state: generation 9539 (cycle)
This commit is contained in:
@@ -1743,7 +1743,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T00:26:53.598647+00:00",
|
||||
"generatedAt": "2026-09-19T00:29:40.126517+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 84,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -67,7 +67,7 @@
|
||||
"6": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 695,
|
||||
"listingErrors": 696,
|
||||
"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": 6,
|
||||
"nextAccountIndex": 7,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-19T00:26:53.575030+00:00",
|
||||
"updatedAt": "2026-09-19T00:29:40.098798+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-19T00:25:12.064018+00:00",
|
||||
"generatedAt": "2026-09-19T00:27:59.956012+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 575.655737704918,
|
||||
"backlogHours": 573.134693877551,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.2516392603856411,
|
||||
"queueFactor": 1.0878567965566528,
|
||||
"queueWeight": 1.0878567965566528,
|
||||
"qualityFactor": 0.2740147611051044,
|
||||
"queueFactor": 1.0850958167131879,
|
||||
"queueWeight": 1.0850958167131879,
|
||||
"recentSuccess": 44,
|
||||
"recentSuccessRate": 0.18032786885245902,
|
||||
"recentTerminal": 244,
|
||||
"recentWilsonLowerBound": 0.13716180622795038,
|
||||
"recentSuccessRate": 0.17959183673469387,
|
||||
"recentTerminal": 245,
|
||||
"recentWilsonLowerBound": 0.13658964915158467,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.27374747969100893,
|
||||
"selectionWeight": 0.29733227099281234,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 40.666666666666664,
|
||||
"waiting": 23410
|
||||
"throughputPerHour": 40.833333333333336,
|
||||
"waiting": 23403
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1187.1971830985915,
|
||||
"backlogHours": 1170.5,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.5979026987351708,
|
||||
"queueFactor": 0.9759278833293384,
|
||||
"queueWeight": 0.9759278833293384,
|
||||
"recentSuccess": 56,
|
||||
"recentSuccessRate": 0.39436619718309857,
|
||||
"recentTerminal": 142,
|
||||
"recentWilsonLowerBound": 0.3177821708116304,
|
||||
"qualityFactor": 1.623356549458683,
|
||||
"queueFactor": 0.9748793725784509,
|
||||
"queueWeight": 0.9748793725784509,
|
||||
"recentSuccess": 55,
|
||||
"recentSuccessRate": 0.3819444444444444,
|
||||
"recentTerminal": 144,
|
||||
"recentWilsonLowerBound": 0.30663220831107374,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.5594377985428527,
|
||||
"selectionWeight": 1.5825768144074,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.666666666666668,
|
||||
"waiting": 28097
|
||||
"throughputPerHour": 24.0,
|
||||
"waiting": 28092
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 260.89655172413796,
|
||||
"backlogHours": 265.10526315789474,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.21879320918555484,
|
||||
"queueFactor": 1.2249712732836942,
|
||||
"queueWeight": 1.2249712732836942,
|
||||
"qualityFactor": 0.25010858132012637,
|
||||
"queueFactor": 1.2181305676996133,
|
||||
"queueWeight": 1.2181305676996133,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.1896551724137931,
|
||||
"recentTerminal": 116,
|
||||
"recentWilsonLowerBound": 0.1287128868844165,
|
||||
"running": 10,
|
||||
"selectionWeight": 0.26801539604185476,
|
||||
"recentSuccessRate": 0.19298245614035087,
|
||||
"recentTerminal": 114,
|
||||
"recentWilsonLowerBound": 0.13103797364220363,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.30466490815003044,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.333333333333332,
|
||||
"waiting": 5044
|
||||
"throughputPerHour": 19.0,
|
||||
"waiting": 5037
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 2397.315789473684,
|
||||
"backlogHours": 2277.45,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.9929180216048226,
|
||||
"queueFactor": 0.8782888476576461,
|
||||
"queueWeight": 0.8782888476576461,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.39473684210526316,
|
||||
"recentTerminal": 38,
|
||||
"recentWilsonLowerBound": 0.2559785926361891,
|
||||
"qualityFactor": 1.162796386510741,
|
||||
"queueFactor": 0.8822451230645567,
|
||||
"queueWeight": 0.8822451230645567,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.4,
|
||||
"recentTerminal": 40,
|
||||
"recentWilsonLowerBound": 0.2634811061240136,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.8720688250138094,
|
||||
"selectionWeight": 1.0258714411161904,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.333333333333333,
