357,
"failureRate": 0.9727, "failureRate": 0.9728,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 3, "platformFailureCount": 3,
"successCount": 10, "successCount": 10,
"successRate": 0.0273, "successRate": 0.0272,
"total": 366, "total": 367,
"unresolvedFailureCount": 216 "unresolvedFailureCount": 217
} }
}, },
"generatedAt": "2026-09-30T16:05:33.240779+00:00", "generatedAt": "2026-09-30T16:28:38.951812+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 109, "attributableFailureCount": 109,
@@ -6204,7 +6204,7 @@
"decisionSuccessRate": 0.1679, "decisionSuccessRate": 0.1679,
"decisionTotal": 131, "decisionTotal": 131,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 143, "ambiguous_runtime": 144,
"context_length": 8, "context_length": 8,
"framework_architecture_unsupported": 95, "framework_architecture_unsupported": 95,
"memory_capacity": 2, "memory_capacity": 2,
@@ -6215,15 +6215,15 @@
"日志缺失": 3, "日志缺失": 3,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 322, "failureCount": 323,
"failureRate": 0.936, "failureRate": 0.9362,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 22, "successCount": 22,
"successRate": 0.064, "successRate": 0.0638,
"total": 344, "total": 345,
"unresolvedFailureCount": 212 "unresolvedFailureCount": 213
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"attributableFailureCount": 325, "attributableFailureCount": 325,
@@ -6894,10 +6894,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 6, "decisionTotal": 6,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 13, "ambiguous_runtime": 14,
"context_length": 6 "context_length": 6
}, },
"failureCount": 19, "failureCount": 20,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"modelType": "llama", "modelType": "llama",
@@ -6909,8 +6909,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 19, "total": 20,
"unresolvedFailureCount": 13 "unresolvedFailureCount": 14
}, },
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": { "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -28106,9 +28106,9 @@
"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_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 32, "loadSizeLog2Bucket": 32,
@@ -28121,8 +28121,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 3
}, },
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|33": { "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|compressed-tensors|33": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -53719,15 +53719,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17164, "terminalRecords": 17165,
"totalRecords": 17385, "totalRecords": 17386,
"totals": { "totals": {
"attributableFailureCount": 6151, "attributableFailureCount": 6151,
"decisionFailureRate": 0.8632, "decisionFailureRate": 0.8632,
"decisionSuccessRate": 0.1368, "decisionSuccessRate": 0.1368,
"decisionTotal": 7126, "decisionTotal": 7126,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4472, "ambiguous_runtime": 4473,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 128, "backend_operator": 128,
@@ -53743,30 +53743,30 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16189, "failureCount": 16190,
"failureRate": 0.9432, "failureRate": 0.9432,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 943, "platformFailureCount": 943,
"successCount": 975, "successCount": 975,
"successRate": 0.0568, "successRate": 0.0568,
"total": 17164, "total": 17165,
"unresolvedFailureCount": 9095 "unresolvedFailureCount": 9096
}, },
"warnings": [ "warnings": [
"GPU Iluvatar_mrv-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 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 Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 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。",
"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 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 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 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 Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-150 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 MetaX_c-500 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。",
"组合 Ascend_910-b4|llamacpp|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-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -53811,6 +53811,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17385, "summarizedRecords": 17386,
"version": 1 "version": 1
} }

