state: generation 9694 (cycle)
This commit is contained in:
@@ -1764,7 +1764,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T07:14:00.517868+00:00",
|
||||
"generatedAt": "2026-09-19T07:17:36.538603+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 85,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
"10": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 706,
|
||||
"listingErrors": 707,
|
||||
"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": 10,
|
||||
"nextAccountIndex": 11,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-19T07:14:00.491462+00:00",
|
||||
"updatedAt": "2026-09-19T07:17:36.515101+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-19T07:11:15.197067+00:00",
|
||||
"generatedAt": "2026-09-19T07:15:11.969448+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 959.6301369863014,
|
||||
"backlogHours": 972.8333333333334,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.138720578018583,
|
||||
"queueFactor": 1.012139474182232,
|
||||
"queueWeight": 1.012139474182232,
|
||||
"recentSuccess": 48,
|
||||
"recentSuccessRate": 0.3287671232876712,
|
||||
"recentTerminal": 146,
|
||||
"recentWilsonLowerBound": 0.2578113384821702,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.1525440470762158,
|
||||
"qualityFactor": 1.0421206501151286,
|
||||
"queueFactor": 1.011124635232316,
|
||||
"queueWeight": 1.011124635232316,
|
||||
"recentSuccess": 47,
|
||||
"recentSuccessRate": 0.3263888888888889,
|
||||
"recentTerminal": 144,
|
||||
"recentWilsonLowerBound": 0.2551815623223416,
|
||||
"running": 9,
|
||||
"selectionWeight": 1.0537138622157234,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 24.333333333333332,
|
||||
"waiting": 23351
|
||||
"throughputPerHour": 24.0,
|
||||
"waiting": 23348
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1378.3140495867767,
|
||||
"backlogHours": 1390.05,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.9586359627373366,
|
||||
"queueWeight": 0.9586359627373366,
|
||||
"recentSuccess": 55,
|
||||
"recentSuccessRate": 0.45454545454545453,
|
||||
"recentTerminal": 121,
|
||||
"recentWilsonLowerBound": 0.3685867066649213,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.3965899068433414,
|
||||
"queueFactor": 0.958420059631003,
|
||||
"queueWeight": 0.958420059631003,
|
||||
"recentSuccess": 56,
|
||||
"recentSuccessRate": 0.4666666666666667,
|
||||
"recentTerminal": 120,
|
||||
"recentWilsonLowerBound": 0.37982764246169837,
|
||||
"running": 9,
|
||||
"selectionWeight": 2.3960501490775075,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.166666666666668,
|
||||
"waiting": 27796
|
||||
"throughputPerHour": 20.0,
|
||||
"waiting": 27801
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 172.7116564417178,
|
||||
"backlogHours": 173.96296296296296,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.2179935298210736,
|
||||
"qualityFactor": 0.1879464203700776,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.17177914110429449,
|
||||
"recentTerminal": 163,
|
||||
"recentWilsonLowerBound": 0.12160470906368633,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.2833915887673957,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.16666666666666666,
|
||||
"recentTerminal": 162,
|
||||
"recentWilsonLowerBound": 0.11714404789856393,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.2443303464811009,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 27.166666666666668,
|
||||
"waiting": 4692
|
||||
"throughputPerHour": 27.0,
|
||||
"waiting": 4697
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1304.5074626865671,
|
||||
"backlogHours": 1507.7586206896553,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.3596450850371864,
|
||||
"queueFactor": 0.9665825703516872,
|
||||
"queueWeight": 0.9665825703516872,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.23880597014925373,
|
||||
"recentTerminal": 67,
|
||||
"recentWilsonLowerBound": 0.15268010510617858,
|
||||
"qualityFactor": 0.3218241063702397,
|
||||
"queueFactor": 0.9468053104790353,
|
||||
"queueWeight": 0.9468053104790353,
|
||||
"recentSuccess": 14,
|
||||
"recentSuccessRate": 0.2413793103448276,
|
||||
"recentTerminal": 58,
|
||||
"recentWilsonLowerBound": 0.14958739726966278,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.34762667070959474,
|
||||
"selectionWeight": 0.3047047729515129,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.166666666666666,
|
||||
"waiting": 14567
|
||||
"throughputPerHour": 9.666666666666666,
|
||||
"waiting": 14575
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 445.65,
|
||||
"backlogHours": 445.85,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.6208283271185647,
|
||||
"queueFactor": 1.1355515596778063,
|
||||
"queueWeight": 1.1355515596778063,
|
||||
"qualityFactor": 0.5811233752241883,
|
||||
"queueFactor": 1.1366640972158537,
|
||||
"queueWeight": 1.1366640972158537,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.26666666666666666,
|
||||
"recentTerminal": 120,
|
||||
