state: generation 6374 (cycle)

This commit is contained in:
2026-09-12 21:32:20 +00:00
parent 4292806846
commit 8623c45bcc
9 changed files with 2556 additions and 2624 deletions

View File

@@ -1429,7 +1429,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-12T21:27:40.564457+00:00", "generatedAt": "2026-09-12T21:32:19.979071+00:00",
"summary": { "summary": {
"activeBlockCount": 72, "activeBlockCount": 72,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": { "2": {
"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": 2, "nextAccountIndex": 3,
"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": "2026-09-12T21:27:40.542131+00:00", "updatedAt": "2026-09-12T21:32:19.953875+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,121 +416,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T21:25:11.674585+00:00", "generatedAt": "2026-09-12T21:28:47.218483+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 984.7605633802816, "backlogHours": 951.1428571428571,
"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": 0.937493598462123, "qualityFactor": 0.9998115623826191,
"queueFactor": 0.9921811710185267, "queueFactor": 0.9918387432666254,
"queueWeight": 0.9921811710185267, "queueWeight": 0.9918387432666254,
"recentSuccess": 48, "recentSuccess": 49,
"recentSuccessRate": 0.3380281690140845, "recentSuccessRate": 0.3333333333333333,
"recentTerminal": 142, "recentTerminal": 147,
"recentWilsonLowerBound": 0.26540265673385566, "recentWilsonLowerBound": 0.26222862590583235,
"running": 8, "running": 8,
"selectionWeight": 0.9301634963445216, "selectionWeight": 0.9916518435370182,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.666666666666668, "throughputPerHour": 24.5,
"waiting": 23306 "waiting": 23303
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1181.3525179856115, "backlogHours": 1156.225352112676,
"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": 1.3334739410235286, "qualityFactor": 1.389872273753939,
"queueFactor": 0.9654585912852688, "queueFactor": 0.9632112762111852,
"queueWeight": 0.9654585912852688, "queueWeight": 0.9632112762111852,
"recentSuccess": 54, "recentSuccess": 54,
"recentSuccessRate": 0.38848920863309355, "recentSuccessRate": 0.38028169014084506,
"recentTerminal": 139, "recentTerminal": 142,
"recentWilsonLowerBound": 0.3115000309736299, "recentWilsonLowerBound": 0.30458316031697674,
"running": 8, "running": 8,
"selectionWeight": 1.2874138726161914, "selectionWeight": 1.3387406465730733,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.166666666666668, "throughputPerHour": 23.666666666666668,
"waiting": 27368 "waiting": 27364
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 158.0701754385965, "backlogHours": 155.20689655172413,
"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": 0.23259348406714728, "qualityFactor": 0.26472700803352767,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 33, "recentSuccess": 34,
"recentSuccessRate": 0.19298245614035087, "recentSuccessRate": 0.19540229885057472,
"recentTerminal": 171, "recentTerminal": 174,
"recentWilsonLowerBound": 0.14084347623053362, "recentWilsonLowerBound": 0.14333520447497392,
"running": 8, "running": 8,
"selectionWeight": 0.3023715292872915, "selectionWeight": 0.344145110443586,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 28.5, "throughputPerHour": 29.0,
"waiting": 4505 "waiting": 4501
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1373.8095238095239, "backlogHours": 1331.353846153846,
"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": 0.44437184837729454, "qualityFactor": 0.5259797088325607,
"queueFactor": 0.9438470001211279, "queueFactor": 0.9430482353735623,
"queueWeight": 0.9438470001211279, "queueWeight": 0.9430482353735623,
"recentSuccess": 18, "recentSuccess": 19,
"recentSuccessRate": 0.2857142857142857, "recentSuccessRate": 0.2923076923076923,
"recentTerminal": 63, "recentTerminal": 65,
"recentWilsonLowerBound": 0.18903043457341692, "recentWilsonLowerBound": 0.19583261556264242,
"running": 7, "running": 7,
"selectionWeight": 0.4194190360291901, "selectionWeight": 0.4960242362568465,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.5, "throughputPerHour": 10.833333333333334,
