state: generation 4806 (cycle)
This commit is contained in:
@@ -1312,7 +1312,7 @@
|
||||
"taskType": "text-generation"
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-09T22:05:25.503619+00:00",
|
||||
"generatedAt": "2026-09-09T22:08:16.254832+00:00",
|
||||
"summary": {
|
||||
"activeBlockCount": 65,
|
||||
"byGpuFramework": {
|
||||
|
||||
@@ -51,7 +51,7 @@
|
||||
"4": {
|
||||
"complete": false,
|
||||
"lastError": "ModelHubAPIError: 系统错误",
|
||||
"listingErrors": 341,
|
||||
"listingErrors": 342,
|
||||
"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": 4,
|
||||
"nextAccountIndex": 5,
|
||||
"recordsScanned": 0,
|
||||
"seenTaskIds": [],
|
||||
"startedAt": "2026-09-04T03:55:51.365685+00:00",
|
||||
"terminalRecords": 0,
|
||||
"uniqueRecords": 0,
|
||||
"updatedAt": "2026-09-09T22:05:25.471873+00:00",
|
||||
"updatedAt": "2026-09-09T22:08:16.231574+00:00",
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -416,121 +416,121 @@
|
||||
}
|
||||
},
|
||||
"frameworkUpdatedAt": null,
|
||||
"generatedAt": "2026-09-09T22:03:40.067794+00:00",
|
||||
"generatedAt": "2026-09-09T22:06:33.965297+00:00",
|
||||
"gpuStats": {
|
||||
"Ascend_910-b3": {
|
||||
"available": true,
|
||||
"backlogHours": 1124.976,
|
||||
"backlogHours": 1115.904761904762,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b3",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.2719746072397144,
|
||||
"queueFactor": 0.9449334116765015,
|
||||
"queueWeight": 0.9449334116765015,
|
||||
"recentSuccess": 46,
|
||||
"recentSuccessRate": 0.368,
|
||||
"recentTerminal": 125,
|
||||
"recentWilsonLowerBound": 0.2885686171370214,
|
||||
"qualityFactor": 1.5228081969309835,
|
||||
"queueFactor": 0.9449496272378999,
|
||||
"queueWeight": 0.9449496272378999,
|
||||
"recentSuccess": 48,
|
||||
"recentSuccessRate": 0.38095238095238093,
|
||||
"recentTerminal": 126,
|
||||
"recentWilsonLowerBound": 0.30086961705731946,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.2019313051849014,
|
||||
"selectionWeight": 1.4389770380447513,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 20.833333333333332,
|
||||
"waiting": 23437
|
||||
"throughputPerHour": 21.0,
|
||||
"waiting": 23434
|
||||
},
|
||||
"Ascend_910-b4": {
|
||||
"available": true,
|
||||
"backlogHours": 949.7931034482758,
|
||||
"backlogHours": 966.4561403508771,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Ascend_910-b4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 1.2242874594608326,
|
||||
"queueFactor": 0.9692333344056376,
|
||||
"queueWeight": 0.9692333344056376,
|
||||
"qualityFactor": 1.3916053656419003,
|
||||
"queueFactor": 0.9655514162796774,
|
||||
"queueWeight": 0.9655514162796774,
|
||||
"recentSuccess": 61,
|
||||
"recentSuccessRate": 0.3505747126436782,
|
||||
"recentTerminal": 174,
|
||||
"recentWilsonLowerBound": 0.2835997855016096,
|
||||
"recentSuccessRate": 0.3567251461988304,
|
||||
"recentTerminal": 171,
|
||||
"recentWilsonLowerBound": 0.28879679791250346,
|
||||
"running": 8,
|
||||
"selectionWeight": 1.1866202166042297,
|
||||
"selectionWeight": 1.3436665316979353,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 29.0,
|
||||
"throughputPerHour": 28.5,
|
||||
"waiting": 27544
|
||||
},
|
||||
"Biren_166m": {
|
||||
"available": true,
|
||||
"backlogHours": 158.98203592814372,
|
||||
"backlogHours": 160.65454545454546,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Biren_166m",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 8,
|
||||
"qualityFactor": 0.13329161860956995,
|
||||
"queueFactor": 1.2672738864275483,
|
||||
"queueWeight": 1.2672738864275483,
|
||||
