state: generation 8647 (cycle)
This commit is contained in:
@@ -1741,7 +1741,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-17T09:09:59.825652+00:00",
|
||||
"generatedAt": "2026-09-17T09:13:20.595943+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 84,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -19,7 +19,7 @@
|
||||
"10": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 632,
|
||||
"listingErrors": 633,
|
||||
"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": "2026-09-17T09:09:59.801570+00:00",
|
||||
"updatedAt": "2026-09-17T09:13:20.569229+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-17T09:08:01.235465+00:00",
|
||||
"generatedAt": "2026-09-17T09:11:08.851921+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1107.8139534883721,
|
||||
"backlogHours": 1201.2100840336136,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.3035915520631596,
|
||||
"queueFactor": 0.988270720010001,
|
||||
"queueWeight": 0.988270720010001,
|
||||
"recentSuccess": 42,
|
||||
"recentSuccessRate": 0.32558139534883723,
|
||||
"recentTerminal": 129,
|
||||
"recentWilsonLowerBound": 0.25077958524200566,
|
||||
"qualityFactor": 1.2202114217481967,
|
||||
"queueFactor": 0.979439131135625,
|
||||
"queueWeight": 0.979439131135625,
|
||||
"recentSuccess": 39,
|
||||
"recentSuccessRate": 0.3277310924369748,
|
||||
"recentTerminal": 119,
|
||||
"recentWilsonLowerBound": 0.2499369805737803,
|
||||
"running": 9,
|
||||
"selectionWeight": 1.2883013617564134,
|
||||
"selectionWeight": 1.1951228147188195,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 21.5,
|
||||
"waiting": 23818
|
||||
"throughputPerHour": 19.833333333333332,
|
||||
"waiting": 23824
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 1496.7610619469028,
|
||||
"backlogHours": 1537.8545454545456,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 2.3732281515364226,
|
||||
"queueFactor": 0.9446546825644213,
|
||||
"queueWeight": 0.9446546825644213,
|
||||
"recentSuccess": 47,
|
||||
"recentSuccessRate": 0.415929203539823,
|
||||
"recentTerminal": 113,
|
||||
"recentWilsonLowerBound": 0.32927895669940405,
|
||||
"running": 8,
|
||||
"selectionWeight": 2.2418810861425875,
|
||||
"qualityFactor": 2.006203404503589,
|
||||
"queueFactor": 0.9438065945998133,
|
||||
"queueWeight": 0.9438065945998133,
|
||||
"recentSuccess": 44,
|
||||
"recentSuccessRate": 0.4,
|
||||
"recentTerminal": 110,
|
||||
"recentWilsonLowerBound": 0.31331775680061763,
|
||||
"running": 9,
|
||||
"selectionWeight": 1.893468003279084,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 18.833333333333332,
|
||||
"waiting": 28189
|
||||
"throughputPerHour": 18.333333333333332,
|
||||
"waiting": 28194
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 190.0,
|
||||
"backlogHours": 188.86046511627907,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 5,
|
||||
"qualityFactor": 0.3663697094824243,
|
||||
"queueFactor": 1.2874575339792815,
|
||||
"queueWeight": 1.2874575339792815,
|
||||
"qualityFactor": 0.3409665041339533,
|
||||
"queueFactor": 1.2927041361810736,
|
||||
"queueWeight": 1.2927041361810736,
|
||||
"recentSuccess": 33,
|
||||
"recentSuccessRate": 0.19298245614035087,
|
||||
"recentTerminal": 171,
|
||||
"recentWilsonLowerBound": 0.14084347623053362,
|
||||
"recentSuccessRate": 0.19186046511627908,
|
||||
"recentTerminal": 172,
|
||||
"recentWilsonLowerBound": 0.14000323744713258,
|
||||
"running": 6,
|
||||
"selectionWeight": 0.4716854426949478,
|
||||
"selectionWeight": 0.44076881019316255,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 28.5,
|
||||
"waiting": 5415
|
||||
"throughputPerHour": 28.666666666666668,
|
||||
"waiting": 5414
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 1240.135135135135,
|
||||
"backlogHours": 1176.5384615384614,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.29112914446510496,
|
||||
"queueFactor": 0.9716852300431394,
|
||||
"queueWeight": 0.9716852300431394,
|
||||
"qualityFactor": 0.2435613009217304,
|
||||
"queueFactor": 0.9824928019426701,
|
||||
"queueWeight": 0.9824928019426701,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.20270270270270271,