"recentWilsonLowerBound": 0.19568340354111466,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.7049825751516495,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.6605420766702318,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.0,
|
||||
"waiting": 8913
|
||||
"waiting": 8917
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 64.05737704918033,
|
||||
"backlogHours": 64.46280991735537,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -539,197 +539,197 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.028688524590163935,
|
||||
"recentTerminal": 244,
|
||||
"recentWilsonLowerBound": 0.013964642892012389,
|
||||
"recentSuccess": 9,
|
||||
"recentSuccessRate": 0.0371900826446281,
|
||||
"recentTerminal": 242,
|
||||
"recentWilsonLowerBound": 0.019686831656322176,
|
||||
"running": 24,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 40.666666666666664,
|
||||
"waiting": 2605
|
||||
"throughputPerHour": 40.333333333333336,
|
||||
"waiting": 2600
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 237.1904761904762,
|
||||
"backlogHours": 240.96774193548384,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.5553907064863209,
|
||||
"queueFactor": 1.2482206345699758,
|
||||
"queueWeight": 1.2482206345699758,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.25396825396825395,
|
||||
"recentTerminal": 126,
|
||||
"recentWilsonLowerBound": 0.1860228544733811,
|
||||
"qualityFactor": 0.4959090853400935,
|
||||
"queueFactor": 1.246569859519965,
|
||||
"queueWeight": 1.246569859519965,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.25,
|
||||
"recentTerminal": 124,
|
||||
"recentWilsonLowerBound": 0.18207534390170776,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.6932501400846227,
|
||||
"selectionWeight": 0.6181853188470747,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 21.0,
|
||||
"waiting": 4981
|
||||
"throughputPerHour": 20.666666666666668,
|
||||
"waiting": 4980
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 3328.551724137931,
|
||||
"backlogHours": 3447.8571428571427,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.8595988115620004,
|
||||
"queueFactor": 0.8398807903555917,
|
||||
"queueWeight": 0.8398807903555917,
|
||||
"qualityFactor": 0.8746942176699313,
|
||||
"queueFactor": 0.8363307569505085,
|
||||
"queueWeight": 0.8363307569505085,
|
||||
"recentSuccess": 11,
|
||||
"recentSuccessRate": 0.3793103448275862,
|
||||
"recentTerminal": 29,
|
||||
"recentWilsonLowerBound": 0.2268779573086734,
|
||||
"recentSuccessRate": 0.39285714285714285,
|
||||
"recentTerminal": 28,
|
||||
"recentWilsonLowerBound": 0.23565451827580033,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.7219605292434202,
|
||||
"selectionWeight": 0.7315336771641264,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 4.833333333333333,
|
||||
"waiting": 16088
|
||||
"throughputPerHour": 4.666666666666667,
|
||||
"waiting": 16090
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 549.5478260869564,
|
||||
"backlogHours": 554.6842105263158,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.35513568223996456,
|
||||
"queueFactor": 1.1004115005841724,
|
||||
"queueWeight": 1.1004115005841724,
|
||||
"qualityFactor": 0.3390869849758045,
|
||||
"queueFactor": 1.1000276146680033,
|
||||
"queueWeight": 1.1000276146680033,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.21739130434782608,
|
||||
"recentTerminal": 115,
|
||||
"recentWilsonLowerBound": 0.15180693897797626,
|
||||
"recentSuccessRate": 0.21929824561403508,
|
||||
"recentTerminal": 114,
|
||||
"recentWilsonLowerBound": 0.15318272840957878,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.3907953890046632,
|
||||
"selectionWeight": 0.37300504724789924,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 19.166666666666668,
|
||||
"waiting": 10533
|
||||
"throughputPerHour": 19.0,
|
||||
"waiting": 10539
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 913.3972602739726,
|
||||
"backlogHours": 913.3150684931508,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.40996000074780986,
|
||||
"queueFactor": 1.0196637712808554,
|
||||
"queueWeight": 1.0196637712808554,
|
||||
"recentSuccess": 18,
|
||||
"recentSuccessRate": 0.2465753424657534,
|
||||
"qualityFactor": 0.4455234078741481,
|
||||
"queueFactor": 1.020745243217436,
|
||||
"queueWeight": 1.020745243217436,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.2602739726027397,
|
||||
"recentTerminal": 73,
|
||||
"recentWilsonLowerBound": 0.16204336317654708,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.4180213604368141,
|
||||
"recentWilsonLowerBound": 0.17342050231153916,
|
||||
"running": 5,
|
||||
"selectionWeight": 0.45476589932955824,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.166666666666666,
|
||||
"waiting": 11113
|
||||
"waiting": 11112
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1840.0298507462687,
|
||||
"backlogHours": 1927.875,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.022890283599749,
