state: generation 6123 (cycle)
This commit is contained in:
@@ -1362,7 +1362,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T08:55:29.959118+00:00",
|
||||
"generatedAt": "2026-09-12T08:58:51.326610+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 69,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -59,7 +59,7 @@
|
||||
"5": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 440,
|
||||
"listingErrors": 441,
|
||||
"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": "2026-09-12T08:55:29.933478+00:00",
|
||||
"updatedAt": "2026-09-12T08:58:51.303961+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-12T08:39:04.315696+00:00",
|
||||
"communityAttemptedAt": "2026-09-12T08:56:37.143828+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-12T08:39:04.315696+00:00",
|
||||
"communityUpdatedAt": "2026-09-12T08:56:37.143828+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-12T08:18:06.149130+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-12T08:53:48.555365+00:00",
|
||||
"generatedAt": "2026-09-12T08:56:37.143828+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 918.156862745098,
|
||||
"backlogHours": 924.3947368421053,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.1107542217613449,
|
||||
"queueFactor": 1.0018941947908158,
|
||||
"queueWeight": 1.0018941947908158,
|
||||
"recentSuccess": 56,
|
||||
"recentSuccessRate": 0.3660130718954248,
|
||||
"recentTerminal": 153,
|
||||
"recentWilsonLowerBound": 0.29383345909854114,
|
||||
"qualityFactor": 0.8675257069615422,
|
||||
"queueFactor": 1.0024901878274108,
|
||||
"queueWeight": 1.0024901878274108,
|
||||
"recentSuccess": 53,
|
||||
"recentSuccessRate": 0.34868421052631576,
|
||||
"recentTerminal": 152,
|
||||
"recentWilsonLowerBound": 0.2774998444463639,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.1128582066220818,
|
||||
"selectionWeight": 0.8696860089169838,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 25.5,
|
||||
"waiting": 23413
|
||||
"throughputPerHour": 25.333333333333332,
|
||||
"waiting": 23418
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1119.142857142857,
|
||||
"backlogHours": 1158.8450704225352,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.0073853464300855,
|
||||
"queueFactor": 0.9725827529145159,
|
||||
"queueWeight": 0.9725827529145159,
|
||||
"qualityFactor": 0.966392292896745,
|
||||
"queueFactor": 0.9690695412097734,
|
||||
"queueWeight": 0.9690695412097734,
|
||||
"recentSuccess": 52,
|
||||
"recentSuccessRate": 0.35374149659863946,
|
||||
"recentTerminal": 147,
|
||||
"recentWilsonLowerBound": 0.28107250514529913,
|
||||
"recentSuccessRate": 0.36619718309859156,
|
||||
"recentTerminal": 142,
|
||||
"recentWilsonLowerBound": 0.2914525045236429,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.9797656134767159,
|
||||
"selectionWeight": 0.9365013359061096,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.5,
|
||||
"waiting": 27419
|
||||
"throughputPerHour": 23.666666666666668,
|
||||
"waiting": 27426
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 157.0909090909091,
|
||||
"backlogHours": 163.98816568047337,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.3185492470808266,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.2215909090909091,
|
||||
"recentTerminal": 176,
|
||||
"recentWilsonLowerBound": 0.16654706350320464,
|
||||
"qualityFactor": 0.20038406823334617,
|
||||
"queueFactor": 1.2993820826856164,
|
||||
"queueWeight": 1.2993820826856164,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.1952662721893491,
|
||||
"recentTerminal": 169,
|
||||
"recentWilsonLowerBound": 0.1425546230655878,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.4141140212050746,
|
||||
"selectionWeight": 0.26037546791806204,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 29.333333333333332,
|
||||
"waiting": 4608
|
||||
"throughputPerHour": 28.166666666666668,
|
||||
"waiting": 4619
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1233.0857142857144,
|
||||
"backlogHours": 1252.3478260869565,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.5737710262641564,
|
||||
"queueFactor": 0.9585403580057731,
|
||||
"queueWeight": 0.9585403580057731,