"waiting": 14425 "waiting": 14423
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 411.65625, "backlogHours": 418.04761904761904,
"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": 0.29084675323658055, "qualityFactor": 0.3300970921176338,
"queueFactor": 1.1308639798898459, "queueFactor": 1.1220031293510107,
"queueWeight": 1.1308639798898459, "queueWeight": 1.1220031293510107,
"recentSuccess": 28, "recentSuccess": 28,
"recentSuccessRate": 0.21875, "recentSuccessRate": 0.2222222222222222,
"recentTerminal": 128, "recentTerminal": 126,
"recentWilsonLowerBound": 0.1559042491230976, "recentWilsonLowerBound": 0.1584594242584552,
"running": 7, "running": 7,
"selectionWeight": 0.3289081169031594, "selectionWeight": 0.37036997034565394,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 21.333333333333332, "throughputPerHour": 21.0,
"waiting": 8782 "waiting": 8779
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 42.603550295857985, "backlogHours": 41.98250728862974,
"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": 13, "recentSuccess": 12,
"recentSuccessRate": 0.038461538461538464, "recentSuccessRate": 0.03498542274052478,
"recentTerminal": 338, "recentTerminal": 343,
"recentWilsonLowerBound": 0.022612432521327438, "recentWilsonLowerBound": 0.020124217684249053,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 56.333333333333336, "throughputPerHour": 57.166666666666664,
"waiting": 2400 "waiting": 2400
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 121.39393939393939, "backlogHours": 117.19024390243904,
"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": 0.05062152569425524, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 21, "recentSuccess": 19,
"recentSuccessRate": 0.10606060606060606, "recentSuccessRate": 0.09268292682926829,
"recentTerminal": 198, "recentTerminal": 205,
"recentWilsonLowerBound": 0.07042200910563365, "recentWilsonLowerBound": 0.060137857862294974,
"running": 7, "running": 5,
"selectionWeight": 0.06580798340253181, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 33.0, "throughputPerHour": 34.166666666666664,
"waiting": 4006 "waiting": 4004
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2328.0, "backlogHours": 2270.7804878048782,
"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": 0.628815010053308, "qualityFactor": 0.792151843886698,
"queueFactor": 0.872053504737986, "queueFactor": 0.8704656910004319,
"queueWeight": 0.872053504737986, "queueWeight": 0.8704656910004319,
"recentSuccess": 14, "recentSuccess": 15,
"recentSuccessRate": 0.35, "recentSuccessRate": 0.36585365853658536,
"recentTerminal": 40, "recentTerminal": 41,
"recentWilsonLowerBound": 0.22134333171049148, "recentWilsonLowerBound": 0.23589630416936813,
"running": 2, "running": 2,
"selectionWeight": 0.5483603333488392, "selectionWeight": 0.6895410021661008,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.666666666666667, "throughputPerHour": 6.833333333333333,
"waiting": 15520 "waiting": 15517
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 892.3783783783783, "backlogHours": 880.32,
"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": 0.30692243944105474, "qualityFactor": 0.3259321450363538,
"queueFactor": 1.0069507329585525, "queueFactor": 1.0034179043592284,
"queueWeight": 1.0069507329585525, "queueWeight": 1.0034179043592284,
"recentSuccess": 18, "recentSuccess": 18,
"recentSuccessRate": 0.24324324324324326, "recentSuccessRate": 0.24,
"recentTerminal": 74, "recentTerminal": 75,
"recentWilsonLowerBound": 0.1597637123272753, "recentWilsonLowerBound": 0.1575474872875825,
"running": 7, "running": 8,
"selectionWeight": 0.309055775356597, "selectionWeight": 0.3270461499356862,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.333333333333334, "throughputPerHour": 12.5,
"waiting": 11006 "waiting": 11004
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 756.4666666666667, "backlogHours": 747.8901098901099,
"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": 0.38330791384333485, "qualityFactor": 0.4092684421245577,
"queueFactor": 1.0322196180050311, "queueFactor": 1.0282583924472537,