|
||||
"recentTerminal": 74,
|
||||
"recentWilsonLowerBound": 0.1268696381027667,
|
||||
"recentSuccessRate": 0.19230769230769232,
|
||||
"recentTerminal": 78,
|
||||
"recentWilsonLowerBound": 0.12015101048823743,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.28288588971183787,
|
||||
"selectionWeight": 0.23929722498739273,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.333333333333334,
|
||||
"throughputPerHour": 13.0,
|
||||
"waiting": 15295
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 602.0210526315789,
|
||||
"backlogHours": 614.7096774193549,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.416959355193707,
|
||||
"queueFactor": 1.0829395162722584,
|
||||
"queueWeight": 1.0829395162722584,
|
||||
"qualityFactor": 0.41272089345544083,
|
||||
"queueFactor": 1.0829783859731013,
|
||||
"queueWeight": 1.0829783859731013,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.22105263157894736,
|
||||
"recentTerminal": 95,
|
||||
"recentWilsonLowerBound": 0.14937242983925722,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.45154176241866584,
|
||||
"recentSuccessRate": 0.22580645161290322,
|
||||
"recentTerminal": 93,
|
||||
"recentWilsonLowerBound": 0.15270042020646624,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.4469678070517496,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.833333333333334,
|
||||
"waiting": 9532
|
||||
"throughputPerHour": 15.5,
|
||||
"waiting": 9528
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 29.017142857142858,
|
||||
"backlogHours": 30.047337278106507,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -540,196 +540,196 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 16,
|
||||
"recentSuccessRate": 0.030476190476190476,
|
||||
"recentTerminal": 525,
|
||||
"recentWilsonLowerBound": 0.018844606632512605,
|
||||
"running": 26,
|
||||
"recentSuccessRate": 0.03155818540433925,
|
||||
"recentTerminal": 507,
|
||||
"recentWilsonLowerBound": 0.019516799596624657,
|
||||
"running": 25,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 87.5,
|
||||
"throughputPerHour": 84.5,
|
||||
"waiting": 2539
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 88.69655172413793,
|
||||
"backlogHours": 92.38709677419355,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 50,
|
||||
"qualityFactor": 0.14025236200203867,
|
||||
"qualityFactor": 0.13408283492037218,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 36,
|
||||
"recentSuccessRate": 0.12413793103448276,
|
||||
"recentTerminal": 290,
|
||||
"recentWilsonLowerBound": 0.09103051906997917,
|
||||
"recentSuccess": 35,
|
||||
"recentSuccessRate": 0.12544802867383512,
|
||||
"recentTerminal": 279,
|
||||
"recentWilsonLowerBound": 0.09159953956635114,
|
||||
"running": 3,
|
||||
"selectionWeight": 0.18232807060265027,
|
||||
"selectionWeight": 0.17430768539648384,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 48.333333333333336,
|
||||
"waiting": 4287
|
||||
"throughputPerHour": 46.5,
|
||||
"waiting": 4296
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 2664.0,
|
||||
"backlogHours": 2740.114285714286,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 1.551144073759706,
|
||||
"queueFactor": 0.8663947661498259,
|
||||
"queueWeight": 0.8663947661498259,
|
||||
"qualityFactor": 1.5646631670646138,
|
||||
"queueFactor": 0.8654759319980893,
|
||||
"queueWeight": 0.8654759319980893,
|
||||
"recentSuccess": 15,
|
||||
"recentSuccessRate": 0.4166666666666667,
|
||||
"recentTerminal": 36,
|
||||
"recentWilsonLowerBound": 0.2714033350508729,
|
||||
"recentSuccessRate": 0.42857142857142855,
|
||||
"recentTerminal": 35,
|
||||
"recentWilsonLowerBound": 0.27984333081678914,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.3439031070497287,
|
||||
"selectionWeight": 1.3541783127783287,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 6.0,
|
||||
"throughputPerHour": 5.833333333333333,
|
||||
"waiting": 15984
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 521.6279069767442,
|
||||
"backlogHours": 529.511811023622,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.6404002289250234,
