state: generation 6894 (cycle)
This commit is contained in:
@@ -1494,7 +1494,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T21:26:14.317413+00:00",
|
||||
"generatedAt": "2026-09-13T21:29:15.402761+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 75,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -75,7 +75,7 @@
|
||||
"7": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 500,
|
||||
"listingErrors": 501,
|
||||
"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": 7,
|
||||
"nextAccountIndex": 8,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-13T21:26:14.290682+00:00",
|
||||
"updatedAt": "2026-09-13T21:29:15.377040+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-13T21:24:25.223600+00:00",
|
||||
"generatedAt": "2026-09-13T21:27:20.793511+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1002.9428571428572,
|
||||
"backlogHours": 981.9020979020979,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.3184011965204878,
|
||||
"queueFactor": 0.9904999933066775,
|
||||
"queueWeight": 0.9904999933066775,
|
||||
"recentSuccess": 48,
|
||||
"recentSuccessRate": 0.34285714285714286,
|
||||
"recentTerminal": 140,
|
||||
"recentWilsonLowerBound": 0.2693693683483557,
|
||||
"qualityFactor": 1.2435146340008383,
|
||||
"queueFactor": 0.9910836075129603,
|
||||
"queueWeight": 0.9910836075129603,
|
||||
"recentSuccess": 47,
|
||||
"recentSuccessRate": 0.32867132867132864,
|
||||
"recentTerminal": 143,
|
||||
"recentWilsonLowerBound": 0.2570448191429695,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.3058763763290588,
|
||||
"selectionWeight": 1.2324269694607093,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.333333333333332,
|
||||
"throughputPerHour": 23.833333333333332,
|
||||
"waiting": 23402
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1248.0,
|
||||
"backlogHours": 1286.3720930232557,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.7352295052412292,
|
||||
"queueFactor": 0.958547673827491,
|
||||
"queueWeight": 0.958547673827491,
|
||||
"recentSuccess": 51,
|
||||
"recentSuccessRate": 0.38345864661654133,
|
||||
"recentTerminal": 133,
|
||||
"recentWilsonLowerBound": 0.30519662302307843,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.6633002058058082,
|
||||
"qualityFactor": 1.7561402777059063,
|
||||
"queueFactor": 0.9517338800470447,
|
||||
"queueWeight": 0.9517338800470447,
|
||||
"recentSuccess": 49,
|
||||
"recentSuccessRate": 0.3798449612403101,
|
||||
"recentTerminal": 129,
|
||||
"recentWilsonLowerBound": 0.30071077692282255,
|
||||
"running": 9,
|
||||
"selectionWeight": 1.671378200407937,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 22.166666666666668,
|
||||
"waiting": 27664
|
||||
"throughputPerHour": 21.5,
|
||||
"waiting": 27657
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 141.54679802955664,
|
||||
"backlogHours": 145.73604060913704,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.5066303334947113,
|
||||
"qualityFactor": 0.5359195219291277,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 46,
|
||||
"recentSuccessRate": 0.22660098522167488,
|
||||
"recentTerminal": 203,
|
||||
"recentWilsonLowerBound": 0.17440135080028984,
|
||||
"recentSuccess": 45,
|
||||
"recentSuccessRate": 0.22842639593908629,
|
||||
"recentTerminal": 197,
|
||||
"recentWilsonLowerBound": 0.17532714567047353,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.6586194335431247,
|
||||
"selectionWeight": 0.6966953785078661,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 33.833333333333336,
|
||||
"waiting": 4789
|
||||
"throughputPerHour": 32.833333333333336,
|
||||
"waiting": 4785
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1426.952380952381,
|
||||
"backlogHours": 1473.4426229508197,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.5158509171556869,
|
||||
"queueFactor": 0.9394733896549833,
|
||||
"queueWeight": 0.9394733896549833,
|
||||
"recentSuccess": 17,
|
||||
"recentSuccessRate": 0.2698412698412698,
|
||||
"recentTerminal": 63,
|
||||
"recentWilsonLowerBound": 0.17583701687980416,
|
||||
"qualityFactor": 0.4090375331792554,
|
||||
"queueFactor": 0.9325465867756138,
|
||||
"queueWeight": 0.9325465867756138,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.2459016393442623,
|
||||
"recentTerminal": 61,
|
||||
"recentWilsonLowerBound": 0.15506522999562844,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.48462820969688514,
|
||||
"selectionWeight": 0.38144655542943146,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 10.5,
|
||||
"waiting": 14983
|
||||
"throughputPerHour": 10.166666666666666,
|
||||
"waiting": 14980
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 477.86086956521734,
|
||||
"backlogHours": 494.9189189189189,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.3733559719064205,
|
||||
"queueFactor": 1.1070078104571186,
|
||||