"queueWeight": 1.0322196180050311, "queueWeight": 1.0282583924472537,
"recentSuccess": 23, "recentSuccess": 23,
"recentSuccessRate": 0.25555555555555554, "recentSuccessRate": 0.25274725274725274,
"recentTerminal": 90, "recentTerminal": 91,
"recentWilsonLowerBound": 0.176746361356073, "recentWilsonLowerBound": 0.17472595343886432,
"running": 4, "running": 6,
"selectionWeight": 0.3956579484056725, "selectionWeight": 0.42083371037838957,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.0, "throughputPerHour": 15.166666666666666,
"waiting": 11347 "waiting": 11343
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2041.5238095238096, "backlogHours": 2108.16393442623,
"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": 1.8089925228174175, "qualityFactor": 1.9504686940284832,
"queueFactor": 0.889400585140462, "queueFactor": 0.8802221124036301,
"queueWeight": 0.889400585140462, "queueWeight": 0.8802221124036301,
"recentSuccess": 30, "recentSuccess": 29,
"recentSuccessRate": 0.47619047619047616, "recentSuccessRate": 0.47540983606557374,
"recentTerminal": 63, "recentTerminal": 61,
"recentWilsonLowerBound": 0.35781921387369653, "recentWilsonLowerBound": 0.3553028228679598,
"running": 4, "running": 5,
"selectionWeight": 1.6089190083085319, "selectionWeight": 1.7168456740349012,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.5, "throughputPerHour": 10.166666666666666,
"waiting": 21436 "waiting": 21433
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 3607.25, "backlogHours": 3462.72,
"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": 0.5694715811369364, "qualityFactor": 0.5660390782832585,
"queueFactor": 0.8166089621416694, "queueFactor": 0.8170814012947899,
"queueWeight": 0.8166089621416694, "queueWeight": 0.8170814012947899,
"recentSuccess": 9, "recentSuccess": 9,
"recentSuccessRate": 0.375, "recentSuccessRate": 0.36,
"recentTerminal": 24, "recentTerminal": 25,
"recentWilsonLowerBound": 0.21159133433631455, "recentWilsonLowerBound": 0.20247656431735636,
"running": 2, "running": 2,
"selectionWeight": 0.46503559684140916, "selectionWeight": 0.46250000327129615,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 4.0, "throughputPerHour": 4.166666666666667,
"waiting": 14429 "waiting": 14428
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 976.7272727272727, "backlogHours": 920.8285714285714,
"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": 0.3991592952782042, "qualityFactor": 0.5106699407748767,
"queueFactor": 0.9934009730505168, "queueFactor": 0.996669374263508,
"queueWeight": 0.9934009730505168, "queueWeight": 0.996669374263508,
"recentSuccess": 18, "recentSuccess": 20,
"recentSuccessRate": 0.2727272727272727, "recentSuccessRate": 0.2857142857142857,
"recentTerminal": 66, "recentTerminal": 70,
"recentWilsonLowerBound": 0.180032031620791, "recentWilsonLowerBound": 0.19322076591803128,
"running": 16, "running": 16,
"selectionWeight": 0.3965252323315266, "selectionWeight": 0.5089690903272791,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.0, "throughputPerHour": 11.666666666666666,
"waiting": 10744 "waiting": 10743
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 629.4606741573034, "backlogHours": 636.4090909090909,
"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": 1.0610730591427577, "queueFactor": 1.053458605436425,
"queueWeight": 1.0610730591427577, "queueWeight": 1.053458605436425,
"recentSuccess": 46, "recentSuccess": 44,
"recentSuccessRate": 0.5168539325842697, "recentSuccessRate": 0.5,
"recentTerminal": 89, "recentTerminal": 88,
"recentWilsonLowerBound": 0.41450403725039653, "recentWilsonLowerBound": 0.3977398665504473,
"running": 6, "running": 7,
"selectionWeight": 2.6526826478568943, "selectionWeight": 2.6336465135910627,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.833333333333334, "throughputPerHour": 14.666666666666666,
"waiting": 9337 "waiting": 9334
} }
}, },
"queueAttemptedAt": "2026-09-12T21:18:32.327630+00:00", "queueAttemptedAt": "2026-09-12T21:28:47.218483+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-12T21:18:32.327630+00:00", "queueUpdatedAt": "2026-09-12T21:28:47.218483+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": "2026-09-12T20:49:10.669850+00:00", "generatedAt": "2026-09-12T21:28:41.538560+00:00",