|
||||
"queueFactor": 1.1064755723310864,
|
||||
"queueWeight": 1.1064755723310864,
|
||||
"qualityFactor": 0.6257859741456816,
|
||||
"queueFactor": 1.1074877951745525,
|
||||
"queueWeight": 1.1074877951745525,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.24806201550387597,
|
||||
"recentTerminal": 129,
|
||||
"recentWilsonLowerBound": 0.1815425856479483,
|
||||
"running": 10,
|
||||
"selectionWeight": 0.7085872098207739,
|
||||
"recentSuccessRate": 0.25196850393700787,
|
||||
"recentTerminal": 127,
|
||||
"recentWilsonLowerBound": 0.18450499480603022,
|
||||
"running": 9,
|
||||
"selectionWeight": 0.6930503287577604,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 21.5,
|
||||
"waiting": 11215
|
||||
"throughputPerHour": 21.166666666666668,
|
||||
"waiting": 11208
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 940.2162162162161,
|
||||
"backlogHours": 915.1578947368422,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.9473276666416071,
|
||||
"queueFactor": 1.0128888550196773,
|
||||
"queueWeight": 1.0128888550196773,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.3108108108108108,
|
||||
"recentTerminal": 74,
|
||||
"recentWilsonLowerBound": 0.21690691603479306,
|
||||
"qualityFactor": 0.744051568024023,
|
||||
"queueFactor": 1.0202248369569957,
|
||||
"queueWeight": 1.0202248369569957,
|
||||
"recentSuccess": 22,
|
||||
"recentSuccessRate": 0.2894736842105263,
|
||||
"recentTerminal": 76,
|
||||
"recentWilsonLowerBound": 0.19960875564331393,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.9595376355930799,
|
||||
"selectionWeight": 0.7590998896749058,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.333333333333334,
|
||||
"waiting": 11596
|
||||
"throughputPerHour": 12.666666666666666,
|
||||
"waiting": 11592
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 2497.2203389830506,
|
||||
"backlogHours": 2456.1,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 2.4975590820667373,
|
||||
"queueFactor": 0.8748375660463971,
|
||||
"queueWeight": 0.8748375660463971,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.4576271186440678,
|
||||
"recentTerminal": 59,
|
||||
"recentWilsonLowerBound": 0.33701102140242434,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.8797988497906151,
|
||||
"queueWeight": 0.8797988497906151,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.4666666666666667,
|
||||
"recentTerminal": 60,
|
||||
"recentWilsonLowerBound": 0.34627701540988,
|
||||
"running": 4,
|
||||
"selectionWeight": 2.184958508412338,
|
||||
"selectionWeight": 2.1994971244765376,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 9.833333333333334,
|
||||
"waiting": 24556
|
||||
"throughputPerHour": 10.0,
|
||||
"waiting": 24561
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 5175.666666666667,
|
||||
"backlogHours": 5177.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 0.7842436454700886,
|
||||
"queueWeight": 0.7842436454700886,
|
||||
"qualityFactor": 2.3574864817106658,
|
||||
"queueFactor": 0.7866989524684359,
|
||||
"queueWeight": 0.7866989524684359,
|
||||
"recentSuccess": 10,
|
||||
"recentSuccessRate": 0.5555555555555556,
|
||||
"recentTerminal": 18,
|
||||
"recentWilsonLowerBound": 0.33716069428251627,
|
||||
"running": 2,
|
||||
"selectionWeight": 1.9606091136752215,
|
||||
"selectionWeight": 1.8546321456202792,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 3.0,
|
||||
"waiting": 15527
|
||||
"waiting": 15531
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 1918.909090909091,
|
||||
"backlogHours": 1918.3636363636365,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.06467294837014517,
|
||||
"queueFactor": 0.9100972311692594,
|
||||
"queueWeight": 0.9100972311692594,
|
||||
"qualityFactor": 0.06098624060599563,
|
||||
"queueFactor": 0.9130207686010736,
|
||||
"queueWeight": 0.9130207686010736,
|
||||
"recentSuccess": 6,
|
||||
"recentSuccessRate": 0.13636363636363635,
|
||||
"recentTerminal": 44,
|
||||
"recentWilsonLowerBound": 0.06402867407860051,
|
||||
"running": 17,
|
||||
