state: generation 6377 (cycle)

This commit is contained in:
2026-09-12 21:41:52 +00:00
parent 9f1479a3df
commit 4e1b79d86f
9 changed files with 2990 additions and 2753 deletions

View File

@@ -1429,7 +1429,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-12T21:38:56.194096+00:00", "generatedAt": "2026-09-12T21:41:51.348331+00:00",
"summary": { "summary": {
"activeBlockCount": 72, "activeBlockCount": 72,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": { "5": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 460, "listingErrors": 461,
"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": 5, "nextAccountIndex": 6,
"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": "2026-09-12T21:38:56.169525+00:00", "updatedAt": "2026-09-12T21:41:51.325171+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,94 +416,94 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T21:36:50.847163+00:00", "generatedAt": "2026-09-12T21:40:03.285542+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 951.1428571428571, "backlogHours": 951.1836734693877,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b3", "gpu": "Ascend_910-b3",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.9998115623826191, "qualityFactor": 0.9807228891547821,
"queueFactor": 0.9918387432666254, "queueFactor": 0.9867163027746888,
"queueWeight": 0.9918387432666254, "queueWeight": 0.9867163027746888,
"recentSuccess": 49, "recentSuccess": 48,
"recentSuccessRate": 0.3333333333333333, "recentSuccessRate": 0.32653061224489793,
"recentTerminal": 147, "recentTerminal": 147,
"recentWilsonLowerBound": 0.26222862590583235, "recentWilsonLowerBound": 0.2559812008773996,
"running": 8, "running": 8,
"selectionWeight": 0.9916518435370182, "selectionWeight": 0.9676952632333176,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.5, "throughputPerHour": 24.5,
"waiting": 23303 "waiting": 23304
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1156.225352112676, "backlogHours": 1156.1408450704225,
"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": 1.389872273753939, "qualityFactor": 1.3702311027451817,
"queueFactor": 0.9632112762111852, "queueFactor": 0.9582533588038795,
"queueWeight": 0.9632112762111852, "queueWeight": 0.9582533588038795,
"recentSuccess": 54, "recentSuccess": 53,
"recentSuccessRate": 0.38028169014084506, "recentSuccessRate": 0.3732394366197183,
"recentTerminal": 142, "recentTerminal": 142,
"recentWilsonLowerBound": 0.30458316031697674, "recentWilsonLowerBound": 0.2980091971868539,
"running": 8, "running": 8,
"selectionWeight": 1.3387406465730733, "selectionWeight": 1.3130285565431141,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.666666666666668, "throughputPerHour": 23.666666666666668,
"waiting": 27364 "waiting": 27362
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 155.20689655172413, "backlogHours": 158.03508771929825,
"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": 0.26472700803352767, "qualityFactor": 0.2634567748496764,
"queueFactor": 1.3, "queueFactor": 1.2915729285392743,
"queueWeight": 1.3, "queueWeight": 1.2915729285392743,
"recentSuccess": 34, "recentSuccess": 33,
"recentSuccessRate": 0.19540229885057472, "recentSuccessRate": 0.19298245614035087,
"recentTerminal": 174, "recentTerminal": 171,
"recentWilsonLowerBound": 0.14333520447497392, "recentWilsonLowerBound": 0.14084347623053362,
"running": 8, "running": 8,
"selectionWeight": 0.344145110443586, "selectionWeight": 0.3402736382361088,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 29.0, "throughputPerHour": 28.5,
"waiting": 4501 "waiting": 4504
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1331.353846153846, "backlogHours": 1395.774193548387,
"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": 0.5259797088325607, "qualityFactor": 0.5222943362093309,
"queueFactor": 0.9430482353735623, "queueFactor": 0.9315575439859277,
"queueWeight": 0.9430482353735623, "queueWeight": 0.9315575439859277,
"recentSuccess": 19, "recentSuccess": 18,
"recentSuccessRate": 0.2923076923076923, "recentSuccessRate": 0.2903225806451613,
"recentTerminal": 65, "recentTerminal": 62,
"recentWilsonLowerBound": 0.19583261556264242, "recentWilsonLowerBound": 0.192234063853952,
"running": 7, "running": 7,
"selectionWeight": 0.4960242362568465, "selectionWeight": 0.48654722907692466,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.833333333333334, "throughputPerHour": 10.333333333333334,
"waiting": 14423 "waiting": 14423
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
@@ -514,15 +514,15 @@
"gpu": "Cambricon_mlu-370-x8", "gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.3300970921176338, "qualityFactor": 0.3747018644113005,