|
||||
"qualityFactor": 0.5254532189168236,
|
||||
"queueFactor": 0.957855517443585,
|
||||
"queueWeight": 0.957855517443585,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.3142857142857143,
|
||||
"recentTerminal": 70,
|
||||
"recentWilsonLowerBound": 0.21762136964668136,
|
||||
"recentSuccessRate": 0.3188405797101449,
|
||||
"recentTerminal": 69,
|
||||
"recentWilsonLowerBound": 0.2209460520472577,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.5499826849285844,
|
||||
"selectionWeight": 0.5033082648979714,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.666666666666666,
|
||||
"waiting": 14386
|
||||
"throughputPerHour": 11.5,
|
||||
"waiting": 14402
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 442.45,
|
||||
"backlogHours": 442.7,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.3501223648884583,
|
||||
"queueFactor": 1.1178403010231714,
|
||||
"queueWeight": 1.1178403010231714,
|
||||
"qualityFactor": 0.31011940486547546,
|
||||
"queueFactor": 1.119546977610921,
|
||||
"queueWeight": 1.119546977610921,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.24166666666666667,
|
||||
"recentTerminal": 120,
|
||||
"recentWilsonLowerBound": 0.1738573324150334,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.3913808897618589,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.3471932424156406,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.0,
|
||||
"waiting": 8849
|
||||
"waiting": 8854
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 44.792792792792795,
|
||||
"backlogHours": 44.392857142857146,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -539,197 +539,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.02702702702702703,
|
||||
"recentTerminal": 333,
|
||||
"recentWilsonLowerBound": 0.014282732737124871,
|
||||
"running": 25,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.02976190476190476,
|
||||
"recentTerminal": 336,
|
||||
"recentWilsonLowerBound": 0.016244723626680543,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 55.5,
|
||||
"throughputPerHour": 56.0,
|
||||
"waiting": 2486
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 56.326829268292684,
|
||||
"backlogHours": 57.11881188118812,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.15427833744486763,
|
||||
"qualityFactor": 0.146979743135376,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 62,
|
||||
"recentSuccessRate": 0.15121951219512195,
|
||||
"recentTerminal": 410,
|
||||
"recentWilsonLowerBound": 0.11978805416912529,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.20056183867832791,
|
||||
"recentSuccess": 63,
|
||||
"recentSuccessRate": 0.15594059405940594,
|
||||
"recentTerminal": 404,
|
||||
"recentWilsonLowerBound": 0.12382173769686958,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.19107366607598883,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 68.33333333333333,
|
||||
"waiting": 3849
|
||||
"throughputPerHour": 67.33333333333333,
|
||||
"waiting": 3846
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2654.571428571429,
|
||||
"backlogHours": 3098.8,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.5211709566320335,
|
||||
"queueFactor": 0.8543980147110947,
|
||||
"queueWeight": 0.8543980147110947,
|
||||
"qualityFactor": 0.6649490972626597,
|
||||
"queueFactor": 0.8361413822705106,
|
||||
"queueWeight": 0.8361413822705106,
|
||||
"recentSuccess": 12,
|
||||
"recentSuccessRate": 0.34285714285714286,
|
||||
"recentTerminal": 35,
|
||||
"recentWilsonLowerBound": 0.20831495282688925,
|
||||
"recentSuccessRate": 0.4,
|
||||
"recentTerminal": 30,
|
||||
"recentWilsonLowerBound": 0.24590394326083398,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.44528743067149146,
|
||||
"selectionWeight": 0.5559914573247285,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.833333333333333,
|
||||
"waiting": 15485
|
||||
"throughputPerHour": 5.0,
|
||||
"waiting": 15494
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 983.4626865671643,
|
||||
"backlogHours": 955.304347826087,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.3651966224752099,
|
||||
"queueFactor": 0.9916209872444902,
|
||||