"selectionWeight": 0.05885867124322159,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.05568170427217614,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 7.333333333333333,
|
||||
"waiting": 14072
|
||||
"waiting": 14068
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 810.3529411764706,
|
||||
"backlogHours": 818.7920792079209,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 1.0966432640978767,
|
||||
"queueFactor": 1.0357258633203983,
|
||||
"queueWeight": 1.0357258633203983,
|
||||
"recentSuccess": 32,
|
||||
"recentSuccessRate": 0.3137254901960784,
|
||||
"recentTerminal": 102,
|
||||
"recentWilsonLowerBound": 0.23182840733684665,
|
||||
"qualityFactor": 0.9724217524003625,
|
||||
"queueFactor": 1.0373952418602577,
|
||||
"queueWeight": 1.0373952418602577,
|
||||
"recentSuccess": 31,
|
||||
"recentSuccessRate": 0.3069306930693069,
|
||||
"recentTerminal": 101,
|
||||
"recentWilsonLowerBound": 0.22543494459305355,
|
||||
"running": 6,
|
||||
"selectionWeight": 1.1358217914622728,
|
||||
"selectionWeight": 1.0087856990215498,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.0,
|
||||
"waiting": 13776
|
||||
"throughputPerHour": 16.833333333333332,
|
||||
"waiting": 13783
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-17T08:59:04.507619+00:00",
|
||||
"queueAttemptedAt": "2026-09-17T09:11:08.851921+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-17T08:59:04.507619+00:00",
|
||||
"queueUpdatedAt": "2026-09-17T09:11:08.851921+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Kunlunxin_p-800",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-17T08:52:55.610811+00:00",
|
||||
"lastSyncTime": "2026-09-17T08:52:54.637063+00:00",
|
||||
"generatedAt": "2026-09-17T09:11:01.258740+00:00",
|
||||
"lastSyncTime": "2026-09-17T09:11:00.510552+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2023,14 +2023,15 @@
|
||||
"unresolvedFailureCount": 78
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
|
||||
"attributableFailureCount": 0,
|
||||
"decisionFailureRate": 0.0,
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 4
|
||||
"ambiguous_runtime": 4,
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 4,
|
||||
"failureCount": 5,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"pendingCount": 0,
|
||||
@@ -2040,7 +2041,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 4,
|
||||
"total": 5,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Cambricon_mlu-370-x8|unknown|text-generation": {
|
||||
@@ -2414,30 +2415,30 @@
|
||||
"unresolvedFailureCount": 58
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation": {
|
||||
"attributableFailureCount": 60,
|
||||
"decisionFailureRate": 0.8696,
|
||||
"decisionSuccessRate": 0.1304,
|
||||
"decisionTotal": 69,
|
||||
"attributableFailureCount": 61,
|
||||
"decisionFailureRate": 0.8714,
|
||||
"decisionSuccessRate": 0.1286,
|
||||
"decisionTotal": 70,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 11,
|
||||
"backend_operator": 29,
|
||||
"backend_operator": 30,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 7,
|
||||
"repository_structure": 1,
|
||||
"参数/模板问题": 9
|
||||
},
|
||||
"failureCount": 80,
|
||||
"failureRate": 0.8989,
|
||||
"failureCount": 81,
|
||||
"failureRate": 0.9,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 9,
|
||||
"successRate": 0.1011,
|
||||
"successRate": 0.1,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 89,
|
||||
"total": 90,
|
||||
"unresolvedFailureCount": 20
|
||||
},
|
||||
"Mthreads_s4000|llamacpp|text-generation": {
|
||||
@@ -2836,13 +2837,13 @@
|
||||
"unresolvedFailureCount": 906
|
||||
},
|
||||
"vllm": {
|
||||
"attributableFailureCount": 392,
|
||||
"decisionFailureRate": 0.9584,
|
||||
"decisionSuccessRate": 0.0416,
|
||||
"decisionTotal": 409,
|
||||
"attributableFailureCount": 393,
|
||||
"decisionFailureRate": 0.9585,
|
||||
"decisionSuccessRate": 0.0415,
|
||||
"decisionTotal": 410,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 230,
|
||||
"backend_operator": 37,
|
||||
"backend_operator": 38,
|
||||
"framework_architecture_unsupported": 294,
|
||||
"memory_capacity": 7,