"queueFactor": 1.1220031293510107, "queueFactor": 1.116215628002637,
"queueWeight": 1.1220031293510107, "queueWeight": 1.116215628002637,
"recentSuccess": 28, "recentSuccess": 29,
"recentSuccessRate": 0.2222222222222222, "recentSuccessRate": 0.23015873015873015,
"recentTerminal": 126, "recentTerminal": 126,
"recentWilsonLowerBound": 0.1584594242584552, "recentWilsonLowerBound": 0.16529948502667766,
"running": 7, "running": 7,
"selectionWeight": 0.37036997034565394, "selectionWeight": 0.4182480768976187,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 21.0, "throughputPerHour": 21.0,
@@ -530,7 +530,7 @@
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 41.98250728862974, "backlogHours": 41.19428571428571,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -540,15 +540,15 @@
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 12, "recentSuccess": 12,
"recentSuccessRate": 0.03498542274052478, "recentSuccessRate": 0.03428571428571429,
"recentTerminal": 343, "recentTerminal": 350,
"recentWilsonLowerBound": 0.020124217684249053, "recentWilsonLowerBound": 0.019719537289799936,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 57.166666666666664, "throughputPerHour": 58.333333333333336,
"waiting": 2400 "waiting": 2403
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
@@ -561,10 +561,10 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 19, "recentSuccess": 18,
"recentSuccessRate": 0.09268292682926829, "recentSuccessRate": 0.08780487804878048,
"recentTerminal": 205, "recentTerminal": 205,
"recentWilsonLowerBound": 0.060137857862294974, "recentWilsonLowerBound": 0.05626136035599752,
"running": 5, "running": 5,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
@@ -574,162 +574,162 @@
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2270.7804878048782, "backlogHours": 2327.5499999999997,
"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": 0.792151843886698, "qualityFactor": 0.8685224810127062,
"queueFactor": 0.8704656910004319, "queueFactor": 0.8627741191659866,
"queueWeight": 0.8704656910004319, "queueWeight": 0.8627741191659866,
"recentSuccess": 15, "recentSuccess": 15,
"recentSuccessRate": 0.36585365853658536, "recentSuccessRate": 0.375,
"recentTerminal": 41, "recentTerminal": 40,
"recentWilsonLowerBound": 0.23589630416936813, "recentWilsonLowerBound": 0.24222773535791722,
"running": 2, "running": 2,
"selectionWeight": 0.6895410021661008, "selectionWeight": 0.749338718531595,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.833333333333333, "throughputPerHour": 6.666666666666667,
"waiting": 15517 "waiting": 15517
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 880.32, "backlogHours": 892.1351351351351,
"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": 0.3259321450363538, "qualityFactor": 0.29674548145581,
"queueFactor": 1.0034179043592284, "queueFactor": 0.9962477769958149,
"queueWeight": 1.0034179043592284, "queueWeight": 0.9962477769958149,
"recentSuccess": 18, "recentSuccess": 17,
"recentSuccessRate": 0.24, "recentSuccessRate": 0.22972972972972974,
"recentTerminal": 75, "recentTerminal": 74,
"recentWilsonLowerBound": 0.1575474872875825, "recentWilsonLowerBound": 0.1486706552074038,
"running": 8, "running": 7,
"selectionWeight": 0.3270461499356862, "selectionWeight": 0.2956320262339035,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.5, "throughputPerHour": 12.333333333333334,
"waiting": 11004 "waiting": 11003
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 747.8901098901099, "backlogHours": 716.5894736842105,
"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": 0.4092684421245577, "qualityFactor": 0.383675206566786,
"queueFactor": 1.0282583924472537, "queueFactor": 1.0295356703419372,
"queueWeight": 1.0282583924472537, "queueWeight": 1.0295356703419372,
"recentSuccess": 23, "recentSuccess": 23,
"recentSuccessRate": 0.25274725274725274, "recentSuccessRate": 0.24210526315789474,
"recentTerminal": 91, "recentTerminal": 95,
"recentWilsonLowerBound": 0.17472595343886432, "recentWilsonLowerBound": 0.16708723217598367,
"running": 6, "running": 4,
"selectionWeight": 0.42083371037838957, "selectionWeight": 0.39500731098631725,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.166666666666666, "throughputPerHour": 15.833333333333334,
"waiting": 11343 "waiting": 11346
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2108.16393442623, "backlogHours": 2009.15625,
"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": 1.9504686940284832, "qualityFactor": 1.7992988420936409,
"queueFactor": 0.8802221124036301, "queueFactor": 0.8820229895298766,
"queueWeight": 0.8802221124036301, "queueWeight": 0.8820229895298766,
