state: generation 5878 (cycle)
This commit is contained in:
@@ -1307,7 +1307,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-11T21:17:29.710928+00:00",
|
||||
"generatedAt": "2026-09-11T21:23:00.239836+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 66,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -27,7 +27,7 @@
|
||||
"11": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 420,
|
||||
"listingErrors": 421,
|
||||
"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": 11,
|
||||
"nextAccountIndex": 0,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-11T21:17:29.688419+00:00",
|
||||
"updatedAt": "2026-09-11T21:23:00.210790+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,8 +1,8 @@
|
||||
{
|
||||
"communityAttemptedAt": "2026-09-11T21:01:33.752450+00:00",
|
||||
"communityAttemptedAt": "2026-09-11T21:18:36.512998+00:00",
|
||||
"communityError": null,
|
||||
"communitySample": {},
|
||||
"communityUpdatedAt": "2026-09-11T21:01:33.752450+00:00",
|
||||
"communityUpdatedAt": "2026-09-11T21:18:36.512998+00:00",
|
||||
"frameworkAttemptedAt": "2026-09-11T19:41:04.394263+00:00",
|
||||
"frameworkError": null,
|
||||
"frameworkStats": {
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-11T21:15:49.554810+00:00",
|
||||
"generatedAt": "2026-09-11T21:18:36.512998+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1081.3846153846152,
|
||||
"backlogHours": 1041.0222222222221,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.7527101349347426,
|
||||
"queueFactor": 0.9761645325616338,
|
||||
"queueWeight": 0.9761645325616338,
|
||||
"qualityFactor": 0.6899937035222186,
|
||||
"queueFactor": 0.9827050367459705,
|
||||
"queueWeight": 0.9827050367459705,
|
||||
"recentSuccess": 46,
|
||||
"recentSuccessRate": 0.35384615384615387,
|
||||
"recentTerminal": 130,
|
||||
"recentWilsonLowerBound": 0.2769231466844021,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.7347689370229773,
|
||||
"recentSuccessRate": 0.34074074074074073,
|
||||
"recentTerminal": 135,
|
||||
"recentWilsonLowerBound": 0.2661860749532783,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.6780602877742901,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 21.666666666666668,
|
||||
"waiting": 23430
|
||||
"throughputPerHour": 22.5,
|
||||
"waiting": 23423
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1073.3725490196077,
|
||||
"backlogHours": 1066.3246753246754,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.7093653948918224,
|
||||
"queueFactor": 0.9772540513783177,
|
||||
"queueWeight": 0.9772540513783177,
|
||||
"recentSuccess": 52,
|
||||
"recentSuccessRate": 0.33986928104575165,
|
||||
"recentTerminal": 153,
|
||||
"recentWilsonLowerBound": 0.26955735281367826,
|
||||
"qualityFactor": 0.7337706671486404,
|
||||
"queueFactor": 0.9791714974167027,
|
||||
"queueWeight": 0.9791714974167027,
|
||||
"recentSuccess": 53,
|
||||
"recentSuccessRate": 0.34415584415584416,
|
||||
"recentTerminal": 154,
|
||||
"recentWilsonLowerBound": 0.27373391810581155,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.6932302060656136,
|
||||
"selectionWeight": 0.7184873229123871,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 25.5,
|
||||
"waiting": 27371
|
||||
"throughputPerHour": 25.666666666666668,
|
||||
"waiting": 27369
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 148.7,
|
||||
"backlogHours": 152.1818181818182,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.0894755255045615,
|
||||
"qualityFactor": 0.08516878337308448,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.15,
|
||||
"recentTerminal": 180,
|
||||
"recentWilsonLowerBound": 0.10518152965026446,
|
||||
"running": 10,
|
||||
"selectionWeight": 0.11631818315592996,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.14772727272727273,
|
||||
"recentTerminal": 176,
|
||||
"recentWilsonLowerBound": 0.10284931061739362,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.11071941838500983,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 30.0,
|
||||
"waiting": 4461
|
||||
"throughputPerHour": 29.333333333333332,
|
||||
"waiting": 4464
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1320.0,
|
||||
"backlogHours": 1280.6865671641792,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 1.0175422419084894,
|
||||
"queueFactor": 0.9474012698617742,
|
||||
"queueWeight": 0.9474012698617742,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.4307692307692308,
|
||||
"recentTerminal": 65,
|
||||
"recentWilsonLowerBound": 0.31759267537345776,
|
||||
"qualityFactor": 0.8579986930434365,
|
||||
"queueFactor": 0.95263328981264,
|
||||
"queueWeight": 0.95263328981264,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.40298507462686567,
|
||||
"recentTerminal": 67,
|
||||
"recentWilsonLowerBound": 0.2939031193036935,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.9640208121220994,
|
||||
"selectionWeight": 0.8173581176089143,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 10.833333333333334,
