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

state: generation 4818 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-09 22:42:56 +00:00
parent a98a9fcf94
commit 896196873a
9 changed files with 2440 additions and 2419 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1312,7 +1312,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-09T22:39:58.989696+00:00", "generatedAt": "2026-09-09T22:42:55.984564+00:00",
"summary": { "summary": {
"activeBlockCount": 65, "activeBlockCount": 65,
"byGpuFramework": { "byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -51,7 +51,7 @@
"4": { "4": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 342, "listingErrors": 343,
"nextPage": 1, "nextPage": 1,
"recordsScanned": 0, "recordsScanned": 0,
"uniqueRecords": 0 "uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00", "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0, "failureLogsInspected": 0,
"mode": "incremental_decision_only", "mode": "incremental_decision_only",
"nextAccountIndex": 4, "nextAccountIndex": 5,
"recordsScanned": 0, "recordsScanned": 0,
"seenTaskIds": [], "seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00", "startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0, "terminalRecords": 0,
"uniqueRecords": 0, "uniqueRecords": 0,
"updatedAt": "2026-09-09T22:39:58.965067+00:00", "updatedAt": "2026-09-09T22:42:55.961788+00:00",
"version": 1 "version": 1
} }

286
.modelhub_state/market_intelligence.json
View File

@@ -416,121 +416,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-09T22:38:32.603331+00:00", "generatedAt": "2026-09-09T22:41:08.180377+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1041.3777777777777, "backlogHours": 1056.857142857143,
"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": 1.6188683723864967, "qualityFactor": 1.8006488689266602,
"queueFactor": 0.9547620857411843, "queueFactor": 0.9508135051999828,
"queueWeight": 0.9547620857411843, "queueWeight": 0.9508135051999828,
"recentSuccess": 50, "recentSuccess": 51,
"recentSuccessRate": 0.37037037037037035, "recentSuccessRate": 0.38345864661654133,
"recentTerminal": 135, "recentTerminal": 133,
"recentWilsonLowerBound": 0.29355089594078115, "recentWilsonLowerBound": 0.30519662302307843,
"running": 8, "running": 9,
"selectionWeight": 1.5456341437601677, "selectionWeight": 1.712081262698542,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.5, "throughputPerHour": 22.166666666666668,
"waiting": 23431 "waiting": 23427
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 966.0701754385965, "backlogHours": 943.7828571428571,
"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": 1.5617490766364877, "qualityFactor": 1.5758380849980538,
"queueFactor": 0.9655729910922606, "queueFactor": 0.9670901770996895,
"queueWeight": 0.9655729910922606, "queueWeight": 0.9670901770996895,
"recentSuccess": 61, "recentSuccess": 62,
"recentSuccessRate": 0.3567251461988304, "recentSuccessRate": 0.35428571428571426,
"recentTerminal": 171, "recentTerminal": 175,
"recentWilsonLowerBound": 0.28879679791250346, "recentWilsonLowerBound": 0.28724575196118396,
"running": 8, "running": 8,
"selectionWeight": 1.5079827272634694, "selectionWeight": 1.5239775327012033,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 28.5, "throughputPerHour": 29.166666666666668,
"waiting": 27533 "waiting": 27527
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 156.46153846153845, "backlogHours": 156.53254437869822,
"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": 0.23549727877005378, "qualityFactor": 0.2628649178120155,
"queueFactor": 1.2687477088416144, "queueFactor": 1.2662139331704556,
"queueWeight": 1.2687477088416144, "queueWeight": 1.2662139331704556,
"recentSuccess": 29, "recentSuccess": 30,
"recentSuccessRate": 0.17159763313609466, "recentSuccessRate": 0.17751479289940827,
"recentTerminal": 169, "recentTerminal": 169,
"recentWilsonLowerBound": 0.12221550277461167, "recentWilsonLowerBound": 0.1272675612570857,
"running": 8, "running": 8,
"selectionWeight": 0.29878663287794066, "selectionWeight": 0.33284322147528067,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 28.166666666666668, "throughputPerHour": 28.166666666666668,
"waiting": 4407 "waiting": 4409
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1009.7142857142857, "backlogHours": 1034.1219512195123,
"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": 0.42447515101048827, "qualityFactor": 0.4579629416969793,
"queueFactor": 0.9591944015980046, "queueFactor": 0.9539201469369945,
"queueWeight": 0.9591944015980046, "queueWeight": 0.9539201469369945,
"recentSuccess": 20, "recentSuccess": 20,
"recentSuccessRate": 0.23809523809523808, "recentSuccessRate": 0.24390243902439024,
"recentTerminal": 84, "recentTerminal": 82,
"recentWilsonLowerBound": 0.15974570781689024, "recentWilsonLowerBound": 0.1637976208028234,
"running": 7, "running": 7,