"queueWeight": 1.1070078104571186,
|
||||
"qualityFactor": 0.42308894826408155,
|
||||
"queueFactor": 1.0983491362460744,
|
||||
"queueWeight": 1.0983491362460744,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.21739130434782608,
|
||||
"recentTerminal": 115,
|
||||
"recentWilsonLowerBound": 0.15180693897797626,
|
||||
"recentSuccessRate": 0.22522522522522523,
|
||||
"recentTerminal": 111,
|
||||
"recentWilsonLowerBound": 0.15746423838098933,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.413307976981216,
|
||||
"selectionWeight": 0.46469938088111407,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.166666666666668,
|
||||
"waiting": 9159
|
||||
"throughputPerHour": 18.5,
|
||||
"waiting": 9156
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 47.009009009009006,
|
||||
"backlogHours": 46.7820895522388,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -539,16 +539,16 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.04804804804804805,
|
||||
"recentTerminal": 333,
|
||||
"recentWilsonLowerBound": 0.029788452765862887,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.04477611940298507,
|
||||
"recentTerminal": 335,
|
||||
"recentWilsonLowerBound": 0.027319653279547478,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 55.5,
|
||||
"waiting": 2609
|
||||
"throughputPerHour": 55.833333333333336,
|
||||
"waiting": 2612
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
@@ -558,15 +558,15 @@
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.19137330478420148,
|
||||
"queueFactor": 1.2806490166661049,
|
||||
"queueWeight": 1.2806490166661049,
|
||||
"qualityFactor": 0.20009270036487017,
|
||||
"queueFactor": 1.277334775845619,
|
||||
"queueWeight": 1.277334775845619,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.16428571428571428,
|
||||
"recentTerminal": 140,
|
||||
"recentWilsonLowerBound": 0.11203753808504885,
|
||||
"running": 11,
|
||||
"selectionWeight": 0.2450820345880304,
|
||||
"running": 10,
|
||||
"selectionWeight": 0.25558536456890607,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 23.333333333333332,
|
||||
@@ -580,15 +580,15 @@
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.8165897112214526,
|
||||
"queueFactor": 0.9021340143139143,
|
||||
"queueWeight": 0.9021340143139143,
|
||||
"qualityFactor": 1.899357599447942,
|
||||
"queueFactor": 0.8997993470187554,
|
||||
"queueWeight": 0.8997993470187554,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.44,
|
||||
"recentTerminal": 50,
|
||||
"recentWilsonLowerBound": 0.3116198721023535,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.6388073685455633,
|
||||
"selectionWeight": 1.709040727738369,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.333333333333334,
|
||||
@@ -596,140 +596,140 @@
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 879.2727272727273,
|
||||
"backlogHours": 868.0769230769231,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.5097627700147268,
|
||||
"queueFactor": 1.0102465244001833,
|
||||
"queueWeight": 1.0102465244001833,
|
||||
"recentSuccess": 20,
|
||||
"recentSuccessRate": 0.2597402597402597,
|
||||
"recentTerminal": 77,
|
||||
"recentWilsonLowerBound": 0.17489066479540774,
|
||||
"qualityFactor": 0.5913906755600402,
|
||||
"queueFactor": 1.0095708199954927,
|
||||
"queueWeight": 1.0095708199954927,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.2692307692307692,
|
||||
"recentTerminal": 78,
|
||||
"recentWilsonLowerBound": 0.18335480551618466,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.5149860666759877,
|
||||
"selectionWeight": 0.5970507692628382,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.833333333333334,
|
||||
"waiting": 11284
|
||||
"throughputPerHour": 13.0,
|
||||
"waiting": 11285
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 673.2815533980582,
|
||||
"backlogHours": 715.1752577319587,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.43000835555629313,
|
||||
"queueFactor": 1.0515172412888116,
|
||||
"queueWeight": 1.0515172412888116,
|
||||
"qualityFactor": 0.5156003405090499,
|
||||
"queueFactor": 1.0393424102794055,
|
||||
"queueWeight": 1.0393424102794055,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.23300970873786409,
|
||||
"recentTerminal": 103,
|
||||
"recentWilsonLowerBound": 0.16187497360880485,
|
||||
"recentSuccessRate": 0.24742268041237114,
|
||||
"recentTerminal": 97,
|
||||
"recentWilsonLowerBound": 0.172273703017395,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.4521611997656918,
|
||||
"selectionWeight": 0.5358853006455582,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.166666666666668,
|
||||
"waiting": 11558
|
||||
"throughputPerHour": 16.166666666666668,
|
||||
"waiting": 11562
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1751.3766233766232,
|
||||
"backlogHours": 1774.1842105263158,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9110432045980312,
