state: generation 7615 (cycle)
This commit is contained in:
@@ -1589,7 +1589,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-15T09:11:59.502404+00:00",
|
||||
"generatedAt": "2026-09-15T09:15:52.978387+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 78,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -59,7 +59,7 @@
|
||||
"5": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 553,
|
||||
"listingErrors": 554,
|
||||
"nextPage": 1,
|
||||
"recordsScanned": 0,
|
||||
"uniqueRecords": 0
|
||||
@@ -102,12 +102,12 @@
|
||||
"cutoffAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"failureLogsInspected": 0,
|
||||
"mode": "incremental_decision_only",
|
||||
"nextAccountIndex": 5,
|
||||
"nextAccountIndex": 6,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-15T09:11:59.477356+00:00",
|
||||
"updatedAt": "2026-09-15T09:15:52.949339+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,51 +416,51 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-15T09:09:57.409580+00:00",
|
||||
"generatedAt": "2026-09-15T09:13:08.258566+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 997.7323943661971,
|
||||
"backlogHours": 997.6478873239436,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.4189204388250787,
|
||||
"queueFactor": 0.9809844833546184,
|
||||
"queueWeight": 0.9809844833546184,
|
||||
"qualityFactor": 1.3131234821973183,
|
||||
"queueFactor": 0.9802911921392758,
|
||||
"queueWeight": 0.9802911921392758,
|
||||
"recentSuccess": 45,
|
||||
"recentSuccessRate": 0.31690140845070425,
|
||||
"recentTerminal": 142,
|
||||
"recentWilsonLowerBound": 0.2460579755145257,
|
||||
"running": 10,
|
||||
"selectionWeight": 1.3919389336021282,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.2872433837892863,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.666666666666668,
|
||||
"waiting": 23613
|
||||
"waiting": 23611
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1234.2794117647059,
|
||||
"backlogHours": 1252.7462686567164,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.9523141759763283,
|
||||
"queueFactor": 0.9501719954563009,
|
||||
"queueWeight": 0.9501719954563009,
|
||||
"qualityFactor": 1.8696202450780888,
|
||||
"queueFactor": 0.9473756672337409,
|
||||
"queueWeight": 0.9473756672337409,
|
||||
"recentSuccess": 49,
|
||||
"recentSuccessRate": 0.3602941176470588,
|
||||
"recentTerminal": 136,
|
||||
"recentWilsonLowerBound": 0.2844681556350323,
|
||||
"recentSuccessRate": 0.3656716417910448,
|
||||
"recentTerminal": 134,
|
||||
"recentWilsonLowerBound": 0.2889258915556576,
|
||||
"running": 9,
|
||||
"selectionWeight": 1.8550342563450517,
|
||||
"selectionWeight": 1.7712327271545645,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.666666666666668,
|
||||
"waiting": 27977
|
||||
"throughputPerHour": 22.333333333333332,
|
||||
"waiting": 27978
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
@@ -470,15 +470,15 @@
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 1,
|
||||
"qualityFactor": 0.30648912023109937,
|
||||
"queueFactor": 1.0374585123416544,
|
||||
"queueWeight": 1.0374585123416544,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.21739130434782608,
|
||||
"qualityFactor": 0.37452666922588207,
|
||||
"queueFactor": 1.0367121373025912,
|
||||
"queueWeight": 1.0367121373025912,
|
||||
"recentSuccess": 11,
|
||||
"recentSuccessRate": 0.2391304347826087,
|
||||
"recentTerminal": 46,
|
||||
"recentWilsonLowerBound": 0.1226077461858075,
|
||||
"recentWilsonLowerBound": 0.13912036561131397,
|
||||
"running": 1,
|
||||
"selectionWeight": 0.3179697467238588,
|
||||
"selectionWeight": 0.3882763437299848,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.666666666666667,
|
||||
@@ -486,51 +486,51 @@
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1590.3103448275863,
|
||||
"backlogHours": 1677.0545454545456,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.8200575666955073,
|
||||
"queueFactor": 0.9147279857960631,
|
||||
"queueWeight": 0.9147279857960631,
|
||||
"qualityFactor": 0.8583665081306685,
|
||||
"queueFactor": 0.9068169210973464,
|
||||
"queueWeight": 0.9068169210973464,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.29310344827586204,
|
||||
"recentTerminal": 58,
|
||||