|
||||
"waiting": 14300
|
||||
"throughputPerHour": 11.166666666666666,
|
||||
"waiting": 14301
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 469.3274336283186,
|
||||
"backlogHours": 465.42105263157896,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.402340940928585,
|
||||
"queueFactor": 1.106365592826831,
|
||||
"queueWeight": 1.106365592826831,
|
||||
"qualityFactor": 0.39429974685103986,
|
||||
"queueFactor": 1.1088307938340942,
|
||||
"queueWeight": 1.1088307938340942,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.2831858407079646,
|
||||
"recentTerminal": 113,
|
||||
"recentWilsonLowerBound": 0.208308815973215,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.44513617362895896,
|
||||
"recentSuccessRate": 0.2807017543859649,
|
||||
"recentTerminal": 114,
|
||||
"recentWilsonLowerBound": 0.2064060006774648,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.43721170130942094,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.833333333333332,
|
||||
"waiting": 8839
|
||||
"throughputPerHour": 19.0,
|
||||
"waiting": 8843
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 88.06896551724138,
|
||||
"backlogHours": 89.71929824561404,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -539,20 +539,20 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.034482758620689655,
|
||||
"recentTerminal": 174,
|
||||
"recentWilsonLowerBound": 0.015897570022231685,
|
||||
"recentSuccess": 5,
|
||||
"recentSuccessRate": 0.029239766081871343,
|
||||
"recentTerminal": 171,
|
||||
"recentWilsonLowerBound": 0.012552617212789352,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 29.0,
|
||||
"waiting": 2554
|
||||
"throughputPerHour": 28.5,
|
||||
"waiting": 2557
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 142.08433734939757,
|
||||
"backlogHours": 142.98181818181817,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
@@ -561,175 +561,175 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.12048192771084337,
|
||||
"recentTerminal": 166,
|
||||
"recentWilsonLowerBound": 0.07936196668337014,
|
||||
"running": 6,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.11515151515151516,
|
||||
"recentTerminal": 165,
|
||||
"recentWilsonLowerBound": 0.07496929809765147,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 27.666666666666668,
|
||||
"waiting": 3931
|
||||
"throughputPerHour": 27.5,
|
||||
"waiting": 3932
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 1687.6363636363637,
|
||||
"backlogHours": 1718.7777777777778,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.08340496936478306,
|
||||
"queueFactor": 0.9131207690920663,
|
||||
"queueWeight": 0.9131207690920663,
|
||||
"qualityFactor": 0.08695779530076801,
|
||||
"queueFactor": 0.9115053509987915,
|
||||
"queueWeight": 0.9115053509987915,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.18181818181818182,
|
||||
"recentTerminal": 55,
|
||||
"recentWilsonLowerBound": 0.10187561448030713,
|
||||
"recentSuccessRate": 0.18518518518518517,
|
||||
"recentTerminal": 54,
|
||||
"recentWilsonLowerBound": 0.10382574505942958,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.07615880977247094,
|
||||
"selectionWeight": 0.0792624957277076,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.166666666666666,
|
||||
"waiting": 15470
|
||||
"throughputPerHour": 9.0,
|
||||
"waiting": 15469
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 654.12,
|
||||
"backlogHours": 674.5360824742268,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.15084680572923764,
|
||||
"queueFactor": 1.0526195650069503,
|
||||
"queueWeight": 1.0526195650069503,
|
||||
"qualityFactor": 0.16165095684134018,
|
||||
"queueFactor": 1.0487969220122215,
|
||||
"queueWeight": 1.0487969220122215,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.2,
|
||||
"recentTerminal": 100,
|
||||
"recentWilsonLowerBound": 0.1333659225590988,
|
||||
"recentSuccessRate": 0.20618556701030927,
|
||||
"recentTerminal": 97,
|
||||
"recentWilsonLowerBound": 0.13762597270753013,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.15878429902939806,
|
||||
"selectionWeight": 0.16953902597552803,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 16.666666666666668,
|
||||
"waiting": 10902
|
||||
"throughputPerHour": 16.166666666666668,
|
||||
"waiting": 10905
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 1005.7058823529411,
|
||||
"backlogHours": 1006.0588235294117,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.2325013497734505,
|
||||
"queueFactor": 0.9868460420719679,
|
||||
"queueWeight": 0.9868460420719679,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.25,
|
||||
"qualityFactor": 0.2724994352146858,
|
||||
"queueFactor": 0.9877537243581698,
|
||||
"queueWeight": 0.9877537243581698,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.2647058823529412,
|
||||
"recentTerminal": 68,
|
||||
"recentWilsonLowerBound": 0.16234881695499528,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.22944303680031986,