"selectionWeight": 0.40715418846672796, "selectionWeight": 0.43686007663528076,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.0, "throughputPerHour": 13.666666666666666,
"waiting": 14136 "waiting": 14133
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 546.4948453608247, "backlogHours": 540.7346938775511,
"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": 0.9109964053176473, "qualityFactor": 1.078460025947306,
"queueFactor": 1.0517160458815802, "queueFactor": 1.05135685214214,
"queueWeight": 1.0517160458815802, "queueWeight": 1.05135685214214,
"recentSuccess": 30, "recentSuccess": 32,
"recentSuccessRate": 0.30927835051546393, "recentSuccessRate": 0.32653061224489793,
"recentTerminal": 97, "recentTerminal": 98,
"recentWilsonLowerBound": 0.22604022957947018, "recentWilsonLowerBound": 0.24176117124691768,
"running": 7, "running": 7,
"selectionWeight": 0.9581095372130093, "selectionWeight": 1.1338463380410901,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.166666666666668, "throughputPerHour": 16.333333333333332,
"waiting": 8835 "waiting": 8832
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 44.29090909090909, "backlogHours": 44.89846153846154,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -539,197 +539,197 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 25, "recentSuccess": 24,
"recentSuccessRate": 0.07575757575757576, "recentSuccessRate": 0.07384615384615385,
"recentTerminal": 330, "recentTerminal": 325,
"recentWilsonLowerBound": 0.05183750170583301, "recentWilsonLowerBound": 0.050123259700832215,
"running": 1, "running": 7,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 55.0, "throughputPerHour": 54.166666666666664,
"waiting": 2436 "waiting": 2432
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 72.60188087774296, "backlogHours": 73.39047619047619,
"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": 0.05682379549591227, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 29, "recentSuccess": 27,
"recentSuccessRate": 0.09090909090909091, "recentSuccessRate": 0.08571428571428572,
"recentTerminal": 319, "recentTerminal": 315,
"recentWilsonLowerBound": 0.06404196333460178, "recentWilsonLowerBound": 0.05957494073284867,
"running": 2, "running": 6,
"selectionWeight": 0.07387093414468596, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 53.166666666666664, "throughputPerHour": 52.5,
"waiting": 3860 "waiting": 3853
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 1437.9375, "backlogHours": 1415.9076923076923,
"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": 0.23769672896863603, "qualityFactor": 0.23427745363980257,
"queueFactor": 0.9096522728084829, "queueFactor": 0.9100024123690049,
"queueWeight": 0.9096522728084829, "queueWeight": 0.9100024123690049,
"recentSuccess": 13, "recentSuccess": 13,
"recentSuccessRate": 0.203125, "recentSuccessRate": 0.2,
"recentTerminal": 64, "recentTerminal": 65,
"recentWilsonLowerBound": 0.12273302562695813, "recentWilsonLowerBound": 0.12077845770945214,
"running": 2, "running": 2,
"selectionWeight": 0.21622136974546172, "selectionWeight": 0.21319304797588806,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.666666666666666, "throughputPerHour": 10.833333333333334,
"waiting": 15338 "waiting": 15339
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 714.989010989011, "backlogHours": 730.9213483146067,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.580030643173818, "qualityFactor": 0.5554410710758848,
"queueFactor": 1.0101631119961207, "queueFactor": 1.004886907215125,
"queueWeight": 1.0101631119961207, "queueWeight": 1.004886907215125,
"recentSuccess": 24, "recentSuccess": 23,
"recentSuccessRate": 0.26373626373626374, "recentSuccessRate": 0.25842696629213485,
"recentTerminal": 91, "recentTerminal": 89,
"recentWilsonLowerBound": 0.18410473382523007, "recentWilsonLowerBound": 0.1788141889199488,
"running": 7, "running": 7,
"selectionWeight": 0.5859255595615754, "selectionWeight": 0.5581554600537023,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.166666666666666, "throughputPerHour": 14.833333333333334,
"waiting": 10844 "waiting": 10842
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 766.9887640449438, "backlogHours": 767.0561797752808,
"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": 0.5439918404608547, "qualityFactor": 0.4923711377300293,
"queueFactor": 0.9995811557736521, "queueFactor": 0.9976396671978134,
"queueWeight": 0.9995811557736521, "queueWeight": 0.9976396671978134,
"recentSuccess": 23, "recentSuccess": 22,
"recentSuccessRate": 0.25842696629213485, "recentSuccessRate": 0.24719101123595505,
"recentTerminal": 89, "recentTerminal": 89,
"recentWilsonLowerBound": 0.1788141889199488, "recentWilsonLowerBound": 0.16928115452187478,
"running": 4, "running": 4,
"selectionWeight": 0.5437639926192973, "selectionWeight": 0.4912089779827951,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.833333333333334, "throughputPerHour": 14.833333333333334,