"recentWilsonLowerBound": 0.19178027828644717,
|
||||
"recentSuccessRate": 0.3090909090909091,
|
||||
"recentTerminal": 55,
|
||||
"recentWilsonLowerBound": 0.20282124520577244,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.7501296062202021,
|
||||
"selectionWeight": 0.7783812740761331,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.666666666666666,
|
||||
"throughputPerHour": 9.166666666666666,
|
||||
"waiting": 15373
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 482.4827586206897,
|
||||
"backlogHours": 478.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.14305804447782153,
|
||||
"queueFactor": 1.0939361626363868,
|
||||
"queueWeight": 1.0939361626363868,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.13793103448275862,
|
||||
"recentTerminal": 116,
|
||||
"recentWilsonLowerBound": 0.08671766101537676,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.15649636821033364,
|
||||
"qualityFactor": 0.15346049656096578,
|
||||
"queueFactor": 1.0946808207417276,
|
||||
"queueWeight": 1.0946808207417276,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.1452991452991453,
|
||||
"recentTerminal": 117,
|
||||
"recentWilsonLowerBound": 0.09273862287355038,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.16799026232679107,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.333333333333332,
|
||||
"waiting": 9328
|
||||
"throughputPerHour": 19.5,
|
||||
"waiting": 9321
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 56.00696864111498,
|
||||
"backlogHours": 57.22419928825622,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -540,196 +540,196 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.05574912891986063,
|
||||
"recentTerminal": 287,
|
||||
"recentWilsonLowerBound": 0.03460322204448632,
|
||||
"recentSuccessRate": 0.05693950177935943,
|
||||
"recentTerminal": 281,
|
||||
"recentWilsonLowerBound": 0.03534846792920131,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 47.833333333333336,
|
||||
"waiting": 2679
|
||||
"throughputPerHour": 46.833333333333336,
|
||||
"waiting": 2680
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 113.06493506493507,
|
||||
"backlogHours": 116.13333333333334,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.49703725201452575,
|
||||
"qualityFactor": 0.6035612088797733,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 46,
|
||||
"recentSuccessRate": 0.19913419913419914,
|
||||
"recentTerminal": 231,
|
||||
"recentWilsonLowerBound": 0.15274274124216144,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.6461484276188835,
|
||||
"recentSuccess": 50,
|
||||
"recentSuccessRate": 0.2222222222222222,
|
||||
"recentTerminal": 225,
|
||||
"recentWilsonLowerBound": 0.17281843222320528,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.7846295715437053,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 38.5,
|
||||
"waiting": 4353
|
||||
"throughputPerHour": 37.5,
|
||||
"waiting": 4355
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2729.8285714285716,
|
||||
"backlogHours": 2582.27027027027,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.2426012413449155,
|
||||
"queueFactor": 0.8435172002110888,
|
||||
"queueWeight": 0.8435172002110888,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.37142857142857144,
|
||||
"recentTerminal": 35,
|
||||
"recentWilsonLowerBound": 0.2316560736889106,
|
||||
"qualityFactor": 1.2503279757488368,
|
||||
"queueFactor": 0.8499657764049287,
|
||||
"queueWeight": 0.8499657764049287,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.3783783783783784,
|
||||
"recentTerminal": 37,
|
||||
"recentWilsonLowerBound": 0.2406378746389103,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.0481555200780865,
|
||||
"selectionWeight": 1.0627359886681629,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.833333333333333,
|
||||
"throughputPerHour": 6.166666666666667,
|
||||
"waiting": 15924
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 742.9677419354839,
|
||||
"backlogHours": 742.8387096774194,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.43491780108607414,
|
||||
"queueFactor": 1.025342018872176,
|
||||
"queueWeight": 1.025342018872176,
|
||||
"qualityFactor": 0.40248964057818504,
|
||||
"queueFactor": 1.0246310550973088,
|
||||