|
||||
"recentWilsonLowerBound": 0.17449602975254203,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.2691623320188037,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.333333333333334,
|
||||
"waiting": 11398
|
||||
"waiting": 11402
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2353.4444444444443,
|
||||
"backlogHours": 2353.222222222222,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8686892748060762,
|
||||
"queueWeight": 0.8686892748060762,
|
||||
"queueFactor": 0.8695463589163253,
|
||||
"queueWeight": 0.8695463589163253,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.6111111111111112,
|
||||
"recentTerminal": 54,
|
||||
"recentWilsonLowerBound": 0.4778805658150834,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.1717231870151905,
|
||||
"selectionWeight": 2.1738658972908134,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.0,
|
||||
"waiting": 21181
|
||||
"waiting": 21179
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 3579.5,
|
||||
"backlogHours": 3578.75,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.952512986474688,
|
||||
"queueFactor": 0.815730493196894,
|
||||
"queueWeight": 0.815730493196894,
|
||||
"queueFactor": 0.8165494260420518,
|
||||
"queueWeight": 0.8165494260420518,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.625,
|
||||
"recentTerminal": 24,
|
||||
"recentWilsonLowerBound": 0.42709619037907065,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.5927243814303376,
|
||||
"selectionWeight": 1.594323358445559,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 4.0,
|
||||
"waiting": 14318
|
||||
"waiting": 14315
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 835.76,
|
||||
"backlogHours": 847.3783783783783,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.726853959474188,
|
||||
"queueFactor": 1.0146302705137507,
|
||||
"queueWeight": 1.0146302705137507,
|
||||
"qualityFactor": 0.7500249185242146,
|
||||
"queueFactor": 1.0135159209872364,
|
||||
"queueWeight": 1.0135159209872364,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.37333333333333335,
|
||||
"recentTerminal": 75,
|
||||
"recentWilsonLowerBound": 0.27255803135314144,
|
||||
"recentSuccessRate": 0.3783783783783784,
|
||||
"recentTerminal": 74,
|
||||
"recentWilsonLowerBound": 0.2764736658122867,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.7374880295252861,
|
||||
"selectionWeight": 0.7601621960614463,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.5,
|
||||
"waiting": 10447
|
||||
"throughputPerHour": 12.333333333333334,
|
||||
"waiting": 10451
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 555.5106382978723,
|
||||
"backlogHours": 555.6382978723404,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 1.605300071103266,
|
||||
"queueFactor": 1.0787385403173264,
|
||||
"queueWeight": 1.0787385403173264,
|
||||
"recentSuccess": 46,
|
||||
"recentSuccessRate": 0.48936170212765956,
|
||||
"qualityFactor": 1.5149326121418119,
|
||||
"queueFactor": 1.0797503567099687,
|
||||
"queueWeight": 1.0797503567099687,
|
||||
"recentSuccess": 45,
|
||||
"recentSuccessRate": 0.4787234042553192,
|
||||
"recentTerminal": 94,
|
||||
"recentWilsonLowerBound": 0.3907258951395345,
|
||||
"recentWilsonLowerBound": 0.3805699633124236,
|
||||
"running": 6,
|
||||
"selectionWeight": 1.7316990554732374,
|
||||
"selectionWeight": 1.635749028351686,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.666666666666666,
|
||||
"waiting": 8703
|
||||
"waiting": 8705
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-11T21:07:06.470581+00:00",
|
||||
"queueAttemptedAt": "2026-09-11T21:18:36.512998+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-11T21:07:06.470581+00:00",
|
||||
"queueUpdatedAt": "2026-09-11T21:18:36.512998+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Iluvatar_mrv-100",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-11T20:14:35.806830+00:00",
|
||||
"lastSyncTime": "2026-09-11T20:14:35.600665+00:00",
|
||||
"generatedAt": "2026-09-11T21:18:30.623096+00:00",
|
||||
"lastSyncTime": "2026-09-11T21:18:30.415792+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2225,19 +2225,19 @@
|
||||
"unresolvedFailureCount": 8
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 36,
|
||||
"attributableFailureCount": 37,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 36,
|
||||
"decisionTotal": 37,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 16,
|
||||
"framework_architecture_unsupported": 27,
|
||||
"framework_architecture_unsupported": 28,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
"repository_structure": 3,
|
||||
"runtime_memory": 2
|
||||
},
|
||||
"failureCount": 52,
|
||||
"failureCount": 53,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2247,7 +2247,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 52,
|
||||
"total": 53,
|
||||
"unresolvedFailureCount": 16
|
||||
}
|
||||
},
|
||||
@@ -2316,14 +2316,14 @@
|
||||
"unresolvedFailureCount": 860