"lastSyncTime": "2026-09-12T20:49:10.452723+00:00", "lastSyncTime": "2026-09-12T21:28:41.303490+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1911,30 +1911,30 @@
"unresolvedFailureCount": 7 "unresolvedFailureCount": 7
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 90, "attributableFailureCount": 91,
"decisionFailureRate": 0.8738, "decisionFailureRate": 0.8667,
"decisionSuccessRate": 0.1262, "decisionSuccessRate": 0.1333,
"decisionTotal": 103, "decisionTotal": 105,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 20, "ambiguous_runtime": 20,
"framework_architecture_unsupported": 49, "framework_architecture_unsupported": 49,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 40, "model_load": 41,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"参数/模板问题": 2, "参数/模板问题": 2,
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 160, "failureCount": 161,
"failureRate": 0.9249, "failureRate": 0.92,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 13, "successCount": 14,
"successRate": 0.0751, "successRate": 0.08,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 173, "total": 175,
"unresolvedFailureCount": 69 "unresolvedFailureCount": 69
}, },
"Iluvatar_mrv-100|vllm|text-generation": { "Iluvatar_mrv-100|vllm|text-generation": {
@@ -2437,29 +2437,29 @@
"unresolvedFailureCount": 8 "unresolvedFailureCount": 8
}, },
"unknown": { "unknown": {
"attributableFailureCount": 147, "attributableFailureCount": 148,
"decisionFailureRate": 0.7387, "decisionFailureRate": 0.7363,
"decisionSuccessRate": 0.2613, "decisionSuccessRate": 0.2637,
"decisionTotal": 199, "decisionTotal": 201,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 136, "ambiguous_runtime": 136,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 93, "framework_architecture_unsupported": 93,
"memory_capacity": 5, "memory_capacity": 5,
"model_load": 42, "model_load": 43,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"tokenizer_compatibility": 3, "tokenizer_compatibility": 3,
"参数/模板问题": 59, "参数/模板问题": 59,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1016, "failureCount": 1017,
"failureRate": 0.9513, "failureRate": 0.9505,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 52, "successCount": 53,
"successRate": 0.0487, "successRate": 0.0495,
"total": 1068, "total": 1070,
"unresolvedFailureCount": 868 "unresolvedFailureCount": 868
}, },
"vllm": { "vllm": {
@@ -2591,7 +2591,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-12T20:49:10.666114+00:00", "generatedAt": "2026-09-12T21:28:41.534086+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 30, "attributableFailureCount": 30,
@@ -2755,27 +2755,27 @@
"unresolvedFailureCount": 44 "unresolvedFailureCount": 44
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"attributableFailureCount": 91, "attributableFailureCount": 92,
"decisionFailureRate": 0.875, "decisionFailureRate": 0.8679,
"decisionSuccessRate": 0.125, "decisionSuccessRate": 0.1321,
"decisionTotal": 104, "decisionTotal": 106,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 20, "ambiguous_runtime": 20,
"framework_architecture_unsupported": 49, "framework_architecture_unsupported": 49,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 41, "model_load": 42,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"参数/模板问题": 2, "参数/模板问题": 2,
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 161, "failureCount": 162,
"failureRate": 0.9253, "failureRate": 0.9205,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 13, "successCount": 14,
"successRate": 0.0747, "successRate": 0.0795,
"total": 174, "total": 176,
"unresolvedFailureCount": 69 "unresolvedFailureCount": 69
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
@@ -4602,30 +4602,30 @@
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 14, "attributableFailureCount": 14,
"consecutiveFailures": 2, "consecutiveFailures": 1,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8235, "decisionFailureRate": 0.7778,
"decisionSuccessRate": 0.1765, "decisionSuccessRate": 0.2222,