|
||||
"model_load": 31,
|
||||
@@ -2852,35 +2853,35 @@
|
||||
"tokenizer_compatibility": 9,
|
||||
"参数/模板问题": 40
|
||||
},
|
||||
"failureCount": 664,
|
||||
"failureRate": 0.975,
|
||||
"failureCount": 665,
|
||||
"failureRate": 0.9751,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 17,
|
||||
"successRate": 0.025,
|
||||
"total": 681,
|
||||
"successRate": 0.0249,
|
||||
"total": 682,
|
||||
"unresolvedFailureCount": 270
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 9,
|
||||
"decisionFailureRate": 0.9,
|
||||
"decisionSuccessRate": 0.1,
|
||||
"decisionTotal": 10,
|
||||
"attributableFailureCount": 10,
|
||||
"decisionFailureRate": 0.9091,
|
||||
"decisionSuccessRate": 0.0909,
|
||||
"decisionTotal": 11,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 31,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"framework_architecture_unsupported": 9,
|
||||
"tokenizer_compatibility": 1,
|
||||
"参数/模板问题": 3
|
||||
},
|
||||
"failureCount": 43,
|
||||
"failureRate": 0.9773,
|
||||
"failureCount": 44,
|
||||
"failureRate": 0.9778,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 1,
|
||||
"successRate": 0.0227,
|
||||
"total": 44,
|
||||
"successRate": 0.0222,
|
||||
"total": 45,
|
||||
"unresolvedFailureCount": 34
|
||||
},
|
||||
"vllm-patch-tokenizer": {
|
||||
@@ -2971,7 +2972,7 @@
|
||||
"unresolvedFailureCount": 7
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-17T08:52:55.605672+00:00",
|
||||
"generatedAt": "2026-09-17T09:11:01.252695+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 54,
|
||||
@@ -3048,26 +3049,26 @@
|
||||
"unresolvedFailureCount": 60
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"attributableFailureCount": 30,
|
||||
"decisionFailureRate": 0.8824,
|
||||
"decisionSuccessRate": 0.1176,
|
||||
"decisionTotal": 34,
|
||||
"attributableFailureCount": 31,
|
||||
"decisionFailureRate": 0.8857,
|
||||
"decisionSuccessRate": 0.1143,
|
||||
"decisionTotal": 35,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 42,
|
||||
"framework_architecture_unsupported": 27,
|
||||
"framework_architecture_unsupported": 28,
|
||||
"memory_capacity": 1,
|
||||
"tokenizer_compatibility": 2,
|
||||
"参数/模板问题": 1,
|
||||
"验证失败": 39
|
||||
},
|
||||
"failureCount": 112,
|
||||
"failureRate": 0.9655,
|
||||
"failureCount": 113,
|
||||
"failureRate": 0.9658,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 4,
|
||||
"successRate": 0.0345,
|
||||
"total": 116,
|
||||
"successRate": 0.0342,
|
||||
"total": 117,
|
||||
"unresolvedFailureCount": 82
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
@@ -3184,13 +3185,13 @@
|
||||
"unresolvedFailureCount": 131
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"attributableFailureCount": 60,
|
||||
"decisionFailureRate": 0.7692,
|
||||
"decisionSuccessRate": 0.2308,
|
||||
"decisionTotal": 78,
|
||||
"attributableFailureCount": 61,
|
||||
"decisionFailureRate": 0.7722,
|
||||
"decisionSuccessRate": 0.2278,
|
||||
"decisionTotal": 79,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 11,
|
||||
"backend_operator": 29,
|
||||
"backend_operator": 30,
|
||||
"framework_architecture_unsupported": 22,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 7,
|
||||
@@ -3198,14 +3199,14 @@
|
||||
"参数/模板问题": 19,
|
||||
"验证失败": 48
|
||||
},
|
||||
"failureCount": 138,
|
||||
"failureRate": 0.8846,
|
||||
"failureCount": 139,
|
||||
"failureRate": 0.8854,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 18,
|
||||
"successRate": 0.1154,
|
||||
"total": 156,
|
||||
"successRate": 0.1146,
|
||||
"total": 157,
|
||||
"unresolvedFailureCount": 78
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
@@ -3943,6 +3944,29 @@
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|exl3": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "exl3",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|deepseek_v4_dspark|none": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -5641,15 +5665,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors": {
|
||||
"attributableFailureCount": 14,
|
||||
"decisionFailureRate": 0.9333,
|
||||