"queueWeight": 0.9916209872444902,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.26865671641791045,
|
||||
"recentTerminal": 67,
|
||||
"recentWilsonLowerBound": 0.17722065178970134,
|
||||
"qualityFactor": 0.35108453107968696,
|
||||
"queueFactor": 0.9975564636930373,
|
||||
"queueWeight": 0.9975564636930373,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.2753623188405797,
|
||||
"recentTerminal": 69,
|
||||
"recentWilsonLowerBound": 0.18394380762574333,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.362136635317221,
|
||||
"selectionWeight": 0.35022664328118075,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.166666666666666,
|
||||
"waiting": 10982
|
||||
"throughputPerHour": 11.5,
|
||||
"waiting": 10986
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 643.9245283018868,
|
||||
"backlogHours": 669.2352941176471,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.5548647539494079,
|
||||
"queueFactor": 1.0566572754165795,
|
||||
"queueWeight": 1.0566572754165795,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.29245283018867924,
|
||||
"recentTerminal": 106,
|
||||
"recentWilsonLowerBound": 0.21433210649260998,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.5863018791328721,
|
||||
"qualityFactor": 0.49212609302491056,
|
||||
"queueFactor": 1.0522572450027963,
|
||||
"queueWeight": 1.0522572450027963,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.29411764705882354,
|
||||
"recentTerminal": 102,
|
||||
"recentWilsonLowerBound": 0.2144622923532573,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.5178432468403822,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.666666666666668,
|
||||
"waiting": 11376
|
||||
"throughputPerHour": 17.0,
|
||||
"waiting": 11377
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2200.344827586207,
|
||||
"backlogHours": 2093.311475409836,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.495559786036085,
|
||||
"queueFactor": 0.8787913650215995,
|
||||
"queueWeight": 0.8787913650215995,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.5517241379310345,
|
||||
"recentTerminal": 58,
|
||||
"recentWilsonLowerBound": 0.4245185822161052,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8868163102176597,
|
||||
"queueWeight": 0.8868163102176597,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.5737704918032787,
|
||||
"recentTerminal": 61,
|
||||
"recentWilsonLowerBound": 0.44895006843512514,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.193076390863662,
|
||||
"selectionWeight": 2.2170407755441492,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.666666666666666,
|
||||
"waiting": 21270
|
||||
"throughputPerHour": 10.166666666666666,
|
||||
"waiting": 21282
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 3078.428571428571,
|
||||
"backlogHours": 3449.9999999999995,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.1086098213209822,
|
||||
"queueFactor": 0.8356223180740944,
|
||||
"queueWeight": 0.8356223180740944,
|
||||
"qualityFactor": 0.12483037823512072,
|
||||
"queueFactor": 0.8227840912050904,
|
||||
"queueWeight": 0.8227840912050904,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.21428571428571427,
|
||||
"recentTerminal": 28,
|
||||
"recentWilsonLowerBound": 0.10212321701189421,
|
||||
"recentSuccessRate": 0.24,
|
||||
"recentTerminal": 25,
|
||||
"recentWilsonLowerBound": 0.11496157730326727,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.09075679065785235,
|
||||
"selectionWeight": 0.1027084493109715,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 4.666666666666667,
|
||||
"waiting": 14366
|
||||
"throughputPerHour": 4.166666666666667,
|
||||
"waiting": 14375
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 941.470588235294,
|
||||
"backlogHours": 970.8181818181819,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 1.4287704485019928,
|
||||
"queueFactor": 0.9981329195521775,
|
||||
"queueWeight": 0.9981329195521775,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.4411764705882353,
|
||||
"recentTerminal": 68,
|
||||
"recentWilsonLowerBound": 0.329460449863809,
|
||||
"running": 17,
|
||||
"selectionWeight": 1.4261028191331682,
|
||||
"qualityFactor": 1.1260031732129372,