"recentSuccess": 29, "recentSuccess": 29,
"recentSuccessRate": 0.47540983606557374, "recentSuccessRate": 0.453125,
"recentTerminal": 61, "recentTerminal": 64,
"recentWilsonLowerBound": 0.3553028228679598, "recentWilsonLowerBound": 0.33729251486034373,
"running": 5, "running": 4,
"selectionWeight": 1.7168456740349012, "selectionWeight": 1.5870229437610783,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.166666666666666, "throughputPerHour": 10.666666666666666,
"waiting": 21433 "waiting": 21431
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 3462.72, "backlogHours": 3206.4444444444443,
"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": 0.5660390782832585, "qualityFactor": 0.48823184399677666,
"queueFactor": 0.8170814012947899, "queueFactor": 0.822296428396369,
"queueWeight": 0.8170814012947899, "queueWeight": 0.822296428396369,
"recentSuccess": 9, "recentSuccess": 9,
"recentSuccessRate": 0.36, "recentSuccessRate": 0.3333333333333333,
"recentTerminal": 25, "recentTerminal": 27,
"recentWilsonLowerBound": 0.20247656431735636, "recentWilsonLowerBound": 0.1864305444359335,
"running": 2, "running": 2,
"selectionWeight": 0.46250000327129615, "selectionWeight": 0.40147130154792265,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 4.166666666666667, "throughputPerHour": 4.5,
"waiting": 14428 "waiting": 14429
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 920.8285714285714, "backlogHours": 847.9736842105264,
"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": 0.5106699407748767, "qualityFactor": 0.43712760747318813,
"queueFactor": 0.996669374263508, "queueFactor": 1.0038633656827842,
"queueWeight": 0.996669374263508, "queueWeight": 1.0038633656827842,
"recentSuccess": 20, "recentSuccess": 20,
"recentSuccessRate": 0.2857142857142857, "recentSuccessRate": 0.2631578947368421,
"recentTerminal": 70, "recentTerminal": 76,
"recentWilsonLowerBound": 0.19322076591803128, "recentWilsonLowerBound": 0.17729266370899457,
"running": 16, "running": 16,
"selectionWeight": 0.5089690903272791, "selectionWeight": 0.4388163912708976,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.666666666666666, "throughputPerHour": 12.666666666666666,
"waiting": 10743 "waiting": 10741
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 636.4090909090909, "backlogHours": 643.7931034482758,
"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": 1.053458605436425, "queueFactor": 1.0462127631898042,
"queueWeight": 1.053458605436425, "queueWeight": 1.0462127631898042,
"recentSuccess": 44, "recentSuccess": 43,
"recentSuccessRate": 0.5, "recentSuccessRate": 0.4942528735632184,
"recentTerminal": 88, "recentTerminal": 87,
"recentWilsonLowerBound": 0.3977398665504473, "recentWilsonLowerBound": 0.39168097748132213,
"running": 7, "running": 6,
"selectionWeight": 2.6336465135910627, "selectionWeight": 2.6155319079745105,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.666666666666666, "throughputPerHour": 14.5,
"waiting": 9334 "waiting": 9335
} }
}, },
"queueAttemptedAt": "2026-09-12T21:28:47.218483+00:00", "queueAttemptedAt": "2026-09-12T21:40:03.285542+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-12T21:28:47.218483+00:00", "queueUpdatedAt": "2026-09-12T21:40:03.285542+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Iluvatar_mrv-100", "Iluvatar_mrv-100",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-12T21:28:41.538560+00:00", "generatedAt": "2026-09-12T21:39:57.345906+00:00",
"lastSyncTime": "2026-09-12T21:28:41.303490+00:00", "lastSyncTime": "2026-09-12T21:39:57.012261+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2052,7 +2052,7 @@
"decisionSuccessRate": 0.0545, "decisionSuccessRate": 0.0545,
"decisionTotal": 55, "decisionTotal": 55,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 8, "ambiguous_runtime": 9,
"backend_operator": 27, "backend_operator": 27,
"framework_architecture_unsupported": 16, "framework_architecture_unsupported": 16,
"memory_capacity": 1, "memory_capacity": 1,
@@ -2060,18 +2060,18 @@
"repository_structure": 1, "repository_structure": 1,
"参数/模板问题": 9 "参数/模板问题": 9
}, },
"failureCount": 69, "failureCount": 70,
"failureRate": 0.9583, "failureRate": 0.9589,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 3, "successCount": 3,
"successRate": 0.0417, "successRate": 0.0411,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 72, "total": 73,
"unresolvedFailureCount": 17 "unresolvedFailureCount": 18
}, },
"Mthreads_s4000|llamacpp|text-generation": { "Mthreads_s4000|llamacpp|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -2468,7 +2468,7 @@
"decisionSuccessRate": 0.0105, "decisionSuccessRate": 0.0105,