|
||||
"queueWeight": 0.9110432045980312,
|
||||
"recentSuccess": 36,
|
||||
"recentSuccessRate": 0.4675324675324675,
|
||||
"recentTerminal": 77,
|
||||
"recentWilsonLowerBound": 0.36029890673598886,
|
||||
"queueFactor": 0.9069236238378686,
|
||||
"queueWeight": 0.9069236238378686,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.4605263157894737,
|
||||
"recentTerminal": 76,
|
||||
"recentWilsonLowerBound": 0.3530754655326989,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.277608011495078,
|
||||
"selectionWeight": 2.2673090595946714,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.833333333333334,
|
||||
"waiting": 22476
|
||||
"throughputPerHour": 12.666666666666666,
|
||||
"waiting": 22473
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 3808.695652173913,
|
||||
"backlogHours": 3369.692307692308,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.1822009274516025,
|
||||
"queueFactor": 0.8108293578267468,
|
||||
"queueWeight": 0.8108293578267468,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.43478260869565216,
|
||||
"recentTerminal": 23,
|
||||
"recentWilsonLowerBound": 0.25634368332198654,
|
||||
"qualityFactor": 0.6704814680370728,
|
||||
"queueFactor": 0.8237245015491164,
|
||||
"queueWeight": 0.8237245015491164,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.34615384615384615,
|
||||
"recentTerminal": 26,
|
||||
"recentWilsonLowerBound": 0.1941201497285213,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.9585632188277674,
|
||||
"selectionWeight": 0.5522920130567576,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 3.8333333333333335,
|
||||
"waiting": 14600
|
||||
"throughputPerHour": 4.333333333333333,
|
||||
"waiting": 14602
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1060.1142857142859,
|
||||
"backlogHours": 1045.1830985915492,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.19075158830012062,
|
||||
"queueFactor": 0.9822974176929055,
|
||||
"queueWeight": 0.9822974176929055,
|
||||
"qualityFactor": 0.19312193392998211,
|
||||
"queueFactor": 0.9818421324177159,
|
||||
"queueWeight": 0.9818421324177159,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.18571428571428572,
|
||||
"recentTerminal": 70,
|
||||
"recentWilsonLowerBound": 0.11187194691822096,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.18737479260802872,
|
||||
"recentSuccessRate": 0.18309859154929578,
|
||||
"recentTerminal": 71,
|
||||
"recentWilsonLowerBound": 0.11024622287362806,
|
||||
"running": 17,
|
||||
"selectionWeight": 0.1896152514264469,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.666666666666666,
|
||||
"throughputPerHour": 11.833333333333334,
|
||||
"waiting": 12368
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 684.4615384615385,
|
||||
"backlogHours": 659.3333333333334,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.46938897341146857,
|
||||
"queueFactor": 1.0489228541935265,
|
||||
"queueWeight": 1.0489228541935265,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.2403846153846154,
|
||||
"recentTerminal": 104,
|
||||
"recentWilsonLowerBound": 0.16845266546271026,
|
||||
"qualityFactor": 0.5532175718421878,
|
||||
"queueFactor": 1.0520945388326541,
|
||||
"queueWeight": 1.0520945388326541,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.25,
|
||||
"recentTerminal": 108,
|
||||
"recentWilsonLowerBound": 0.17787718518702555,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.49235282171772693,
|
||||
"selectionWeight": 0.5820371861214273,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.333333333333332,
|
||||
"waiting": 11864
|
||||
"throughputPerHour": 18.0,
|
||||
"waiting": 11868
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-13T21:15:44.712206+00:00",
|
||||
"queueAttemptedAt": "2026-09-13T21:27:20.793511+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-13T21:15:44.712206+00:00",
|
||||
"queueUpdatedAt": "2026-09-13T21:27:20.793511+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Iluvatar_mrv-100",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-13T21:18:48.937127+00:00",
|
||||
"lastSyncTime": "2026-09-13T21:18:48.715311+00:00",
|
||||
"generatedAt": "2026-09-13T21:27:15.319333+00:00",
|
||||
"lastSyncTime": "2026-09-13T21:27:15.041934+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2254,18 +2254,18 @@
|
||||
"unresolvedFailureCount": 34
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 49,
|
||||
"attributableFailureCount": 50,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 49,
|
||||
"decisionTotal": 50,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 6,
|
||||
"platform_infrastructure": 4,
|
||||
"tokenizer_compatibility": 41,
|
||||
"tokenizer_compatibility": 42,
|
||||
"参数/模板问题": 6
|
||||
},
|
||||
"failureCount": 59,
|
||||
"failureCount": 60,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"pendingCount": 0,