"queueWeight": 1.0246310550973088,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.21505376344086022,
|
||||
"recentTerminal": 93,
|
||||
"recentWilsonLowerBound": 0.14374913397362912,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.4459394962090427,
|
||||
"selectionWeight": 0.4124033850913623,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.5,
|
||||
"waiting": 11516
|
||||
"waiting": 11514
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 758.0,
|
||||
"backlogHours": 749.6808510638298,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.6357208037484641,
|
||||
"queueFactor": 1.0222658858302898,
|
||||
"queueWeight": 1.0222658858302898,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.24731182795698925,
|
||||
"recentTerminal": 93,
|
||||
"recentWilsonLowerBound": 0.17082099814063503,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.6498756905846674,
|
||||
"qualityFactor": 0.6440291824551023,
|
||||
"queueFactor": 1.0232228522546747,
|
||||
"queueWeight": 1.0232228522546747,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.2553191489361702,
|
||||
"recentTerminal": 94,
|
||||
"recentWilsonLowerBound": 0.1779922418978549,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.6589853770069561,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.5,
|
||||
"waiting": 11749
|
||||
"throughputPerHour": 15.666666666666666,
|
||||
"waiting": 11745
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1734.3703703703704,
|
||||
"backlogHours": 1734.2962962962963,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9029069005132161,
|
||||
"queueWeight": 0.9029069005132161,
|
||||
"recentSuccess": 34,
|
||||
"recentSuccessRate": 0.41975308641975306,
|
||||
"queueFactor": 0.9022631058398901,
|
||||
"queueWeight": 0.9022631058398901,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.43209876543209874,
|
||||
"recentTerminal": 81,
|
||||
"recentWilsonLowerBound": 0.3183079093457035,
|
||||
"recentWilsonLowerBound": 0.32971902770593203,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.2572672512830403,
|
||||
"selectionWeight": 2.255657764599725,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.5,
|
||||
"waiting": 23414
|
||||
"waiting": 23413
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 3515.3076923076924,
|
||||
"backlogHours": 3385.1111111111113,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.8422306095457572,
|
||||
"queueFactor": 0.812119142351949,
|
||||
"queueWeight": 0.812119142351949,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.34615384615384615,
|
||||
"recentTerminal": 26,
|
||||
"recentWilsonLowerBound": 0.1941201497285213,
|
||||
"qualityFactor": 0.9790875771197365,
|
||||
"queueFactor": 0.8161420496948925,
|
||||
"queueWeight": 0.8161420496948925,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.37037037037037035,
|
||||
"recentTerminal": 27,
|
||||
"recentWilsonLowerBound": 0.21532287067936856,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.6839916002868597,
|
||||
"selectionWeight": 0.7990745420213078,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 4.333333333333333,
|
||||
"throughputPerHour": 4.5,
|
||||
"waiting": 15233
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1456.7547169811319,
|
||||
"backlogHours": 1544.28,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.16292677081177348,
|
||||
"queueFactor": 0.9268432342550259,
|
||||
"queueWeight": 0.9268432342550259,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.16981132075471697,
|
||||
"recentTerminal": 53,
|
||||
"recentWilsonLowerBound": 0.09199841772223753,
|
||||
"running": 17,
|
||||
"selectionWeight": 0.1510075752059115,
|
||||
"qualityFactor": 0.23443237175124518,
|
||||
"queueFactor": 0.9181059175249032,
|
||||
"queueWeight": 0.9181059175249032,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.2,
|
||||
"recentTerminal": 50,
|
||||
"recentWilsonLowerBound": 0.11243629945973886,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.21523374776421617,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.833333333333334,
|
||||
"waiting": 12868
|
||||
"throughputPerHour": 8.333333333333334,
|
||||
"waiting": 12869
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 748.9514563106795,
|
||||