"decisionTotal": 285, "decisionTotal": 285,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 200, "ambiguous_runtime": 201,
"backend_operator": 34, "backend_operator": 34,
"framework_architecture_unsupported": 196, "framework_architecture_unsupported": 196,
"memory_capacity": 6, "memory_capacity": 6,
@@ -2479,15 +2479,15 @@
"tokenizer_compatibility": 6, "tokenizer_compatibility": 6,
"参数/模板问题": 24 "参数/模板问题": 24
}, },
"failureCount": 507, "failureCount": 508,
"failureRate": 0.9941, "failureRate": 0.9941,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 3, "successCount": 3,
"successRate": 0.0059, "successRate": 0.0059,
"total": 510, "total": 511,
"unresolvedFailureCount": 224 "unresolvedFailureCount": 225
}, },
"vllm-mlu": { "vllm-mlu": {
"attributableFailureCount": 7, "attributableFailureCount": 7,
@@ -2591,7 +2591,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-12T21:28:41.534086+00:00", "generatedAt": "2026-09-12T21:39:57.341679+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 30, "attributableFailureCount": 30,
@@ -2805,7 +2805,7 @@
"decisionSuccessRate": 0.1875, "decisionSuccessRate": 0.1875,
"decisionTotal": 64, "decisionTotal": 64,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 8, "ambiguous_runtime": 9,
"backend_operator": 27, "backend_operator": 27,
"framework_architecture_unsupported": 16, "framework_architecture_unsupported": 16,
"memory_capacity": 1, "memory_capacity": 1,
@@ -2814,15 +2814,15 @@
"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": 125, "failureCount": 126,
"failureRate": 0.9124, "failureRate": 0.913,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 12, "successCount": 12,
"successRate": 0.0876, "successRate": 0.087,
"total": 137, "total": 138,
"unresolvedFailureCount": 73 "unresolvedFailureCount": 74
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"attributableFailureCount": 33, "attributableFailureCount": 33,
@@ -4660,9 +4660,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 6 "ambiguous_runtime": 5
}, },
"failureCount": 6, "failureCount": 5,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -4674,8 +4674,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation", "taskType": "text-generation",
"total": 6, "total": 5,
"unresolvedFailureCount": 6 "unresolvedFailureCount": 5
}, },
"MetaX_c-500|vllm|text-generation": { "MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6, "attributableFailureCount": 6,
@@ -4685,16 +4685,16 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 6, "decisionTotal": 6,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1, "ambiguous_runtime": 2,
"framework_architecture_unsupported": 2, "framework_architecture_unsupported": 2,
"model_load": 3, "model_load": 3,
"repository_structure": 1 "repository_structure": 1
}, },
"failureCount": 7, "failureCount": 8,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T17:06:34.916681+00:00", "lastTerminalAt": "2026-09-12T21:39:57.012261+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -4702,8 +4702,8 @@
"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": 1 "unresolvedFailureCount": 2
}, },
"Mthreads_s4000|llamacpp|text-generation": { "Mthreads_s4000|llamacpp|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
@@ -4941,31 +4941,6 @@
} }
}, },
"recentProfileCombinationStats": { "recentProfileCombinationStats": {
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-10T12:23:25.501745+00:00",
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": { "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"consecutiveFailures": 0, "consecutiveFailures": 0,
@@ -7296,15 +7271,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1739, "terminalRecords": 1740,
"totalRecords": 1826, "totalRecords": 1827,
"totals": { "totals": {
"attributableFailureCount": 496, "attributableFailureCount": 496,
"decisionFailureRate": 0.8953, "decisionFailureRate": 0.8953,
"decisionSuccessRate": 0.1047, "decisionSuccessRate": 0.1047,
"decisionTotal": 554, "decisionTotal": 554,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 407, "ambiguous_runtime": 408,
"backend_operator": 42, "backend_operator": 42,
"framework_architecture_unsupported": 308, "framework_architecture_unsupported": 308,
"memory_capacity": 11, "memory_capacity": 11,
@@ -7316,21 +7291,20 @@
"参数/模板问题": 101, "参数/模板问题": 101,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1681, "failureCount": 1682,
"failureRate": 0.9666, "failureRate": 0.9667,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 4, "platformFailureCount": 4,
"successCount": 58, "successCount": 58,
"successRate": 0.0334, "successRate": 0.0333,
"total": 1739, "total": 1740,
"unresolvedFailureCount": 1181 "unresolvedFailureCount": 1182
}, },
"warnings": [ "warnings": [