|
||||
"queueFactor": 0.9951488946147189,
|
||||
"queueWeight": 0.9951488946147189,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.42424242424242425,
|
||||
"recentTerminal": 66,
|
||||
"recentWilsonLowerBound": 0.31242322955377905,
|
||||
"running": 16,
|
||||
"selectionWeight": 1.1205408131555203,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.333333333333334,
|
||||
"waiting": 10670
|
||||
"throughputPerHour": 11.0,
|
||||
"waiting": 10679
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 618.1379310344828,
|
||||
"backlogHours": 634.0235294117647,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 1.063154994559514,
|
||||
"queueWeight": 1.063154994559514,
|
||||
"qualityFactor": 2.341271337581391,
|
||||
"queueFactor": 1.0608230405701924,
|
||||
"queueWeight": 1.0608230405701924,
|
||||
"recentSuccess": 46,
|
||||
"recentSuccessRate": 0.5287356321839081,
|
||||
"recentTerminal": 87,
|
||||
"recentWilsonLowerBound": 0.4248617443382648,
|
||||
"recentSuccessRate": 0.5411764705882353,
|
||||
"recentTerminal": 85,
|
||||
"recentWilsonLowerBound": 0.43576147559119544,
|
||||
"running": 6,
|
||||
"selectionWeight": 2.657887486398785,
|
||||
"selectionWeight": 2.483674579132933,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.5,
|
||||
"waiting": 8963
|
||||
"throughputPerHour": 14.166666666666666,
|
||||
"waiting": 8982
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-12T08:44:52.417040+00:00",
|
||||
"queueAttemptedAt": "2026-09-12T08:56:37.143828+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-12T08:44:52.417040+00:00",
|
||||
"queueUpdatedAt": "2026-09-12T08:56:37.143828+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Iluvatar_mrv-100",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-12T08:47:45.080978+00:00",
|
||||
"lastSyncTime": "2026-09-12T08:47:44.834299+00:00",
|
||||
"generatedAt": "2026-09-12T08:56:31.046689+00:00",
|
||||
"lastSyncTime": "2026-09-12T08:56:30.820631+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1518,18 +1518,18 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 38,
|
||||
"attributableFailureCount": 39,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 38,
|
||||
"decisionTotal": 39,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 34,
|
||||
"framework_architecture_unsupported": 34,
|
||||
"framework_architecture_unsupported": 35,
|
||||
"memory_capacity": 1,
|
||||
"repository_structure": 1,
|
||||
"tokenizer_compatibility": 2
|
||||
},
|
||||
"failureCount": 72,
|
||||
"failureCount": 73,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -1539,7 +1539,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 72,
|
||||
"total": 73,
|
||||
"unresolvedFailureCount": 34
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
@@ -2394,14 +2394,14 @@
|
||||
"unresolvedFailureCount": 863
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 263,
|
||||
"decisionFailureRate": 0.9887,
|
||||
"decisionSuccessRate": 0.0113,
|
||||
"decisionTotal": 266,
|
||||
"attributableFailureCount": 264,
|
||||
"decisionFailureRate": 0.9888,
|
||||
"decisionSuccessRate": 0.0112,
|
||||
"decisionTotal": 267,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 198,
|
||||
"backend_operator": 34,
|
||||
"framework_architecture_unsupported": 180,
|
||||
"framework_architecture_unsupported": 181,
|
||||
"memory_capacity": 6,
|
||||
"model_load": 24,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2410,14 +2410,14 @@
|
||||
"tokenizer_compatibility": 6,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 486,
|
||||
"failureCount": 487,
|
||||
"failureRate": 0.9939,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0061,
|
||||
"total": 489,
|
||||
"total": 490,
|
||||
"unresolvedFailureCount": 222
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2522,7 +2522,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-12T08:47:45.070626+00:00",
|
||||
"generatedAt": "2026-09-12T08:56:31.042291+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2548,13 +2548,13 @@
|
||||
"unresolvedFailureCount": 63
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"attributableFailureCount": 39,
|
||||
"decisionFailureRate": 0.9512,
|
||||