"backlogHours": 734.6857142857143,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 1.1187280899629624,
|
||||
"queueFactor": 1.0241090371493269,
|
||||
"queueWeight": 1.0241090371493269,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.30097087378640774,
|
||||
"recentTerminal": 103,
|
||||
"recentWilsonLowerBound": 0.22085799615777002,
|
||||
"qualityFactor": 1.077465097691056,
|
||||
"queueFactor": 1.026328654543586,
|
||||
"queueWeight": 1.026328654543586,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.3047619047619048,
|
||||
"recentTerminal": 105,
|
||||
"recentWilsonLowerBound": 0.22490075875702692,
|
||||
"running": 6,
|
||||
"selectionWeight": 1.1456995470438749,
|
||||
"selectionWeight": 1.105833304030935,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.166666666666668,
|
||||
"throughputPerHour": 17.5,
|
||||
"waiting": 12857
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-15T09:00:55.659924+00:00",
|
||||
"queueAttemptedAt": "2026-09-15T09:13:08.258566+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-15T09:00:55.659924+00:00",
|
||||
"queueUpdatedAt": "2026-09-15T09:13:08.258566+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Iluvatar_mrv-100",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-15T09:03:42.046409+00:00",
|
||||
"lastSyncTime": "2026-09-15T09:03:41.806180+00:00",
|
||||
"generatedAt": "2026-09-15T09:13:01.586487+00:00",
|
||||
"lastSyncTime": "2026-09-15T09:13:01.342842+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2077,13 +2077,13 @@
|
||||
"unresolvedFailureCount": 7
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 100,
|
||||
"decisionFailureRate": 0.8696,
|
||||
"decisionSuccessRate": 0.1304,
|
||||
"decisionTotal": 115,
|
||||
"attributableFailureCount": 101,
|
||||
"decisionFailureRate": 0.8707,
|
||||
"decisionSuccessRate": 0.1293,
|
||||
"decisionTotal": 116,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 23,
|
||||
"framework_architecture_unsupported": 55,
|
||||
"framework_architecture_unsupported": 56,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 43,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2091,17 +2091,17 @@
|
||||
"参数/模板问题": 3,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 174,
|
||||
"failureRate": 0.9206,
|
||||
"failureCount": 175,
|
||||
"failureRate": 0.9211,
|
||||
"framework": "unknown",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 15,
|
||||
"successRate": 0.0794,
|
||||
"successRate": 0.0789,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 189,
|
||||
"total": 190,
|
||||
"unresolvedFailureCount": 73
|
||||
},
|
||||
"Iluvatar_mrv-100|vllm|text-generation": {
|
||||
@@ -2606,14 +2606,14 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"unknown": {
|
||||
"attributableFailureCount": 167,
|
||||
"decisionFailureRate": 0.7455,
|
||||
"decisionSuccessRate": 0.2545,
|
||||
"decisionTotal": 224,
|
||||
"attributableFailureCount": 168,
|
||||
"decisionFailureRate": 0.7467,
|
||||
"decisionSuccessRate": 0.2533,
|
||||
"decisionTotal": 225,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 156,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 108,
|
||||
"framework_architecture_unsupported": 109,
|
||||
"memory_capacity": 5,
|
||||
"model_load": 45,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2621,14 +2621,14 @@
|
||||
"参数/模板问题": 66,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1063,
|
||||
"failureRate": 0.9491,
|
||||
"failureCount": 1064,
|
||||
"failureRate": 0.9492,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 57,
|
||||
"successRate": 0.0509,
|
||||
"total": 1120,
|
||||
"successRate": 0.0508,
|
||||
"total": 1121,
|
||||
"unresolvedFailureCount": 895
|
||||
},
|
||||
"vllm": {
|
||||
@@ -2764,7 +2764,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-15T09:03:42.041766+00:00",
|
||||
"generatedAt": "2026-09-15T09:13:01.579682+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 40,
|
||||
@@ -2930,13 +2930,13 @@
|
||||
"unresolvedFailureCount": 48
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"attributableFailureCount": 103,
|
||||
"decisionFailureRate": 0.8729,
|
||||
"decisionSuccessRate": 0.1271,
|
||||
"decisionTotal": 118,
|
||||
"attributableFailureCount": 104,
|
||||
"decisionFailureRate": 0.8739,
|
||||