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 242,
|
||||
"attributableFailureCount": 243,
|
||||
"decisionFailureRate": 0.9878,
|
||||
"decisionSuccessRate": 0.0122,
|
||||
"decisionTotal": 245,
|
||||
"decisionTotal": 246,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 195,
|
||||
"backend_operator": 33,
|
||||
"framework_architecture_unsupported": 170,
|
||||
"framework_architecture_unsupported": 171,
|
||||
"memory_capacity": 6,
|
||||
"model_load": 18,
|
||||
"platform_infrastructure": 1,
|
||||
@@ -2332,14 +2332,14 @@
|
||||
"tokenizer_compatibility": 4,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 462,
|
||||
"failureRate": 0.9935,
|
||||
"failureCount": 463,
|
||||
"failureRate": 0.9936,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0065,
|
||||
"total": 465,
|
||||
"successRate": 0.0064,
|
||||
"total": 466,
|
||||
"unresolvedFailureCount": 219
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2443,7 +2443,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-11T20:14:35.802524+00:00",
|
||||
"generatedAt": "2026-09-11T21:18:30.618510+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2747,13 +2747,13 @@
|
||||
"unresolvedFailureCount": 206
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"attributableFailureCount": 39,
|
||||
"attributableFailureCount": 40,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 39,
|
||||
"decisionTotal": 40,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 18,
|
||||
"framework_architecture_unsupported": 30,
|
||||
"framework_architecture_unsupported": 31,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
"repository_structure": 3,
|
||||
@@ -2761,14 +2761,14 @@
|
||||
"参数/模板问题": 9,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 93,
|
||||
"failureCount": 94,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 93,
|
||||
"total": 94,
|
||||
"unresolvedFailureCount": 54
|
||||
}
|
||||
},
|
||||
@@ -4593,23 +4593,23 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"hygon_k100-ai|vllm|text-generation": {
|
||||
"attributableFailureCount": 4,
|
||||
"consecutiveFailures": 4,
|
||||
"attributableFailureCount": 5,
|
||||
"consecutiveFailures": 5,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 4,
|
||||
"decisionTotal": 5,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 12,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"framework_architecture_unsupported": 3,
|
||||
"repository_structure": 1,
|
||||
"runtime_memory": 1
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureCount": 17,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-10T12:23:25.501677+00:00",
|
||||
"lastTerminalAt": "2026-09-11T21:18:30.415792+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4617,7 +4617,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 16,
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 12
|
||||
}
|
||||
},
|
||||
@@ -6960,17 +6960,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1665,
|
||||
"totalRecords": 1752,
|
||||
"terminalRecords": 1666,
|
||||
"totalRecords": 1753,
|
||||
"totals": {
|
||||
"attributableFailureCount": 440,
|
||||
"decisionFailureRate": 0.8889,
|
||||
"decisionSuccessRate": 0.1111,
|
||||
"decisionTotal": 495,
|
||||
"attributableFailureCount": 441,
|
||||
"decisionFailureRate": 0.8891,
|
||||
"decisionSuccessRate": 0.1109,
|
||||
"decisionTotal": 496,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 394,
|
||||
"backend_operator": 40,
|
||||
"framework_architecture_unsupported": 275,
|
||||
"framework_architecture_unsupported": 276,
|
||||
"memory_capacity": 11,
|
||||
"model_load": 61,
|
||||
"platform_infrastructure": 4,
|
||||
@@ -6980,31 +6980,30 @@
|
||||
"参数/模板问题": 99,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1610,
|
||||
"failureCount": 1611,
|
||||
"failureRate": 0.967,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 55,
|
||||
"successRate": 0.033,
|
||||
"total": 1665,
|
||||
"total": 1666,
|
||||
"unresolvedFailureCount": 1166
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Vastai_va16 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 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 MetaX_c-500 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 Iluvatar_bi-150 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-x8 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 Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Cambricon_mlu-370-x8 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。",
|
||||
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
"组合 Mthreads_s4000|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 Cambricon_mlu-370-x8|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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -7019,10 +7018,11 @@
|
||||
"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 Iluvatar_bi-150|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 Vastai_va16|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 Cambricon_mlu-370-x4|unknown|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。"