"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 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 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 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 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。",
@@ -7339,6 +7313,7 @@
"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。",
"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 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 Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|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 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7361,6 +7336,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1826, "summarizedRecords": 1827,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,4 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-12T21:39:57.012261+00:00", "modelId": "QuantTrio/KAT-Dev-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T21:29:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079182", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-12T21:28:41.303467+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T21:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523212", "taskType": "text-generation", "verifyResult": -1} {"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-12T21:28:41.303467+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T21:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523212", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-12T21:28:41.303490+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-12T21:25:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549638", "taskType": "text-generation", "verifyResult": 1} {"failReason": null, "framework": "", "lastSyncTime": "2026-09-12T21:28:41.303490+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-12T21:25:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4549638", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T20:49:10.452723+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T20:41:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4549113", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-12T20:49:10.452723+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T20:41:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4549113", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T14:21:21.949441+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703969742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703969742}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.998598+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729524", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T14:21:21.949441+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20683239637, "estimatedRequiredGiB": 23.138, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20703969742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 6086364400, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:m1", "custom_tag:m2", "custom_tag:fp16", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20703969742}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.998598+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729524", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T13:57:00.114030+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 225662258, "estimatedRequiredGiB": 0.282, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 252393272, "modelscopeLicense": "apache-2.0", "modelscopeParams": 79652352, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:mxfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 252393272}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.995104+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729526", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T13:57:00.114030+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-mxfp4", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 225662258, "estimatedRequiredGiB": 0.282, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 252393272, "modelscopeLicense": "apache-2.0", "modelscopeParams": 79652352, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:mxfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 252393272}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.995104+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729526", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T20:13:30.044094+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 238933307, "estimatedRequiredGiB": 0.297, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 265664321, "modelscopeLicense": "apache-2.0", "modelscopeParams": 106194432, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:nvfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 