"decisionTotal": 17, "decisionTotal": 18,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 3, "ambiguous_runtime": 2,
"framework_architecture_unsupported": 1, "framework_architecture_unsupported": 1,
"model_load": 13 "model_load": 13
}, },
"failureCount": 17, "failureCount": 16,
"failureRate": 0.85, "failureRate": 0.8,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T09:54:24.312986+00:00", "lastTerminalAt": "2026-09-12T21:28:41.303467+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 3, "successCount": 4,
"successRate": 0.15, "successRate": 0.2,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 20, "total": 20,
"unresolvedFailureCount": 3 "unresolvedFailureCount": 2
}, },
"Kunlunxin_p-800|unknown|text-generation": { "Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -4660,9 +4660,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 8 "ambiguous_runtime": 6
}, },
"failureCount": 8, "failureCount": 6,
"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": 8, "total": 6,
"unresolvedFailureCount": 8 "unresolvedFailureCount": 6
}, },
"MetaX_c-500|vllm|text-generation": { "MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6, "attributableFailureCount": 6,
@@ -4966,31 +4966,6 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|phi3small|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": "2026-09-09T11:30:49.443166+00:00",
"modelType": "phi3small",
"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,
@@ -5066,31 +5041,6 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|starcoder2|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": "2026-09-09T16:50:57.939999+00:00",
"modelType": "starcoder2",
"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
},
"Mthreads_s4000|vllm|text-generation|zaya|none": { "Mthreads_s4000|vllm|text-generation|zaya|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"consecutiveFailures": 0, "consecutiveFailures": 0,
@@ -7346,19 +7296,19 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1737, "terminalRecords": 1739,
"totalRecords": 1824, "totalRecords": 1826,
"totals": { "totals": {
"attributableFailureCount": 495, "attributableFailureCount": 496,
"decisionFailureRate": 0.8967, "decisionFailureRate": 0.8953,
"decisionSuccessRate": 0.1033, "decisionSuccessRate": 0.1047,
"decisionTotal": 552, "decisionTotal": 554,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 407, "ambiguous_runtime": 407,
"backend_operator": 42, "backend_operator": 42,
"framework_architecture_unsupported": 308, "framework_architecture_unsupported": 308,
"memory_capacity": 11, "memory_capacity": 11,
"model_load": 72, "model_load": 73,
"platform_infrastructure": 4, "platform_infrastructure": 4,
"repository_structure": 8, "repository_structure": 8,
"runtime_memory": 6, "runtime_memory": 6,
@@ -7366,20 +7316,21 @@
"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": 1680, "failureCount": 1681,
"failureRate": 0.9672, "failureRate": 0.9666,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 4, "platformFailureCount": 4,
"successCount": 57, "successCount": 58,
"successRate": 0.0328, "successRate": 0.0334,
"total": 1737, "total": 1739,
"unresolvedFailureCount": 1181 "unresolvedFailureCount": 1181
}, },
"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。",
@@ -7388,7 +7339,6 @@
"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。",
@@ -7411,6 +7361,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1824, "summarizedRecords": 1826,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,5 @@
{"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": "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}
{"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": "", "lastSyncTime": "2026-09-12T20:28:29.094162+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T20:23:21+00:00", "targetGpu": "Biren_166m", "taskId": "4111539", "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": "", "lastSyncTime": "2026-09-12T20:28:29.094162+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Llama-70B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T20:23:21+00:00", "targetGpu": "Biren_166m", "taskId": "4111539", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-12T19:23:45.302791+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T19:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4583368", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-12T19:23:45.302791+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T19:13:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4583368", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +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": "2026-09-09T13:57:00.114030+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} {"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}