|
||||
"throughputPerHour": 6.666666666666667,
|
||||
"waiting": 15183
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 519.7009345794393,
|
||||
"backlogHours": 534.6346153846155,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.2627542311302671,
|
||||
"queueFactor": 1.1046714512512936,
|
||||
"queueWeight": 1.1046714512512936,
|
||||
"qualityFactor": 0.30802929337307156,
|
||||
"queueFactor": 1.0964732296544972,
|
||||
"queueWeight": 1.0964732296544972,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.205607476635514,
|
||||
"recentTerminal": 107,
|
||||
"recentWilsonLowerBound": 0.13988321742546095,
|
||||
"recentSuccessRate": 0.21153846153846154,
|
||||
"recentTerminal": 104,
|
||||
"recentWilsonLowerBound": 0.14405120914153324,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.29025709782508996,
|
||||
"selectionWeight": 0.33774587413296436,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.833333333333332,
|
||||
"waiting": 9268
|
||||
"throughputPerHour": 17.333333333333332,
|
||||
"waiting": 9267
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 55.135714285714286,
|
||||
"backlogHours": 56.18181818181818,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -540,125 +540,125 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.03571428571428571,
|
||||
"recentTerminal": 280,
|
||||
"recentWilsonLowerBound": 0.019512721132581616,
|
||||
"recentSuccessRate": 0.03636363636363636,
|
||||
"recentTerminal": 275,
|
||||
"recentWilsonLowerBound": 0.01986961974491093,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 46.666666666666664,
|
||||
"waiting": 2573
|
||||
"throughputPerHour": 45.833333333333336,
|
||||
"waiting": 2575
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 192.0,
|
||||
"backlogHours": 191.9225806451613,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.1601705219350656,
|
||||
"queueFactor": 1.2826287511931855,
|
||||
"queueWeight": 1.2826287511931855,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.16129032258064516,
|
||||
"qualityFactor": 0.215907684796713,
|
||||
"queueFactor": 1.2786087813052456,
|
||||
"queueWeight": 1.2786087813052456,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.17419354838709677,
|
||||
"recentTerminal": 155,
|
||||
"recentWilsonLowerBound": 0.11170002806327119,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.20543931652753392,
|
||||
"recentWilsonLowerBound": 0.12256590380244957,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.2760614617323623,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 25.833333333333332,
|
||||
"waiting": 4960
|
||||
"waiting": 4958
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 3684.923076923077,
|
||||
"backlogHours": 3548.4444444444443,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8234398698324294,
|
||||
"queueWeight": 0.8234398698324294,
|
||||
"queueFactor": 0.8254692361072941,
|
||||
"queueWeight": 0.8254692361072941,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.5769230769230769,
|
||||
"recentTerminal": 26,
|
||||
"recentWilsonLowerBound": 0.3894829692111983,
|
||||
"recentSuccessRate": 0.5555555555555556,
|
||||
"recentTerminal": 27,
|
||||
"recentWilsonLowerBound": 0.3731271947957688,
|
||||
"running": 2,
|
||||
"selectionWeight": 2.0585996745810737,
|
||||
"selectionWeight": 2.063673090268235,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 4.333333333333333,
|
||||
"throughputPerHour": 4.5,
|
||||
"waiting": 15968
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 547.1186440677966,
|
||||
"backlogHours": 524.829268292683,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.2966919664238902,
|
||||
"queueFactor": 1.09618518410257,
|
||||
"queueWeight": 1.09618518410257,
|
||||
"qualityFactor": 0.29676361192092554,
|
||||
"queueFactor": 1.0995219077435308,
|
||||
"queueWeight": 1.0995219077435308,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.211864406779661,
|
||||
"recentTerminal": 118,
|
||||
"recentWilsonLowerBound": 0.14782423635341965,
|
||||
"recentSuccessRate": 0.2032520325203252,
|
||||
"recentTerminal": 123,
|
||||
"recentWilsonLowerBound": 0.1416321145776123,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.32522933783612556,
|
||||
"selectionWeight": 0.32629809272815685,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.666666666666668,
|
||||
"waiting": 10760
|
||||
"throughputPerHour": 20.5,
|
||||
"waiting": 10759
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 897.078947368421,
|
||||
"backlogHours": 908.96,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.9045660113468874,