265664321}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.985375+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729522", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T20:13:30.044094+00:00", "modelId": "mlx-community/Qwen3.8-27B-MTP-nvfp4", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 238933307, "estimatedRequiredGiB": 0.297, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_mtp", "modelscopeFileSize": 265664321, "modelscopeLicense": "apache-2.0", "modelscopeParams": 106194432, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_mtp", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-vlm", "custom_tag:qwen3_5_mtp", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:qwen", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:nvfp4"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 265664321}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.985375+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729522", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T12:23:25.501745+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998647728, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020563851, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "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": 12020563851}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.913002+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729521", "taskType": "text-generation", "verifyResult": -1}

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -1,24 +1,24 @@
{ {
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "b9fd91056eb8a9ee12898ea133444ccbd556935f42b5439229de042b19b29814", ".modelhub_state/architecture_compatibility_blacklist.json": "accc40adb31a4c2c92235fce0769f136c14b87d1a441f0a247b0d2885ad2f969",
".modelhub_state/architecture_history_backfill.json": "613cf57b67852528e279d7fe6e76072a334fdb279065b8a2836066e8f2956854", ".modelhub_state/architecture_history_backfill.json": "d42695b5b373157ed25309edd73256d2ced8c774f1728e2dd35563f1f3387e6c",
".modelhub_state/market_intelligence.json": "46360154b52e9f61d9b05554043a3801dd2d1c937a2b4862b216f9798c856a11", ".modelhub_state/market_intelligence.json": "8ccf089146a9f6852baef92eb3d7997ddd5446e688a30f97c539bf3740a24a39",
".modelhub_state/official_capabilities.json": "ec930fd0388da2c0034802eb599e49faf05d96e5773e6aed1ff037e88e816fe8", ".modelhub_state/official_capabilities.json": "b8d756c4537665a047750292700d43be6bd72599343b6c841f41c9dafa3ecd99",
".modelhub_state/outcome_checkpoint.json": "4769a34c49858203721726945d10df81f346aaaa98191d1e189b0259d0f44f57", ".modelhub_state/outcome_checkpoint.json": "e52c7d8dc8a18ac08fe48a352f9404aa7c808a820b4df1be44f40274d4193eec",
".modelhub_state/queue_cleanup_latest.json": "1138f6ff3d4a387f335781418eae5f60d8291f48eb315007dba62a41d3ea4742", ".modelhub_state/queue_cleanup_latest.json": "1138f6ff3d4a387f335781418eae5f60d8291f48eb315007dba62a41d3ea4742",
".modelhub_state/recent_outcomes.jsonl": "b69ea854994ffeb3486cd7834d0494c159f9277e91a782ae4b38f7a9626ac583", ".modelhub_state/recent_outcomes.jsonl": "cc72bc6fd600d6362a2b5ae2163f95449b62cd058986aa805fecbbc12b8f9683",
".modelhub_state/recovery_active_tasks.jsonl": "a3a82c12a5ed483efaaf45e5063fb6669ea2239a5da4b5da763cb4b516df6fbc", ".modelhub_state/recovery_active_tasks.jsonl": "9b7e49c771d3760f51e4bd61ed5b42edfb98c58bc4ea30964a00be477d4933cf",
".modelhub_state/recovery_intents.jsonl": "d1ba7097ca253b850404045b0e3942e96006f11601d1c4e9173956a273338a79", ".modelhub_state/recovery_intents.jsonl": "0f6da00a440e19d2713beadbccabaa90ed5c9c3324d3502c31ad00b854aa659c",
".modelhub_state/routing_intelligence.json": "cdd3341d66484775862c4a1f5c766a7fc0200b1a3a204a76975162502e1d3457", ".modelhub_state/routing_intelligence.json": "cdd3341d66484775862c4a1f5c766a7fc0200b1a3a204a76975162502e1d3457",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220", ".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162", ".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "b7a4c9900ee212be7c7f8578a0a71942885eb83e97c5583098a169266bedf55c", "ledger/submissions.jsonl": "b7a4c9900ee212be7c7f8578a0a71942885eb83e97c5583098a169266bedf55c",
"outcomes/submissions.jsonl": "330f4925bfdc6851862a37bcf16ba89cafeb5e0ec5028e9aac675e630a66f055" "outcomes/submissions.jsonl": "330f4925bfdc6851862a37bcf16ba89cafeb5e0ec5028e9aac675e630a66f055"
}, },
"generation": 6376, "generation": 6377,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-12T21:38:56.343053+00:00", "updatedAt": "2026-09-12T21:41:51.992164+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2" "writerId": "e5dd59a4c84a4f21926bad61448789e2"
} }