{"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": "2026-09-09T16:50:57.939999+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "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", "recentProfileFeedback": {"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": "2026-09-07T06:07:37.712079+00:00", "modelType": "starcoder2", "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}, "repositoryOnDiskBytes": 17788663591}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.889698+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729518", "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": "2026-09-09T11:30:49.443166+00:00", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3SmallForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8630134648, "estimatedRequiredGiB": 9.647, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3small", "modelscopeFileSize": 8632060880, "modelscopeLicense": "mit", "modelscopeParams": 7803314176, "modelscopeTags": ["license:mit", "model_type:phi3small", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8632060880}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:51.888188+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729519", "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": "f69a3237acd372e591f1fca417894bce44e2d0299280acf4f6973bc3fc901f6f", ".modelhub_state/architecture_compatibility_blacklist.json": "ca592bf9f4d182b03c6d138edbf7c64bf5e854164e0cbacf4d5e51334a600a0c",
".modelhub_state/architecture_history_backfill.json": "0859a440bb69209fb428d2107ad25f363b661c08e34a9293ded401708f36c77e", ".modelhub_state/architecture_history_backfill.json": "00f30bbc7802ec2f3799e2669ee65da262c3ce663331fd5701b580a3acff8269",
".modelhub_state/market_intelligence.json": "2e3f573a5dafa5ca362ec03362f3041c2155cb8e2a5535984241ea62b1b0673e", ".modelhub_state/market_intelligence.json": "7f231fa8141d96684306b6e8e15230ca0f446c5ca7a8e3749a5bea5490d7b61d",
".modelhub_state/official_capabilities.json": "1a7133af6993dfadcafc4846034f3a1b8f59cb3bc154345d81af860ee32c13f8", ".modelhub_state/official_capabilities.json": "9ed4d2554615d82b112ac4a4a81d0a981f6f12b62d3a2ca1e4bad1073007e57e",
".modelhub_state/outcome_checkpoint.json": "5deb99b07fbef0684cb30ba353b458bef9d8ee9f65f07d9d313e87ba8cdffef9", ".modelhub_state/outcome_checkpoint.json": "4769a34c49858203721726945d10df81f346aaaa98191d1e189b0259d0f44f57",
".modelhub_state/queue_cleanup_latest.json": "1138f6ff3d4a387f335781418eae5f60d8291f48eb315007dba62a41d3ea4742", ".modelhub_state/queue_cleanup_latest.json": "1138f6ff3d4a387f335781418eae5f60d8291f48eb315007dba62a41d3ea4742",
".modelhub_state/recent_outcomes.jsonl": "cdee684132d57bfd4a56d6829ac020663cd4a0702e4681bced23314cf669ab10", ".modelhub_state/recent_outcomes.jsonl": "b69ea854994ffeb3486cd7834d0494c159f9277e91a782ae4b38f7a9626ac583",
".modelhub_state/recovery_active_tasks.jsonl": "34af069044dc571d5eb8b510567c30d22df6d62208aec5c8752655573d052f00", ".modelhub_state/recovery_active_tasks.jsonl": "a3a82c12a5ed483efaaf45e5063fb6669ea2239a5da4b5da763cb4b516df6fbc",
".modelhub_state/recovery_intents.jsonl": "510384c899b5a00f298379917b9f3bb1cbd1491b8740814b7d3cfbcf11a3b2f1", ".modelhub_state/recovery_intents.jsonl": "d1ba7097ca253b850404045b0e3942e96006f11601d1c4e9173956a273338a79",
".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": 6373, "generation": 6374,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-12T21:27:40.633548+00:00", "updatedAt": "2026-09-12T21:32:20.711581+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2" "writerId": "e5dd59a4c84a4f21926bad61448789e2"
} }