|
||||
"queueFactor": 0.9179778759627185,
|
||||
"queueWeight": 0.9179778759627185,
|
||||
"qualityFactor": 2.1114752104508736,
|
||||
"queueFactor": 0.9125331021464494,
|
||||
"queueWeight": 0.9125331021464494,
|
||||
"recentSuccess": 30,
|
||||
"recentSuccessRate": 0.44776119402985076,
|
||||
"recentTerminal": 67,
|
||||
"recentWilsonLowerBound": 0.33476201784797566,
|
||||
"running": 4,
|
||||
"selectionWeight": 1.8569685258445188,
|
||||
"recentSuccessRate": 0.46875,
|
||||
"recentTerminal": 64,
|
||||
"recentWilsonLowerBound": 0.3517578764404486,
|
||||
"running": 5,
|
||||
"selectionWeight": 1.9267910238980628,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.166666666666666,
|
||||
"waiting": 20547
|
||||
"throughputPerHour": 10.666666666666666,
|
||||
"waiting": 20564
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 8627.454545454546,
|
||||
"backlogHours": 8630.181818181818,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.3664690860214406,
|
||||
"queueFactor": 0.7280706812901704,
|
||||
"queueWeight": 0.7280706812901704,
|
||||
"qualityFactor": 1.279076828040158,
|
||||
"queueFactor": 0.7287984937415607,
|
||||
"queueWeight": 0.7287984937415607,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.5454545454545454,
|
||||
"recentTerminal": 11,
|
||||
"recentWilsonLowerBound": 0.2800877556899882,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.9948860784215867,
|
||||
"running": 3,
|
||||
"selectionWeight": 0.9321892656554005,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 1.8333333333333333,
|
||||
"waiting": 15817
|
||||
"waiting": 15822
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1656.0000000000002,
|
||||
"backlogHours": 1657.7142857142858,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.0666542133218188,
|
||||
"queueFactor": 0.9326031862436596,
|
||||
"queueWeight": 0.9326031862436596,
|
||||
"qualityFactor": 0.06239135639680789,
|
||||
"queueFactor": 0.9334348389058359,
|
||||
"queueWeight": 0.9334348389058359,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.14285714285714285,
|
||||
"recentTerminal": 49,
|
||||
"recentWilsonLowerBound": 0.07096333720544586,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.062161931720492794,
|
||||
"selectionWeight": 0.058238265707370965,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 8.166666666666666,
|
||||
"waiting": 13524
|
||||
"waiting": 13538
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 1120.4,
|
||||
"backlogHours": 1121.76,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 0.5888127561710934,
|
||||
"queueFactor": 0.9888945416264797,
|
||||
"queueWeight": 0.9888945416264797,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.28,
|
||||
"qualityFactor": 0.4187276698768985,
|
||||
"queueFactor": 0.9897498981300665,
|
||||
"queueWeight": 0.9897498981300665,
|
||||
"recentSuccess": 19,
|
||||
"recentSuccessRate": 0.25333333333333335,
|
||||
"recentTerminal": 75,
|
||||
"recentWilsonLowerBound": 0.19103020085378442,
|
||||
"recentWilsonLowerBound": 0.1685991964794815,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.5822737206176376,
|
||||
"selectionWeight": 0.41443566860490044,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.5,
|
||||
"waiting": 14005
|
||||
"waiting": 14022
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-19T07:04:43.717727+00:00",
|
||||
"queueAttemptedAt": "2026-09-19T07:15:11.969448+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-19T07:04:43.717727+00:00",
|
||||
"queueUpdatedAt": "2026-09-19T07:15:11.969448+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Kunlunxin_p-800",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-19T07:04:35.527321+00:00",
|
||||
"lastSyncTime": "2026-09-19T07:04:35.491155+00:00",
|
||||
"generatedAt": "2026-09-19T07:15:01.858041+00:00",
|
||||
"lastSyncTime": "2026-09-19T07:15:01.294906+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -1998,26 +1998,26 @@
|
||||
"unresolvedFailureCount": 60
|
||||
},
|
||||
"Biren_166m|vllm|text-generation": {
|
||||
"attributableFailureCount": 27,
|
||||
"decisionFailureRate": 0.7297,
|
||||
"decisionSuccessRate": 0.2703,
|
||||
"decisionTotal": 37,
|
||||
"attributableFailureCount": 28,
|
||||
"decisionFailureRate": 0.7368,
|
||||
"decisionSuccessRate": 0.2632,
|
||||
"decisionTotal": 38,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 21,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"model_load": 5,
|
||||
"tokenizer_compatibility": 1
|
||||
},
|
||||
"failureCount": 27,
|
||||
"failureRate": 0.7297,
|
||||
"failureCount": 28,
|
||||
"failureRate": 0.7368,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 10,
|
||||
"successRate": 0.2703,
|
||||
"successRate": 0.2632,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 37,
|
||||
"total": 38,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x4|unknown|text-generation": {
|
||||
@@ -2862,14 +2862,14 @@
|
||||
"unresolvedFailureCount": 910
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 420,
|