"recentSuccess": 25,
|
||||
"recentSuccessRate": 0.1497005988023952,
|
||||
"recentTerminal": 167,
|
||||
"recentWilsonLowerBound": 0.10350039506050464,
|
||||
"qualityFactor": 0.18342327088960864,
|
||||
"queueFactor": 1.2637721340266104,
|
||||
"queueWeight": 1.2637721340266104,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.16363636363636364,
|
||||
"recentTerminal": 165,
|
||||
"recentWilsonLowerBound": 0.11496465647221277,
|
||||
"running": 8,
|
||||
"selectionWeight": 0.16891698754356824,
|
||||
"selectionWeight": 0.23180521848230173,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 27.833333333333332,
|
||||
"waiting": 4425
|
||||
"throughputPerHour": 27.5,
|
||||
"waiting": 4418
|
||||
},
|
||||
"Cambricon_mlu-370-x4": {
|
||||
"available": true,
|
||||
"backlogHours": 963.6818181818182,
|
||||
"backlogHours": 952.9213483146067,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x4",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.3557517668101479,
|
||||
"queueFactor": 0.9671250764692119,
|
||||
"queueWeight": 0.9671250764692119,
|
||||
"qualityFactor": 0.37863483398142184,
|
||||
"queueFactor": 0.9675962335847911,
|
||||
"queueWeight": 0.9675962335847911,
|
||||
"recentSuccess": 21,
|
||||
"recentSuccessRate": 0.23863636363636365,
|
||||
"recentTerminal": 88,
|
||||
"recentWilsonLowerBound": 0.1617092401848666,
|
||||
"recentSuccessRate": 0.23595505617977527,
|
||||
"recentTerminal": 89,
|
||||
"recentWilsonLowerBound": 0.15982321425035884,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.34405645468032153,
|
||||
"selectionWeight": 0.36636563926442645,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.666666666666666,
|
||||
"waiting": 14134
|
||||
"throughputPerHour": 14.833333333333334,
|
||||
"waiting": 14135
|
||||
},
|
||||
"Cambricon_mlu-370-x8": {
|
||||
"available": true,
|
||||
"backlogHours": 589.3333333333334,
|
||||
"backlogHours": 576.4565217391304,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Cambricon_mlu-370-x8",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.6664596912868703,
|
||||
"queueFactor": 1.041162561243572,
|
||||
"queueWeight": 1.041162561243572,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.3,
|
||||
"recentTerminal": 90,
|
||||
"recentWilsonLowerBound": 0.21510778051256527,
|
||||
"qualityFactor": 0.8378298949691569,
|
||||
"queueFactor": 1.0433685556994101,
|
||||
"queueWeight": 1.0433685556994101,
|
||||
"recentSuccess": 29,
|
||||
"recentSuccessRate": 0.31521739130434784,
|
||||
"recentTerminal": 92,
|
||||
"recentWilsonLowerBound": 0.2293129742179435,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.6938928791458382,
|
||||
"selectionWeight": 0.8741653674357578,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.0,
|
||||
"waiting": 8840
|
||||
"throughputPerHour": 15.333333333333334,
|
||||
"waiting": 8839
|
||||
},
|
||||
"Iluvatar_bi-100": {
|
||||
"available": true,
|
||||
"backlogHours": 40.88333333333333,
|
||||
"backlogHours": 41.51123595505618,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-100",
|
||||
@@ -540,19 +540,19 @@
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 23,
|
||||
"recentSuccessRate": 0.06388888888888888,
|
||||
"recentTerminal": 360,
|
||||
"recentWilsonLowerBound": 0.04294608551772852,
|
||||
"running": 5,
|
||||
"recentSuccessRate": 0.06460674157303371,
|
||||
"recentTerminal": 356,
|
||||
"recentWilsonLowerBound": 0.04343295746910989,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 60.0,
|
||||
"waiting": 2453
|
||||
"throughputPerHour": 59.333333333333336,
|
||||
"waiting": 2463
|
||||
},
|
||||
"Iluvatar_bi-150": {
|
||||