"waiting": 11377 "waiting": 11378
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1648.5974025974026, "backlogHours": 1606.7848101265824,
"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": 1.058504329339454, "qualityFactor": 0.9158464636480725,
"queueFactor": 0.8911877716566271, "queueFactor": 0.8929026814355905,
"queueWeight": 0.8911877716566271, "queueWeight": 0.8929026814355905,
"recentSuccess": 26, "recentSuccess": 25,
"recentSuccessRate": 0.33766233766233766, "recentSuccessRate": 0.31645569620253167,
"recentTerminal": 77, "recentTerminal": 79,
"recentWilsonLowerBound": 0.24199766918027013, "recentWilsonLowerBound": 0.22445138397970427,
"running": 4, "running": 4,
"selectionWeight": 0.9433261145529206, "selectionWeight": 0.817761763174667,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.833333333333334, "throughputPerHour": 13.166666666666666,
"waiting": 21157 "waiting": 21156
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 4616.0, "backlogHours": 4887.529411764705,
"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": 0.7195057060386414, "qualityFactor": 0.8426144059512395,
"queueFactor": 0.7636538408459407, "queueFactor": 0.7556738211869004,
"queueWeight": 0.7636538408459407, "queueWeight": 0.7556738211869004,
"recentSuccess": 7, "recentSuccess": 7,
"recentSuccessRate": 0.3888888888888889, "recentSuccessRate": 0.4117647058823529,
"recentTerminal": 18, "recentTerminal": 17,
"recentWilsonLowerBound": 0.2030499192693116, "recentWilsonLowerBound": 0.21610786039131383,
"running": 2, "running": 2,
"selectionWeight": 0.5494532959269788, "selectionWeight": 0.6367416479323033,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 3.0, "throughputPerHour": 2.8333333333333335,
"waiting": 13848 "waiting": 13848
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 762.7105263157895, "backlogHours": 743.0769230769231,
"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": 0.7822226535360739, "qualityFactor": 0.7522005123815025,
"queueFactor": 1.000420193526946, "queueFactor": 1.0024038330654412,
"queueWeight": 1.000420193526946, "queueWeight": 1.0024038330654412,
"recentSuccess": 23, "recentSuccess": 23,
"recentSuccessRate": 0.3026315789473684, "recentSuccessRate": 0.2948717948717949,
"recentTerminal": 76, "recentTerminal": 78,
"recentWilsonLowerBound": 0.21091189301319777, "recentWilsonLowerBound": 0.205240767244175,
"running": 16, "running": 16,
"selectionWeight": 0.7825513384317203, "selectionWeight": 0.754008676845007,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.666666666666666, "throughputPerHour": 13.0,
"waiting": 9661 "waiting": 9660
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 464.57142857142856, "backlogHours": 460.40707964601773,
"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": 2.5, "qualityFactor": 2.5,
"queueFactor": 1.0776519916646858, "queueFactor": 1.0770267397477082,
"queueWeight": 1.0776519916646858, "queueWeight": 1.0770267397477082,
"recentSuccess": 50, "recentSuccess": 50,
"recentSuccessRate": 0.44642857142857145, "recentSuccessRate": 0.4424778761061947,
"recentTerminal": 112, "recentTerminal": 113,
"recentWilsonLowerBound": 0.3576589345942301, "recentWilsonLowerBound": 0.35428881381187033,
"running": 6, "running": 6,
"selectionWeight": 2.6941299791617146, "selectionWeight": 2.6925668493692707,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.666666666666668, "throughputPerHour": 18.833333333333332,
"waiting": 8672 "waiting": 8671
} }
}, },
"queueAttemptedAt": "2026-09-09T22:29:54.808119+00:00", "queueAttemptedAt": "2026-09-09T22:41:08.180377+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-09T22:29:54.808119+00:00", "queueUpdatedAt": "2026-09-09T22:41:08.180377+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Iluvatar_mrv-100", "Iluvatar_mrv-100",

1520
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

126
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-09T22:24:28.440996+00:00", "generatedAt": "2026-09-09T22:41:00.047359+00:00",
"lastSyncTime": "2026-09-09T22:24:28.408286+00:00", "lastSyncTime": "2026-09-09T22:40:59.810547+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1906,19 +1906,19 @@
"unresolvedFailureCount": 56 "unresolvedFailureCount": 56
}, },
"MetaX_c-500|vllm|text-generation": { "MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 34, "attributableFailureCount": 36,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 34, "decisionTotal": 36,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 7, "ambiguous_runtime": 7,
"backend_operator": 15, "backend_operator": 17,
"framework_architecture_unsupported": 14, "framework_architecture_unsupported": 14,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 4, "model_load": 4,
"参数/模板问题": 9 "参数/模板问题": 9
}, },
"failureCount": 50, "failureCount": 52,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -1928,7 +1928,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 50, "total": 52,