|
||||
@@ -2275,22 +2275,23 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 59,
|
||||
"total": 60,
|
||||
"unresolvedFailureCount": 6
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
"attributableFailureCount": 6,
|
||||
"attributableFailureCount": 7,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 6,
|
||||
"decisionTotal": 7,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"framework_architecture_unsupported": 2,
|
||||
"memory_capacity": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 4,
|
||||
"参数/模板问题": 2
|
||||
},
|
||||
"failureCount": 10,
|
||||
"failureCount": 11,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2300,7 +2301,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 10,
|
||||
"total": 11,
|
||||
"unresolvedFailureCount": 3
|
||||
},
|
||||
"Vastai_va16|unknown|text-generation": {
|
||||
@@ -2529,15 +2530,15 @@
|
||||
"unresolvedFailureCount": 877
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 301,
|
||||
"decisionFailureRate": 0.9901,
|
||||
"decisionSuccessRate": 0.0099,
|
||||
"decisionTotal": 304,
|
||||
"attributableFailureCount": 302,
|
||||
"decisionFailureRate": 0.9902,
|
||||
"decisionSuccessRate": 0.0098,
|
||||
"decisionTotal": 305,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 201,
|
||||
"backend_operator": 34,
|
||||
"framework_architecture_unsupported": 214,
|
||||
"memory_capacity": 6,
|
||||
"memory_capacity": 7,
|
||||
"model_load": 26,
|
||||
"platform_infrastructure": 1,
|
||||
"repository_structure": 8,
|
||||
@@ -2545,14 +2546,14 @@
|
||||
"tokenizer_compatibility": 7,
|
||||
"参数/模板问题": 24
|
||||
},
|
||||
"failureCount": 527,
|
||||
"failureRate": 0.9943,
|
||||
"failureCount": 528,
|
||||
"failureRate": 0.9944,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 3,
|
||||
"successRate": 0.0057,
|
||||
"total": 530,
|
||||
"successRate": 0.0056,
|
||||
"total": 531,
|
||||
"unresolvedFailureCount": 225
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2615,27 +2616,27 @@
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"vllm_fix_tokenizer": {
|
||||
"attributableFailureCount": 52,
|
||||
"attributableFailureCount": 53,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 52,
|
||||
"decisionTotal": 53,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 37,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"model_load": 1,
|
||||
"platform_infrastructure": 4,
|
||||
"tokenizer_compatibility": 41,
|
||||
"tokenizer_compatibility": 42,
|
||||
"参数/模板问题": 7
|
||||
},
|
||||
"failureCount": 100,
|
||||
"failureCount": 101,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 4,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 100,
|
||||
"total": 101,
|
||||
"unresolvedFailureCount": 44
|
||||
},
|
||||
"vllm_tokenizer_patch": {
|
||||
@@ -2657,7 +2658,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-13T21:18:48.933122+00:00",
|
||||
"generatedAt": "2026-09-13T21:27:15.315167+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 31,
|
||||
@@ -2917,27 +2918,28 @@
|
||||
"unresolvedFailureCount": 77
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"attributableFailureCount": 55,
|
||||
"decisionFailureRate": 0.9821,
|
||||
"decisionSuccessRate": 0.0179,
|
||||
"decisionTotal": 56,
|
||||
"attributableFailureCount": 57,
|
||||
"decisionFailureRate": 0.9828,
|
||||
"decisionSuccessRate": 0.0172,
|
||||
"decisionTotal": 58,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 1,
|
||||
"backend_operator": 2,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"memory_capacity": 1,
|
||||
"platform_infrastructure": 5,
|
||||
"tokenizer_compatibility": 45,
|
||||
"tokenizer_compatibility": 46,
|
||||
"参数/模板问题": 10,
|
||||
"验证失败": 32
|
||||
},
|
||||
"failureCount": 103,
|
||||
"failureRate": 0.9904,
|
||||
"failureCount": 105,
|
||||
"failureRate": 0.9906,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 5,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0096,
|
||||
"total": 104,
|
||||
"successRate": 0.0094,
|
||||
"total": 106,
|
||||
"unresolvedFailureCount": 43
|
||||
},
|
||||
"Vastai_va16": {
|
||||
@@ -2999,6 +3001,7 @@
|
||||
"Kunlunxin_p-800": 100.0,
|
||||
"MetaX_c-500": 64.0,
|
||||
"Mthreads_s4000": 48.0,
|
||||
"Sunrise_pt-200-x1": 64.0,
|
||||
"Vastai_va16": 32.0,
|
||||
"hygon_k100-ai": 64.0
|
||||
},
|
||||
@@ -4383,6 +4386,29 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"modelType": "starcoder2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -4990,24 +5016,24 @@
|
||||
"consecutiveFailures": 0,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"decisionSuccessRate": 1.0,
|
||||
"decisionTotal": 1,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"failureBreakdown": {
|
||||