|
||||
"queueFactor": 1.01782134737836,
|
||||
"queueWeight": 1.01782134737836,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.34210526315789475,
|
||||
"recentTerminal": 76,
|
||||
"recentWilsonLowerBound": 0.2453616992261352,
|
||||
"qualityFactor": 1.252750503914601,
|
||||
"queueFactor": 1.0125695850857703,
|
||||
"queueWeight": 1.0125695850857703,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.37333333333333335,
|
||||
"recentTerminal": 75,
|
||||
"recentWilsonLowerBound": 0.27255803135314144,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.9206865964617578,
|
||||
"selectionWeight": 1.2684970579647972,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.666666666666666,
|
||||
"waiting": 11363
|
||||
"throughputPerHour": 12.5,
|
||||
"waiting": 11362
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2069.6065573770493,
|
||||
"backlogHours": 2036.1290322580644,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.0425957191696726,
|
||||
"queueFactor": 0.8978690186595988,
|
||||
"queueWeight": 0.8978690186595988,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.47540983606557374,
|
||||
"recentTerminal": 61,
|
||||
"recentWilsonLowerBound": 0.3553028228679598,
|
||||
"qualityFactor": 2.3688155289030632,
|
||||
"queueFactor": 0.8971928409556393,
|
||||
"queueWeight": 0.8971928409556393,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.4838709677419355,
|
||||
"recentTerminal": 62,
|
||||
"recentWilsonLowerBound": 0.3640965420650529,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.8339834138891713,
|
||||
"selectionWeight": 2.1252843340763747,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 10.166666666666666,
|
||||
"waiting": 21041
|
||||
"throughputPerHour": 10.333333333333334,
|
||||
"waiting": 21040
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
@@ -668,15 +668,15 @@
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.3096402601824888,
|
||||
"queueFactor": 0.7815673033168615,
|
||||
"queueWeight": 0.7815673033168615,
|
||||
"qualityFactor": 1.4392673367239968,
|
||||
"queueFactor": 0.7790706104485285,
|
||||
"queueWeight": 0.7790706104485285,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.5,
|
||||
"recentTerminal": 18,
|
||||
"recentWilsonLowerBound": 0.2903070395897999,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.0235720064660208,
|
||||
"selectionWeight": 1.121290882620192,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 3.0,
|
||||
@@ -690,15 +690,15 @@
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.10419225533172663,
|
||||
"queueFactor": 0.8596163256416084,
|
||||
"queueWeight": 0.8596163256416084,
|
||||
"qualityFactor": 0.11450511594509541,
|
||||
"queueFactor": 0.856870307556379,
|
||||
"queueWeight": 0.856870307556379,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.1935483870967742,
|
||||
"recentTerminal": 31,
|
||||
"recentWilsonLowerBound": 0.09186883586347631,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.08956536368857113,
|
||||
"selectionWeight": 0.09811603391665275,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 5.166666666666667,
|
||||
@@ -706,30 +706,30 @@
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1121.3076923076924,
|
||||
"backlogHours": 1066.829268292683,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.8516113382040111,
|
||||
"queueFactor": 0.9843225506964657,
|
||||
"queueWeight": 0.9843225506964657,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.3333333333333333,
|
||||
"recentTerminal": 78,
|
||||
"recentWilsonLowerBound": 0.23872517005631877,
|
||||
"qualityFactor": 0.9227962428551,
|
||||
"queueFactor": 0.9885356946000066,
|
||||
"queueWeight": 0.9885356946000066,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.32926829268292684,
|
||||
"recentTerminal": 82,
|
||||
"recentWilsonLowerBound": 0.2371996746292997,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.8382602446230027,
|
||||
"selectionWeight": 0.9122170249050426,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 13.0,
|
||||
"waiting": 14577
|
||||
"throughputPerHour": 13.666666666666666,
|
||||
"waiting": 14580
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-19T00:17:14.784492+00:00",
|
||||
"queueAttemptedAt": "2026-09-19T00:27:59.956012+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-19T00:17:14.784492+00:00",
|
||||
"queueUpdatedAt": "2026-09-19T00:27:59.956012+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Kunlunxin_p-800",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user