"unresolvedFailureCount": 16 "unresolvedFailureCount": 16
}, },
"Mthreads_s4000|llamacpp|text-generation": { "Mthreads_s4000|llamacpp|text-generation": {
@@ -2315,13 +2315,13 @@
"unresolvedFailureCount": 818 "unresolvedFailureCount": 818
}, },
"vllm": { "vllm": {
"attributableFailureCount": 223, "attributableFailureCount": 225,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 223, "decisionTotal": 225,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 116, "ambiguous_runtime": 116,
"backend_operator": 18, "backend_operator": 20,
"framework_architecture_unsupported": 168, "framework_architecture_unsupported": 168,
"memory_capacity": 6, "memory_capacity": 6,
"model_load": 18, "model_load": 18,
@@ -2331,14 +2331,14 @@
"tokenizer_compatibility": 3, "tokenizer_compatibility": 3,
"参数/模板问题": 21 "参数/模板问题": 21
}, },
"failureCount": 361, "failureCount": 363,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 361, "total": 363,
"unresolvedFailureCount": 137 "unresolvedFailureCount": 137
}, },
"vllm-mlu": { "vllm-mlu": {
@@ -2442,7 +2442,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-09T22:24:28.437080+00:00", "generatedAt": "2026-09-09T22:41:00.042625+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2649,27 +2649,27 @@
"unresolvedFailureCount": 72 "unresolvedFailureCount": 72
}, },
"MetaX_c-500": { "MetaX_c-500": {
"attributableFailureCount": 34, "attributableFailureCount": 36,
"decisionFailureRate": 0.7907, "decisionFailureRate": 0.8,
"decisionSuccessRate": 0.2093, "decisionSuccessRate": 0.2,
"decisionTotal": 43, "decisionTotal": 45,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 7, "ambiguous_runtime": 7,
"backend_operator": 15, "backend_operator": 17,
"framework_architecture_unsupported": 14, "framework_architecture_unsupported": 14,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 4, "model_load": 4,
"参数/模板问题": 17, "参数/模板问题": 17,
"验证失败": 48 "验证失败": 48
}, },
"failureCount": 106, "failureCount": 108,
"failureRate": 0.9217, "failureRate": 0.9231,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 9, "successCount": 9,
"successRate": 0.0783, "successRate": 0.0769,
"total": 115, "total": 117,
"unresolvedFailureCount": 72 "unresolvedFailureCount": 72
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
@@ -3453,14 +3453,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": { "MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 7, "attributableFailureCount": 8,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 7, "decisionTotal": 8,
"failureBreakdown": { "failureBreakdown": {
"backend_operator": 7 "backend_operator": 8
}, },
"failureCount": 7, "failureCount": 8,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "llama", "modelType": "llama",
@@ -3472,7 +3472,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 7, "total": 8,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors": { "MetaX_c-500|vllm|text-generation|phi3small|compressed-tensors": {
@@ -3614,14 +3614,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": { "MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 4, "attributableFailureCount": 5,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 4, "decisionTotal": 5,
"failureBreakdown": { "failureBreakdown": {
"backend_operator": 4 "backend_operator": 5
}, },
"failureCount": 4, "failureCount": 5,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"modelType": "starcoder2", "modelType": "starcoder2",
@@ -3633,7 +3633,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 4, "total": 5,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": { "Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": {
@@ -6079,14 +6079,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|30": { "MetaX_c-500|vllm|text-generation|llama|compressed-tensors|30": {
"attributableFailureCount": 2, "attributableFailureCount": 3,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"backend_operator": 2 "backend_operator": 3
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"loadSizeLog2Bucket": 30, "loadSizeLog2Bucket": 30,
@@ -6099,7 +6099,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|33": { "MetaX_c-500|vllm|text-generation|llama|compressed-tensors|33": {
@@ -6342,6 +6342,30 @@
"total": 2, "total": 2,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 33,
"modelType": "starcoder2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|34": { "MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -6655,16 +6679,16 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1452, "terminalRecords": 1454,
"totalRecords": 1536, "totalRecords": 1538,
"totals": { "totals": {
"attributableFailureCount": 386, "attributableFailureCount": 388,
"decisionFailureRate": 0.8894, "decisionFailureRate": 0.8899,
"decisionSuccessRate": 0.1106, "decisionSuccessRate": 0.1101,