"decisionSuccessRate": 0.1261,
|
||||
"decisionTotal": 119,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 23,
|
||||
"framework_architecture_unsupported": 57,
|
||||
"framework_architecture_unsupported": 58,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 44,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2944,14 +2944,14 @@
|
||||
"参数/模板问题": 3,
|
||||
"验证失败": 47
|
||||
},
|
||||
"failureCount": 177,
|
||||
"failureRate": 0.9219,
|
||||
"failureCount": 178,
|
||||
"failureRate": 0.9223,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 15,
|
||||
"successRate": 0.0781,
|
||||
"total": 192,
|
||||
"successRate": 0.0777,
|
||||
"total": 193,
|
||||
"unresolvedFailureCount": 73
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
@@ -5545,13 +5545,13 @@
|
||||
"decisionSuccessRate": 0.1111,
|
||||
"decisionTotal": 9,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 9,
|
||||
"ambiguous_runtime": 8,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 6,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 18,
|
||||
"failureRate": 0.9474,
|
||||
"failureCount": 17,
|
||||
"failureRate": 0.9444,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-14T18:50:27.851828+00:00",
|
||||
@@ -5559,11 +5559,11 @@
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0526,
|
||||
"successRate": 0.0556,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 19,
|
||||
"unresolvedFailureCount": 10
|
||||
"total": 18,
|
||||
"unresolvedFailureCount": 9
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
"attributableFailureCount": 6,
|
||||
@@ -5698,29 +5698,29 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Iluvatar_mrv-100|unknown|text-generation": {
|
||||
"attributableFailureCount": 12,
|
||||
"consecutiveFailures": 8,
|
||||
"attributableFailureCount": 13,
|
||||
"consecutiveFailures": 9,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.8,
|
||||
"decisionSuccessRate": 0.2,
|
||||
"decisionFailureRate": 0.8667,
|
||||
"decisionSuccessRate": 0.1333,
|
||||
"decisionTotal": 15,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4,
|
||||
"framework_architecture_unsupported": 6,
|
||||
"framework_architecture_unsupported": 7,
|
||||
"model_load": 5,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 17,
|
||||
"failureRate": 0.85,
|
||||
"failureCount": 18,
|
||||
"failureRate": 0.9,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-15T09:03:41.806180+00:00",
|
||||
"lastTerminalAt": "2026-09-15T09:13:01.342842+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 3,
|
||||
"successRate": 0.15,
|
||||
"successCount": 2,
|
||||
"successRate": 0.1,
|
||||
"targetGpu": "Iluvatar_mrv-100",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
@@ -9369,17 +9369,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1910,
|
||||
"totalRecords": 2004,
|
||||
"terminalRecords": 1911,
|
||||
"totalRecords": 2005,
|
||||
"totals": {
|
||||
"attributableFailureCount": 588,
|
||||
"decisionFailureRate": 0.8991,
|
||||
"decisionSuccessRate": 0.1009,
|
||||
"decisionTotal": 654,
|
||||
"attributableFailureCount": 589,
|
||||
"decisionFailureRate": 0.8992,
|
||||
"decisionSuccessRate": 0.1008,
|
||||
"decisionTotal": 655,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 460,
|
||||
"backend_operator": 44,
|
||||
"framework_architecture_unsupported": 382,
|
||||
"framework_architecture_unsupported": 383,
|
||||
"memory_capacity": 12,
|
||||
"model_load": 78,
|
||||
"platform_infrastructure": 7,
|
||||
@@ -9389,14 +9389,14 @@
|
||||
"参数/模板问题": 116,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1844,
|
||||
"failureRate": 0.9654,
|
||||
"failureCount": 1845,
|
||||
"failureRate": 0.9655,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 7,
|
||||
"successCount": 66,
|
||||
"successRate": 0.0346,
|
||||
"total": 1910,
|
||||
"successRate": 0.0345,
|
||||
"total": 1911,
|
||||
"unresolvedFailureCount": 1249
|
||||
},
|
||||
"warnings": [
|
||||
@@ -9435,6 +9435,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 2004,
|
||||