"decisionSuccessRate": 0.0667,
|
||||
"decisionTotal": 15,
|
||||
"attributableFailureCount": 15,
|
||||
"decisionFailureRate": 0.9375,
|
||||
"decisionSuccessRate": 0.0625,
|
||||
"decisionTotal": 16,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 14
|
||||
"backend_operator": 15
|
||||
},
|
||||
"failureCount": 14,
|
||||
"failureRate": 0.9333,
|
||||
"failureCount": 15,
|
||||
"failureRate": 0.9375,
|
||||
"framework": "vllm",
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
@@ -5657,10 +5681,10 @@
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 1,
|
||||
"successRate": 0.0667,
|
||||
"successRate": 0.0625,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 15,
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors": {
|
||||
@@ -8250,6 +8274,30 @@
|
||||
"total": 4,
|
||||
"unresolvedFailureCount": 4
|
||||
},
|
||||
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|exl3|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm-mlu",
|
||||
"loadSizeLog2Bucket": 33,
|
||||
"modelType": "qwen3_5",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "exl3",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Cambricon_mlu-370-x4",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|deepseek_v4_dspark|none|33": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -10952,6 +11000,30 @@
|
||||
"total": 7,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|llama|compressed-tensors|34": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 1,
|
||||
"failureBreakdown": {
|
||||
"backend_operator": 1
|
||||
},
|
||||
"failureCount": 1,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"loadSizeLog2Bucket": 34,
|
||||
"modelType": "llama",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"quantizationMethod": "compressed-tensors",
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "MetaX_c-500",
|
||||
"taskType": "text-generation",
|
||||
"total": 1,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"MetaX_c-500|vllm|text-generation|nanbeige|compressed-tensors|32": {
|
||||
"attributableFailureCount": 1,
|
||||
"decisionFailureRate": 1.0,
|
||||
@@ -12316,17 +12388,17 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 2110,
|
||||
"totalRecords": 2213,
|
||||
"terminalRecords": 2112,
|
||||
"totalRecords": 2215,
|
||||
"totals": {
|
||||
"attributableFailureCount": 686,
|
||||
"decisionFailureRate": 0.884,
|
||||
"decisionSuccessRate": 0.116,
|
||||
"decisionTotal": 776,
|
||||
"attributableFailureCount": 688,
|
||||
"decisionFailureRate": 0.8843,
|
||||
"decisionSuccessRate": 0.1157,
|
||||
"decisionTotal": 778,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 518,
|
||||
"backend_operator": 47,
|
||||
"framework_architecture_unsupported": 456,
|
||||
"backend_operator": 48,
|
||||
"framework_architecture_unsupported": 457,
|
||||
"memory_capacity": 12,
|
||||
"model_load": 85,
|
||||
"platform_infrastructure": 10,
|
||||
@@ -12336,14 +12408,14 @@
|
||||
"参数/模板问题": 133,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 2020,
|
||||
"failureRate": 0.9573,
|
||||
"failureCount": 2022,
|
||||
"failureRate": 0.9574,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 10,
|
||||
"successCount": 90,
|
||||
"successRate": 0.0427,
|
||||
"total": 2110,
|
||||
"successRate": 0.0426,
|
||||
"total": 2112,
|
||||
"unresolvedFailureCount": 1324
|
||||
},
|
||||
"warnings": [
|
||||
@@ -12354,11 +12426,11 @@
|
||||
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
|
||||
"GPU hygon_k100-ai 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 Vastai_va16 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 Ascend_910-b3 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 Vastai_va16 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。",
|
||||
"组合 Biren_166m|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 Biren_166m|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_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
|
||||
@@ -12383,6 +12455,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 2213,
|
||||
"summarizedRecords": 2215,
|
||||
"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