"decisionTotal": 434, "decisionTotal": 436,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 249, "ambiguous_runtime": 249,
"backend_operator": 21, "backend_operator": 23,
"framework_architecture_unsupported": 266, "framework_architecture_unsupported": 266,
"memory_capacity": 11, "memory_capacity": 11,
"model_load": 45, "model_load": 45,
@@ -6675,21 +6699,21 @@
"参数/模板问题": 94, "参数/模板问题": 94,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1404, "failureCount": 1406,
"failureRate": 0.9669, "failureRate": 0.967,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 48, "successCount": 48,
"successRate": 0.0331, "successRate": 0.033,
"total": 1452, "total": 1454,
"unresolvedFailureCount": 1016 "unresolvedFailureCount": 1016
}, },
"warnings": [ "warnings": [
"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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 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 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 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 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。",
@@ -6697,7 +6721,7 @@
"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-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 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 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。",
"组合 Iluvatar_mrv-100|unknown|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|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|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 Cambricon_mlu-370-x8|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 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -6718,6 +6742,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1536, "summarizedRecords": 1538,
"version": 1 "version": 1
} }

1847
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1050
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

20
manifest.json
View File

@@ -1,24 +1,24 @@
{ {
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "724bae5316e460c5e74231a76fbcd9579717e12076fa09e037a601bb60d34035", ".modelhub_state/architecture_compatibility_blacklist.json": "3e8ee4165128fa672d638a805c672e42f28588c2c411e8c5f6bac818e89a0021",
".modelhub_state/architecture_history_backfill.json": "b655042e11ee34ffe2329c64c182e511d415ae9639d8722524471d988d8c626e", ".modelhub_state/architecture_history_backfill.json": "05cbece4797bac507b9d28a2eeaa1ff2efbd1162e5d1e334b0916822e5b34012",
".modelhub_state/market_intelligence.json": "5df4710238dd5d8666ece2175904f8f9f7d77c0e9e984cf55c5f79201b2867f0", ".modelhub_state/market_intelligence.json": "4d38d3b12291c129d685e1604c18cc6f4cffd646765cea96e4926c54d8ce4fa2",
".modelhub_state/official_capabilities.json": "55d0c1dbc38e02944020363f5e72fa8334109024adf9394b2cfd4cf2393313a2", ".modelhub_state/official_capabilities.json": "b2893d04dbe0f417bb3821d5430fb58dc02a235bc6ae21dfe51ef70c9691d0cd",
".modelhub_state/outcome_checkpoint.json": "9a5ca9a4872219ce62b4916fee942532d50a1b0d164ca05675bd63f13c08b525", ".modelhub_state/outcome_checkpoint.json": "3dfef337d7db95518d3db42b06eaf636eeb790b22a002cf368adca65ec55880d",
".modelhub_state/queue_cleanup_latest.json": "9a11c448074d1c105fe90e48fb81cfc27bce5e7e08d76397232f05c4c9432a32", ".modelhub_state/queue_cleanup_latest.json": "9a11c448074d1c105fe90e48fb81cfc27bce5e7e08d76397232f05c4c9432a32",
".modelhub_state/recent_outcomes.jsonl": "0ba62edeb0936c478c13e9ebb7a444549eb69e48501525583a4d8a935a6afd7b", ".modelhub_state/recent_outcomes.jsonl": "0ba62edeb0936c478c13e9ebb7a444549eb69e48501525583a4d8a935a6afd7b",
".modelhub_state/recovery_active_tasks.jsonl": "4b1e3a384e2dd2d41904923eb6d5c40e33a8a5986855922812d4383c9d0fa25a", ".modelhub_state/recovery_active_tasks.jsonl": "c89c37e1b6f5c0a2e3164b1530c625ace272177af2d07c7b07398a93a0bb76c2",
".modelhub_state/recovery_intents.jsonl": "c1e418cee2a32acdb19de388403246f85cce6a7ea0951d66bd9a344d217fcddb", ".modelhub_state/recovery_intents.jsonl": "996394b9d66f65e07a2a20b39f659ddc7fdf3c9cb7fe0fa8085791185310ba8e",
".modelhub_state/routing_intelligence.json": "4effdc96741bb83e9319ea4665226a7e2442dc48c76af38dae47ff1343260b42", ".modelhub_state/routing_intelligence.json": "4effdc96741bb83e9319ea4665226a7e2442dc48c76af38dae47ff1343260b42",
".modelhub_state/submission_exclusions.jsonl": "363b21d9f5526f9b072e4f5ff55cc1ff126e844da64fb08a7b6e4d09b2559cdb", ".modelhub_state/submission_exclusions.jsonl": "363b21d9f5526f9b072e4f5ff55cc1ff126e844da64fb08a7b6e4d09b2559cdb",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76", ".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "877ac486271d5afd91db3f6b8aee973a960a405d6789142e0a8e03758d9691ba", "ledger/submissions.jsonl": "877ac486271d5afd91db3f6b8aee973a960a405d6789142e0a8e03758d9691ba",
"outcomes/submissions.jsonl": "83a45446b5f4e4296c7f7ff8cce66aaf47b90461b191ea04f291b1e8048f8f5e" "outcomes/submissions.jsonl": "e579fb8d5b700e664329c0f65817d051df1dceeddea02016efd539c927b19ab3"
}, },