"summarizedRecords": 2005,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T09:13:01.342842+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4585989", "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", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "", "lastSyncTime": "2026-09-15T09:03:41.806180+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:03:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4593341", "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": "2026-09-15T08:44:38.534762+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T08:35:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4595483", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-15T08:35:00.090935+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T08:31:22+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4593061", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:33:34.200752+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:29:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505107", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:33:34.200761+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:29:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505106", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T06:11:26.144205+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:09:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610359", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T06:11:26.144180+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:05:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610355", "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
@@ -1,24 +1,24 @@
|
||||
{
|
||||
"agentVersion": "2026.09.04.4",
|
||||
"checksums": {
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "2272462b5cafbd798172ffee84a21bc6b44989bdce112c1c2d708e1450322bcd",
|
||||
".modelhub_state/architecture_history_backfill.json": "8558b5c7e4bcfb6c22f98ba9cdad30a08d950b2a2cc6130bd42243e8f797bb43",
|
||||
".modelhub_state/market_intelligence.json": "c34229266a5a53ac25440b40d71f820b47a0edf078c97bb1ce98b3c58cdad3b6",
|
||||
".modelhub_state/official_capabilities.json": "757cff2222e113f0d63b649cfe59d64ce766a790151ccbd7dc32bd6d673a031d",
|
||||
".modelhub_state/outcome_checkpoint.json": "bc357995d50763f0ba01869dd11f10a56513cfd75101b62e8b1a305690f3447b",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "d9b8a9c193712453b9b527bb28263f32a7cd2d8ad5e47eadb04885e355b6f613",
|
||||
".modelhub_state/architecture_history_backfill.json": "0cb32e9c50bd87cf4f23933c0d83c276cb7f3fc15ae331aa9d2b9985dee7dbcf",
|
||||
".modelhub_state/market_intelligence.json": "100da0d742d00d9500b3805666222fe1666632401dbab379bff75cd6c14fba02",
|
||||
".modelhub_state/official_capabilities.json": "19e283f233e99f6b8ff8a0e7bc1c5ca69e81e0ed08851ed7361e268fecf8ec5b",
|
||||
".modelhub_state/outcome_checkpoint.json": "7a44592a40a6cd89a3cf8e8da8281c091a4a626e7928551ed69278d6213e9c9e",
|
||||
".modelhub_state/queue_cleanup_latest.json": "3e511035a77fe68d9f1adfb35e149ee220beed7c3962d87b7d1892cc816fb69a",
|
||||
".modelhub_state/recent_outcomes.jsonl": "f5c122b57b0a6c7ee478e63bf3652ee7e7c75098c4b914ac38191b54771912fc",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "a64a991d0761181dc81001076f9b4a2e6e0207301768d3ba58780efebae00f3c",
|
||||
".modelhub_state/recovery_intents.jsonl": "2e097bb48ac10a309c59e405d38c0f69b5515c04473b2395a45ccacbc335b386",
|
||||
".modelhub_state/recent_outcomes.jsonl": "24354b2f111c8ca8323a4c4ed761afc5755f53095d2a02ca78c4ab6fe2408af4",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "88104f5650b1980a10c5c668e785f42541d3f77b2b2e3938c8c9b83a1507dac8",
|
||||
".modelhub_state/recovery_intents.jsonl": "9e20bc8887886ea1e4a367143d6fc8e6eb4a8b1f6294cab66a96840623e72542",
|
||||
".modelhub_state/routing_intelligence.json": "e2e6203553a870b58a0f2f64ef0b06f8d85cea236effe6439aef0de6d32972fb",
|
||||
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
|
||||
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
|
||||
"ledger/submissions.jsonl": "3e376c6c3b6907caba60d52fb21662e90c8bd63c421d517f1dad425711add699",
|
||||
"outcomes/submissions.jsonl": "ff30032fdc8c2669b97f2e7020f42866fd4dcea9be3bdc68ec77b643850e5cd8"
|
||||
},
|
||||
"generation": 7614,
|
||||
"generation": 7615,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-15T09:11:59.647226+00:00",
|
||||
"updatedAt": "2026-09-15T09:15:53.692117+00:00",
|
||||
"writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user