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1752,
|
||||
"summarizedRecords": 1753,
|
||||
"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": "2026-09-11T21:18:30.415792+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T21:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080096", "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", "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-11T20:14:35.600665+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T20:07:21+00:00", "targetGpu": "Iluvatar_bi-100", "taskId": "4080034", "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", "framework": "vllm", "lastSyncTime": "2026-09-11T20:03:23.495341+00:00", "modelId": "amd/Qwen2.5-7B-Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T19:59:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079943", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-11T18:23:30.509203+00:00", "modelId": "LiquidAI/LFM2-2.6B-Transcript-GGUF", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-11T18:21:22+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079227", "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": "2026-09-08T11:18:26.601968+00:00", "modelId": "amd/Qwen2.5-Coder-7B-Instruct-onnx-ryzenai-npu", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:53:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079200", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T10:53:19.117704+00:00", "modelId": "BAAI/AquilaDense-7B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:51:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079198", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T10:53:19.117664+00:00", "modelId": "mlx-community/Ornith-1.0-9B-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:39:21+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4080189", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T10:53:19.117686+00:00", "modelId": "ModelCloud.AI/Qwen2.5-0.5B-Instruct-gptqmodel-4bit", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:35:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4080017", "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": "c59cfaa5cd9e5de2682089129e504d7287aa2a99ffa16b595cb0b2cc35601c53",
|
||||
".modelhub_state/architecture_history_backfill.json": "3c42bada0c61ae5217e0869af4d045e1e13702668ee9c1c1a4ae358747a104d5",
|
||||
".modelhub_state/market_intelligence.json": "0adada5d68607d47b2f2e1acac119537b6f2a4de1d74f1e81afb80afdd53b02c",
|
||||
".modelhub_state/official_capabilities.json": "5f3664206bb1d76c7afa662c597c0e8d826b1744034607c2fc616137b18b0f04",
|
||||
".modelhub_state/outcome_checkpoint.json": "014f8a2455be0cfd1a8501719da688ca7ca1d104664da85485f2d525e886f4cd",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "20929746d64561737249a936152d32ad4bef7bdb041051a0a339e8329e400dab",
|
||||
".modelhub_state/architecture_history_backfill.json": "6f812a7f3614b56a83f7eea1971218417e04d8ffa42cbc7a09e12be8d4546b96",
|
||||
".modelhub_state/market_intelligence.json": "5451082eb74f269ed47d42ce070c1c1dc03719c8c33f0f15e91938c5412159fb",
|
||||
".modelhub_state/official_capabilities.json": "8f9db55e3df5b92b76870918aedda90557c0df54b164ade58c15646e0e6f4eb6",
|
||||
".modelhub_state/outcome_checkpoint.json": "885b54de9f69d531dd5fee8df767afbbcb6a69604d18e9b3de82a929769b3f4a",
|
||||
".modelhub_state/queue_cleanup_latest.json": "aef9d56345e6e6b2c6e9bcc5c224abe9dc0699f57e994e20e663ac3e21dd4b56",
|
||||
".modelhub_state/recent_outcomes.jsonl": "0c0089683190e9c3458f7155e642dec540718ef12e799fb0a9fef3506152743c",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "25349f2bc2462184f7c6c965b013e43783b89773d79e37720c0ca8832bbe8656",
|
||||
".modelhub_state/recovery_intents.jsonl": "5a473f9ff28a622dc35231f40bfdf74dea3c2b3fd17f27a38d9559e2dcb1b96c",
|
||||
".modelhub_state/recent_outcomes.jsonl": "374788dcd5e51ea79a1810300aef95739e97ea4ec2b73174c2c83d9f03ebdc82",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "5ed1131ea3945885312db4885530827e04ca6942abbc62abaf8a6e422a136ae0",
|
||||
".modelhub_state/recovery_intents.jsonl": "0a5e260fdfe71e1b048a6d0bb15206ccbd3cce8607922b745701763df34d2218",
|
||||
".modelhub_state/routing_intelligence.json": "2da3713196ca1e91894849ef085aa23e7bbbe62f73e4798de45905af36ff3d02",
|
||||
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
|
||||
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
|
||||
"ledger/submissions.jsonl": "3ab3b5a7948321363483df7e744cbfbeffd1d760cd4f71f95cc60aff52bdf233",
|
||||
"outcomes/submissions.jsonl": "7c95d20dc8045bece4b2a76fc32adf6b921687d867ac930b1920289c4b9b4510"
|
||||
},
|
||||
"generation": 5877,
|
||||
"generation": 5878,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-11T21:17:29.779658+00:00",
|
||||
"updatedAt": "2026-09-11T21:23:00.813071+00:00",
|
||||
"writerId": "18252d8a8ef94333abd55823b2d81c42"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user