"generation": 4817, "generation": 4818,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-09T22:39:59.105569+00:00", "updatedAt": "2026-09-09T22:42:56.554358+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977" "writerId": "58ff5dc2a2d64b119ad1e4560700f977"
} }

2
outcomes/submissions.jsonl
View File

@@ -45,7 +45,6 @@
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-04T16:14:29.511220+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:14:12.544960+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4622655", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-04T16:14:29.511220+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "modelhub_preflight_oom:49"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:14:12.544960+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4622655", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:33:41.731498+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:33:06.846794+00:00", "targetGpu": "Biren_166m", "taskId": "4623002", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T16:33:41.731498+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:33:06.846794+00:00", "targetGpu": "Biren_166m", "taskId": "4623002", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-04T16:50:26.817445+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:44:58.161709+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4623226", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-04T16:50:26.817445+00:00", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15338408461, "estimatedRequiredGiB": 17.168, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15362064483, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7669052656, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:exl3", "custom_tag:exllamav3", "custom_tag:quantization", "custom_tag:long-context", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "exl3", "repositoryOnDiskBytes": 15362064483}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T08:44:58.161709+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4623226", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T17:43:13.003958+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "5dc29cb4673042e118df9721ee1fc20ce84e880992fba859071f1332bb52342f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2014810120, "estimatedRequiredGiB": 2.256, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2018195521, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1812039680, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2018195521}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T09:39:47.066326+00:00", "targetGpu": "MetaX_c-500", "taskId": "4624118", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T19:52:10.096489+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "5dc29cb4673042e118df9721ee1fc20ce84e880992fba859071f1332bb52342f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T11:51:30.613200+00:00", "targetGpu": "MetaX_c-500", "taskId": "4625822", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T19:52:10.096489+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "5dc29cb4673042e118df9721ee1fc20ce84e880992fba859071f1332bb52342f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T11:51:30.613200+00:00", "targetGpu": "MetaX_c-500", "taskId": "4625822", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T20:39:27.718139+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T12:34:49.403585+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4626360", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-04T20:39:27.718139+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:8"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T12:34:49.403585+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4626360", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T20:54:37.415689+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663867, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788663867}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T12:51:02.061439+00:00", "targetGpu": "MetaX_c-500", "taskId": "4626559", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T20:54:37.415689+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:29"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663867, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "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": 17788663867}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T12:51:02.061439+00:00", "targetGpu": "MetaX_c-500", "taskId": "4626559", "taskType": "text-generation", "verifyResult": null}