"参数/模板问题": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 0.5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "unknown",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-13T02:55:29.910704+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.5,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 2,
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
@@ -5038,22 +5064,23 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|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": 1,
|
||||
"framework_architecture_unsupported": 1,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 3
|
||||
},
|
||||
"failureCount": 5,
|
||||
"failureCount": 6,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-13T21:09:24.912775+00:00",
|
||||
"lastTerminalAt": "2026-09-13T21:27:15.041934+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -5061,7 +5088,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 5,
|
||||
"total": 6,
|
||||
"unresolvedFailureCount": 1
|
||||
},
|
||||
"Vastai_va16|vllm|text-generation": {
|
||||
@@ -7400,6 +7427,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "starcoder2",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation|llama|compressed-tensors|30": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -7641,34 +7692,34 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1786,
|
||||
"totalRecords": 1879,
|
||||
"terminalRecords": 1788,
|
||||
"totalRecords": 1881,
|
||||
"totals": {
|
||||
"attributableFailureCount": 528,
|
||||
"decisionFailureRate": 0.8995,
|
||||
"decisionSuccessRate": 0.1005,
|
||||
"decisionTotal": 587,
|
||||
"attributableFailureCount": 530,
|
||||
"decisionFailureRate": 0.8998,
|
||||
"decisionSuccessRate": 0.1002,
|
||||
"decisionTotal": 589,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 417,
|
||||
"backend_operator": 43,
|
||||
"framework_architecture_unsupported": 335,
|
||||
"memory_capacity": 11,
|
||||
"memory_capacity": 12,
|
||||
"model_load": 74,
|
||||
"platform_infrastructure": 6,
|
||||
"repository_structure": 8,
|
||||
"runtime_memory": 6,
|
||||
"tokenizer_compatibility": 51,
|
||||
"tokenizer_compatibility": 52,
|
||||
"参数/模板问题": 103,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1727,
|
||||
"failureCount": 1729,
|
||||
"failureRate": 0.967,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 6,
|
||||
"successCount": 59,
|
||||
"successRate": 0.033,
|
||||
"total": 1786,
|
||||
"total": 1788,
|
||||
"unresolvedFailureCount": 1193
|
||||
},
|
||||
"warnings": [
|
||||
@@ -7707,6 +7758,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1879,
|
||||
"summarizedRecords": 1881,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"failReason": "memory_capacity", "failureAction": "reject_if_estimated_load_exceeds_memory", "failureCategory": "memory_capacity", "failureClassificationReason": "structured_oom", "failureCode": "PREFLIGHT_OOM", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureObservedGpuMemoryGiB": 64.0, "failureScope": "model_gpu", "framework": "vllm", "lastSyncTime": "2026-09-13T21:27:15.041934+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:21:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4581573", "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_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mellum"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T21:09:24.912761+00:00", "modelId": "JetBrains/Mellum2-12B-A2.5B-Instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4152538", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-13T21:09:24.912775+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:05:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490277", "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_fix_tokenizer", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T21:09:24.912708+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Bare-Speed-FP16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-13T21:01:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4336358", "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": "2026-09-09T18:09:45.834698+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471904", "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": "2026-09-09T18:09:45.834707+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T18:05:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471907", "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": ["rwkv7"], "framework": "", "lastSyncTime": "2026-09-09T17:42:15.798661+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T17:39:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610396", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-09T17:24:58.529030+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step240", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-09T17:23:22+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4458425", "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
Reference in New Issue
Block a user