1288
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1504
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.22.1", "agentVersion": "2026.09.22.1",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "f454cb81dda72a6dee952eab00c4985df2cab2a0802e4231fa96ccf78947a461", ".modelhub_state/architecture_compatibility_blacklist.json": "f0141561d95acab9b056ba662f2854d8ca81f3b1bd884e7598c9b769a23bb432",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "6025b426cb67ff341d0500da189d05bdd83cf4e17f8173e7f0d7d57cfe853803", ".modelhub_state/market_intelligence.json": "cadef7a0d83a09e345ff711d9749acc34370073e3a8d2e9c63fd19749d968029",
".modelhub_state/official_capabilities.json": "bf47fdb67aa6a82def4dbec2e20f1d260fbcd285e84012ba9e7e199b1936a7ce", ".modelhub_state/official_capabilities.json": "997755b33328f3e0da8c5fd71f7860ea66e4ba7850c344ee6145a3989af5f196",
".modelhub_state/outcome_checkpoint.json": "f7c151e2dda63ad7e20cb3b37b8665810001623bbf31362460411c2f74517cab", ".modelhub_state/outcome_checkpoint.json": "29540503c8692eba815eea6001d322660238411f9a6eccb42cdd3b52741b22e9",
".modelhub_state/queue_cleanup_latest.json": "c1930ca8fdcacb5490295c7c7dc06f8ef1bd9c45953bf68d684e316cf0b931fd", ".modelhub_state/queue_cleanup_latest.json": "c1930ca8fdcacb5490295c7c7dc06f8ef1bd9c45953bf68d684e316cf0b931fd",
".modelhub_state/recent_outcomes.jsonl": "0ab1d5c5cfd855068e4f18ef6f8e3076175a93fcf632e662039eca492632e3b0", ".modelhub_state/recent_outcomes.jsonl": "0ab1d5c5cfd855068e4f18ef6f8e3076175a93fcf632e662039eca492632e3b0",
".modelhub_state/recovery_active_tasks.jsonl": "9559fa0e6d4aca8d4b71026d15b3e155ce3a115411b6a98755f3fb246ae23d6d", ".modelhub_state/recovery_active_tasks.jsonl": "53672a9467676c49fcc3e70a8ffe25a33ad5149baf26476a12ed7bed501d4c14",
".modelhub_state/recovery_intents.jsonl": "2bcf334827021998904318ea20addc4490b552696afe715495bfa3a815dba984", ".modelhub_state/recovery_intents.jsonl": "b14921b9ad9672c592e948e356c9f94831aa6ddf0f2d9b33530a5a226dbde54e",
".modelhub_state/routing_intelligence.json": "ad5036c22163257eb214ffb5ed3f45f7344d321b1597a4b4099df6dde09a83a5", ".modelhub_state/routing_intelligence.json": "ad5036c22163257eb214ffb5ed3f45f7344d321b1597a4b4099df6dde09a83a5",
".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c", ".modelhub_state/submission_exclusions.jsonl": "1e62f6ba5bd2ba5f2f360bc134b44f7b69190230dd0e274919a87a73ea66761c",
".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd", ".modelhub_state/worker_crashes.jsonl": "21a892d638884250c04f19e07a433baae065285327484e361c9e5067b0bc17dd",
"ledger/submissions.jsonl": "dcf2c30617991563b08515887f74fa61df5737c8a9bf303a39290cc1ed384f04", "ledger/submissions.jsonl": "dcf2c30617991563b08515887f74fa61df5737c8a9bf303a39290cc1ed384f04",
"outcomes/submissions.jsonl": "8c136fd69e3834064dd961815c4739a59ffd0abb65283ad8f19f248bec09ec72" "outcomes/submissions.jsonl": "85e81534717f0031b4775e43348c3560ab19692ba414ebd1075d8168623ca762"
}, },
"generation": 18847, "generation": 18848,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-30T16:27:36.836970+00:00", "updatedAt": "2026-09-30T16:31:07.247486+00:00",
"writerId": "a812d0e025c3474eb16b828a4d987334" "writerId": "a812d0e025c3474eb16b828a4d987334"
} }

1
outcomes/submissions.jsonl
View File

@@ -301,7 +301,6 @@
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T13:18:18.977292+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T05:16:13.324611+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4971311", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T13:18:18.977292+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T05:16:13.324611+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4971311", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T14:18:03.258951+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T06:16:07.269550+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4972172", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T14:18:03.258951+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T06:16:07.269550+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4972172", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T16:51:24.761939+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T08:49:13.744928+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974217", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T16:51:24.761939+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T08:49:13.744928+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4974217", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T17:39:36.352398+00:00", "modelId": "RedHatAI/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161034, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T09:25:37.077913+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4976379", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T17:54:13.170240+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {"architectures": ["Param2MoEForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34302758832, "estimatedRequiredGiB": 38.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "param2moe", "modelscopeFileSize": 34317809830, "modelscopeLicense": null, "modelscopeParams": 17151125376, "modelscopeTags": ["model_type:param2moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:multilingual", "custom_tag:indian-languages"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 34317809830}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T09:41:34.108703+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4976623", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T17:54:13.170240+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {"architectures": ["Param2MoEForCausalLM"], "configFingerprint": "53aadead5bb69dd6c72976cf6353832080116244f86ffae86297646e5bb48fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34302758832, "estimatedRequiredGiB": 38.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "param2moe", "modelscopeFileSize": 34317809830, "modelscopeLicense": null, "modelscopeParams": 17151125376, "modelscopeTags": ["model_type:param2moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:multilingual", "custom_tag:indian-languages"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 34317809830}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T09:41:34.108703+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4976623", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T21:06:45.850274+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:01:42.205703+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979280", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T21:06:45.850274+00:00", "modelId": "RedHatAI/gemma-4-12B-it-FP8-Dynamic", "modelProfile": {"architectures": ["Gemma4UnifiedForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15037393456, "estimatedRequiredGiB": 16.842, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4_unified", "modelscopeFileSize": 15069601989, "modelscopeLicense": "apache-2.0", "modelscopeParams": 12966363184, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4_unified", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "task:image-text-to-text", "custom_tag:fp8", "custom_tag:vllm", "custom_tag:llm-compressor", "custom_tag:compressed-tensors"], "modelscopeTasks": ["text-generation", "image-text-to-text"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 15069601989}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T13:01:42.205703+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4979280", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754909+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457730, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096457730}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:38:07.337494+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4980575", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T22:43:47.754909+00:00", "modelId": "neuralmagic/starcoder2-3b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093158536, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096457730, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096457730}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T14:38:07.337494+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4980575", "taskType": "text-generation", "verifyResult": null}