@@ -127,7 +126,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T17:46:46.041785+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20041566112, "estimatedRequiredGiB": 22.408, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 20050750527, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 20050750527}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:38:43.506267+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645748", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T17:46:46.041785+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-Non-Uniform-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20041566112, "estimatedRequiredGiB": 22.408, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 20050750527, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 20050750527}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:38:43.506267+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645748", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T17:46:46.041804+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081293776, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504091, "modelscopeLicense": "llama3", "modelscopeParams": 8030261312, "modelscopeTags": ["license:llama3", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 9090504091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:38:43.485599+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645738", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T17:46:46.041804+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081293776, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090504091, "modelscopeLicense": "llama3", "modelscopeParams": 8030261312, "modelscopeTags": ["license:llama3", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 9090504091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:38:43.485599+00:00", "targetGpu": "MetaX_c-500", "taskId": "4645738", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T17:46:46.041763+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:43:33.758884+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4645816", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-05T17:46:46.041763+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:43:33.758884+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4645816", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T18:24:30.794851+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16564748304, "estimatedRequiredGiB": 18.516, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 16568142341, "modelscopeLicense": "other", "modelscopeParams": 15957889024, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": {"backend_operator": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T10:14:38.509276+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 16568142341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T10:20:32.691216+00:00", "targetGpu": "MetaX_c-500", "taskId": "4646326", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T18:34:58.235083+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5700679600, "estimatedRequiredGiB": 6.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5709884743, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 5709884743}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T10:33:51.489696+00:00", "targetGpu": "MetaX_c-500", "taskId": "4646504", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T18:34:58.235083+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5700679600, "estimatedRequiredGiB": 6.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5709884743, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 5709884743}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T10:33:51.489696+00:00", "targetGpu": "MetaX_c-500", "taskId": "4646504", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T18:34:58.235126+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T10:33:51.484756+00:00", "targetGpu": "MetaX_c-500", "taskId": "4646505", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T18:34:58.235126+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T10:33:51.484756+00:00", "targetGpu": "MetaX_c-500", "taskId": "4646505", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T19:13:04.549009+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5705684944, "estimatedRequiredGiB": 6.387, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5714910031, "modelscopeLicense": null, "modelscopeParams": 8031506432, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 5714910031}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T11:12:23.284350+00:00", "targetGpu": "MetaX_c-500", "taskId": "4647279", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T19:13:04.549009+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5705684944, "estimatedRequiredGiB": 6.387, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5714910031, "modelscopeLicense": null, "modelscopeParams": 8031506432, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T03:28:46.602358+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 5714910031}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T11:12:23.284350+00:00", "targetGpu": "MetaX_c-500", "taskId": "4647279", "taskType": "text-generation", "verifyResult": null}