||||
"decisionFailureRate": 0.8842,
|
||||
"decisionSuccessRate": 0.1158,
|
||||
"decisionTotal": 475,
|
||||
"attributableFailureCount": 421,
|
||||
"decisionFailureRate": 0.8845,
|
||||
"decisionSuccessRate": 0.1155,
|
||||
"decisionTotal": 476,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 246,
|
||||
"backend_operator": 40,
|
||||
"framework_architecture_unsupported": 315,
|
||||
"framework_architecture_unsupported": 316,
|
||||
"memory_capacity": 7,
|
||||
"model_load": 32,
|
||||
"platform_infrastructure": 2,
|
||||
@@ -2878,14 +2878,14 @@
|
||||
"tokenizer_compatibility": 12,
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 708,
|
||||
"failureRate": 0.9279,
|
||||
"failureCount": 709,
|
||||
"failureRate": 0.928,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 55,
|
||||
"successRate": 0.0721,
|
||||
"total": 763,
|
||||
"successRate": 0.072,
|
||||
"total": 764,
|
||||
"unresolvedFailureCount": 286
|
||||
},
|
||||
"vllm-mlu": {
|
||||
@@ -2998,7 +2998,7 @@
|
||||
"unresolvedFailureCount": 18
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-19T07:04:35.522032+00:00",
|
||||
"generatedAt": "2026-09-19T07:15:01.851796+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 60,
|
||||
@@ -3049,14 +3049,14 @@
|
||||
"unresolvedFailureCount": 243
|
||||
},
|
||||
"Biren_166m": {
|
||||
"attributableFailureCount": 67,
|
||||
"decisionFailureRate": 0.8481,
|
||||
"decisionSuccessRate": 0.1519,
|
||||
"decisionTotal": 79,
|
||||
"attributableFailureCount": 68,
|
||||
"decisionFailureRate": 0.85,
|
||||
"decisionSuccessRate": 0.15,
|
||||
"decisionTotal": 80,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 32,
|
||||
"backend_operator": 4,
|
||||
"framework_architecture_unsupported": 50,
|
||||
"framework_architecture_unsupported": 51,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 8,
|
||||
"runtime_memory": 2,
|
||||
@@ -3064,14 +3064,14 @@
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 127,
|
||||
"failureRate": 0.9137,
|
||||
"failureCount": 128,
|
||||
"failureRate": 0.9143,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 12,
|
||||
"successRate": 0.0863,
|
||||
"total": 139,
|
||||
"successRate": 0.0857,
|
||||
"total": 140,
|
||||
"unresolvedFailureCount": 60
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
@@ -3905,6 +3905,29 @@
|
||||
"total": 2,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|muse_glimmer|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"modelType": "muse_glimmer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|nanbeige|compressed-tensors": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -9270,6 +9293,30 @@
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|muse_glimmer|none|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "muse_glimmer",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "none",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Biren_166m",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Biren_166m|vllm|text-generation|nanbeige|compressed-tensors|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -15239,17 +15286,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 2305,
|
||||
"totalRecords": 2408,
|
||||
"terminalRecords": 2306,
|
||||
"totalRecords": 2409,
|
||||
"totals": {
|
||||
"attributableFailureCount": 752,
|
||||
"decisionFailureRate": 0.8291,
|
||||
"decisionSuccessRate": 0.1709,
|
||||
"decisionTotal": 907,
|
||||
"attributableFailureCount": 753,
|
||||
"decisionFailureRate": 0.8293,
|
||||
"decisionSuccessRate": 0.1707,
|
||||
"decisionTotal": 908,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 581,
|
||||
"backend_operator": 55,
|
||||
"framework_architecture_unsupported": 503,
|
||||
"framework_architecture_unsupported": 504,
|
||||
"memory_capacity": 12,
|
||||
"model_load": 88,
|
||||
"platform_infrastructure": 11,
|
||||
@@ -15259,18 +15306,18 @@
|
||||
"参数/模板问题": 133,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 2150,
|
||||
"failureCount": 2151,
|
||||
"failureRate": 0.9328,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 11,
|
||||
"successCount": 155,
|
||||
"successRate": 0.0672,
|
||||
"total": 2305,
|
||||
"total": 2306,
|
||||
"unresolvedFailureCount": 1387
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Iluvatar_bi-150 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-b3 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 Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
@@ -15281,7 +15328,7 @@
|
||||
"GPU Sunrise_pt-200-x1 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 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。",
|
||||
"组合 MetaX_c-500|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_tokenizer_patch|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_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。",
|
||||
@@ -15306,6 +15353,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 2408,
|
||||
"summarizedRecords": 2409,
|
||||
"version": 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