"decisionSuccessRate": 0.0488,
|
||||
"decisionTotal": 41,
|
||||
"attributableFailureCount": 40,
|
||||
"decisionFailureRate": 0.9524,
|
||||
"decisionSuccessRate": 0.0476,
|
||||
"decisionTotal": 42,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 35,
|
||||
"framework_architecture_unsupported": 34,
|
||||
"framework_architecture_unsupported": 35,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 1,
|
||||
"repository_structure": 1,
|
||||
@@ -2562,14 +2562,14 @@
|
||||
"参数/模板问题": 12,
|
||||
"验证失败": 175
|
||||
},
|
||||
"failureCount": 261,
|
||||
"failureCount": 262,
|
||||
"failureRate": 0.9924,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 2,
|
||||
"successRate": 0.0076,
|
||||
"total": 263,
|
||||
"total": 264,
|
||||
"unresolvedFailureCount": 222
|
||||
},
|
||||
"Biren_166m": {
|
||||
@@ -4277,21 +4277,21 @@
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Ascend_910-b4|vllm|text-generation": {
|
||||
"attributableFailureCount": 2,
|
||||
"consecutiveFailures": 2,
|
||||
"attributableFailureCount": 3,
|
||||
"consecutiveFailures": 3,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 2,
|
||||
"decisionTotal": 3,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 18,
|
||||
"framework_architecture_unsupported": 2
|
||||
"ambiguous_runtime": 17,
|
||||
"framework_architecture_unsupported": 3
|
||||
},
|
||||
"failureCount": 20,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-12T06:59:46.603354+00:00",
|
||||
"lastTerminalAt": "2026-09-12T08:56:30.820631+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4300,7 +4300,7 @@
|
||||
"targetGpu": "Ascend_910-b4",
|
||||
"taskType": "text-generation",
|
||||
"total": 20,
|
||||
"unresolvedFailureCount": 18
|
||||
"unresolvedFailureCount": 17
|
||||
},
|
||||
"Biren_166m|unknown|text-generation": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -7183,17 +7183,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1706,
|
||||
"totalRecords": 1793,
|
||||
"terminalRecords": 1707,
|
||||
"totalRecords": 1794,
|
||||
"totals": {
|
||||
"attributableFailureCount": 472,
|
||||
"decisionFailureRate": 0.8922,
|
||||
"decisionSuccessRate": 0.1078,
|
||||
"decisionTotal": 529,
|
||||
"attributableFailureCount": 473,
|
||||
"decisionFailureRate": 0.8925,
|
||||
"decisionSuccessRate": 0.1075,
|
||||
"decisionTotal": 530,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 399,
|
||||
"backend_operator": 42,
|
||||
"framework_architecture_unsupported": 288,
|
||||
"framework_architecture_unsupported": 289,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 70,
|
||||
"platform_infrastructure": 4,
|
||||
@@ -7203,20 +7203,21 @@
|
||||
"参数/模板问题": 101,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1649,
|
||||
"failureCount": 1650,
|
||||
"failureRate": 0.9666,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 57,
|
||||
"successRate": 0.0334,
|
||||
"total": 1706,
|
||||
"total": 1707,
|
||||
"unresolvedFailureCount": 1173
|
||||
},
|
||||
"warnings": [
|
||||
"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 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 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。",
|
||||
@@ -7225,7 +7226,6 @@
|
||||
"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 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|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。",
|
||||
@@ -7247,6 +7247,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1793,
|
||||
"summarizedRecords": 1794,
|
||||
"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", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-12T08:56:30.820631+00:00", "modelId": "amd/Qwen-2.5-1.5B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:55:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079114", "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": "2026-09-12T08:47:44.834299+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:41:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523323", "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": "2026-09-12T08:38:57.213433+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T08:35:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523313", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-12T08:20:40.114700+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-12T08:17:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523325", "taskType": "text-generation", "verifyResult": 1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"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", "framework": "vllm", "lastSyncTime": "2026-09-08T18:40:55.416591+00:00", "modelId": "amd/Phi-3.5-mini-instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:37:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080043", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "no_idle_device", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T18:32:01.542091+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Thinking-SFT", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:27:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152885", "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": "2026-09-08T18:12:11.499754+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:05:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4460344", "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": "2026-09-08T18:12:11.499780+00:00", "modelId": "ModelCloud.AI/Qwen2.5-0.5B-Instruct-gptqmodel-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T18:03:22+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079264", "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": "8c7908e88a27463338f6218a3ee6809193ea206cfcbe5310ce966564c89b5a35",
|
||||
".modelhub_state/architecture_history_backfill.json": "6addf18b92c64491ca0f01f9b92d97fd7f9837736ffde823e13448ef795ca23c",
|
||||
".modelhub_state/market_intelligence.json": "4dd006beade68dca33fa80a0fc469270b272cde899484c704206075ce3bc8d2a",
|
||||
".modelhub_state/official_capabilities.json": "3f5077165c4b3848132e94dbf2df0abff5fbca778f772b39290cea695cbdbf1c",
|
||||
".modelhub_state/outcome_checkpoint.json": "1cbfc54d6807200122a231e694e59059486319702b7ce72f8fd2155b569e1415",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "89125e882ad1166cbb91ee240a11e5c195bf08599b902252a74712acf3983a57",
|
||||
".modelhub_state/architecture_history_backfill.json": "371a9a4651127548f0549095f44940f9c4b42b9d9099ac3c73f20297af22e5df",
|
||||
".modelhub_state/market_intelligence.json": "510572675082fd0cbdff6efd4b85489265d492e48de77b3e0a465768d6eb4972",
|
||||
".modelhub_state/official_capabilities.json": "6afbfe75af9c41692def426d1e158522245f80ecce3f101a50c9a533bd32a5f6",
|
||||
".modelhub_state/outcome_checkpoint.json": "33345b8cdf4261df4ca9da31897014b46f4e18f3219be95c43c8a5af0e8f95ad",
|
||||
".modelhub_state/queue_cleanup_latest.json": "6b05059de615759adb561da08f7e955c6aa7fc0a1781227efab19cf90b539800",
|
||||
".modelhub_state/recent_outcomes.jsonl": "f3142235f4c2aff3032775656a21b179bb82c53a4f701266dcd41c7675d4301f",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "6481f8f799c3b83c28dae5595c7367f6694073bbd47ea15153a9a54372355a57",
|
||||
".modelhub_state/recovery_intents.jsonl": "28e5868aa1ae868de6ccb5e03e48c54be8d3f73f68d3eb0dae2d842f9a846d97",
|
||||
".modelhub_state/recent_outcomes.jsonl": "1e95194ab02d07033c6d936c90142af36bcdb0f002e5eff0a379a5737416a847",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "c08d7661747afc85c07e74aea2397a2b3ad967ed86a86d4af9aec11fda746d9c",
|
||||
".modelhub_state/recovery_intents.jsonl": "08d1ffab1bbf4a81d6b28a1e1767af5290e92764de810bbfd0cdb497b558fe11",
|
||||
".modelhub_state/routing_intelligence.json": "2855b5a64db2097d238c63bc8e3c9527429b37e5743e8c4067b04a47b96bf6d5",
|
||||
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
|
||||
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
|
||||
"ledger/submissions.jsonl": "fce27fb2f360720694402834960f8bd72b07cc9cdb7df41af2ff877c48deb61a",
|
||||
"outcomes/submissions.jsonl": "c1fb4ffb5f8805609635341d14f8a0d312d7065898c795a6d23cb2b73c0d9814"
|
||||
},
|
||||
"generation": 6122,
|
||||
"generation": 6123,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-12T08:55:30.122896+00:00",
|
||||
"updatedAt": "2026-09-12T08:58:52.512080+00:00",
|
||||
"writerId": "e5dd59a4c84a4f21926bad61448789e2"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user