"available": true,
|
||||
"backlogHours": 64.65,
|
||||
"backlogHours": 66.32478632478633,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_bi-150",
|
||||
@@ -561,175 +561,175 @@
|
||||
"qualityFactor": 0.05,
|
||||
"queueFactor": 1.3,
|
||||
"queueWeight": 1.3,
|
||||
"recentSuccess": 28,
|
||||
"recentSuccessRate": 0.07777777777777778,
|
||||
"recentTerminal": 360,
|
||||
"recentWilsonLowerBound": 0.054357230699082416,
|
||||
"running": 5,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.07692307692307693,
|
||||
"recentTerminal": 351,
|
||||
"recentWilsonLowerBound": 0.05340169223626828,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.065,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 60.0,
|
||||
"waiting": 3879
|
||||
"throughputPerHour": 58.5,
|
||||
"waiting": 3880
|
||||
},
|
||||
"Iluvatar_mrv-100": {
|
||||
"available": true,
|
||||
"backlogHours": 1373.8208955223881,
|
||||
"backlogHours": 1438.125,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Iluvatar_mrv-100",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.1747240780178455,
|
||||
"queueFactor": 0.9170292246408891,
|
||||
"queueWeight": 0.9170292246408891,
|
||||
"recentSuccess": 13,
|
||||
"recentSuccessRate": 0.19402985074626866,
|
||||
"recentTerminal": 67,
|
||||
"recentWilsonLowerBound": 0.11705063857457097,
|
||||
"qualityFactor": 0.1313560322661581,
|
||||
"queueFactor": 0.9096686592753765,
|
||||
"queueWeight": 0.9096686592753765,
|
||||
"recentSuccess": 11,
|
||||
"recentSuccessRate": 0.171875,
|
||||
"recentTerminal": 64,
|
||||
"recentWilsonLowerBound": 0.09877641267316228,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.16022708579079908,
|
||||
"selectionWeight": 0.11949046575928915,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 11.166666666666666,
|
||||
"waiting": 15341
|
||||
"throughputPerHour": 10.666666666666666,
|
||||
"waiting": 15340
|
||||
},
|
||||
"Kunlunxin_p-800": {
|
||||
"available": true,
|
||||
"backlogHours": 731.6629213483146,
|
||||
"backlogHours": 757.1860465116279,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Kunlunxin_p-800",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 7,
|
||||
"qualityFactor": 0.49797322856713,
|
||||
"queueFactor": 1.00791993977138,
|
||||
"queueWeight": 1.00791993977138,
|
||||
"qualityFactor": 0.5884189352459078,
|
||||
"queueFactor": 1.0015493128903414,
|
||||
"queueWeight": 1.0015493128903414,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.2696629213483146,
|
||||
"recentTerminal": 89,
|
||||
"recentWilsonLowerBound": 0.18841924495236884,
|
||||
"recentSuccessRate": 0.27906976744186046,
|
||||
"recentTerminal": 86,
|
||||
"recentWilsonLowerBound": 0.19528545330537803,
|
||||
"running": 7,
|
||||
"selectionWeight": 0.5019171465451413,
|
||||
"selectionWeight": 0.5893305802872053,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 14.833333333333334,
|
||||
"throughputPerHour": 14.333333333333334,
|
||||
"waiting": 10853
|
||||
},
|
||||
"MetaX_c-500": {
|
||||
"available": true,
|
||||
"backlogHours": 758.5333333333333,
|
||||
"backlogHours": 767.0561797752808,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "MetaX_c-500",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.4853724756968554,
|
||||
"queueFactor": 1.0024817922854876,
|
||||
"queueWeight": 1.0024817922854876,
|
||||
"qualityFactor": 0.5438616585137743,
|
||||
"queueFactor": 0.9996055337577108,
|
||||
"queueWeight": 0.9996055337577108,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.26666666666666666,
|
||||
"recentTerminal": 90,
|
||||
"recentWilsonLowerBound": 0.18623692042961368,
|
||||
"recentSuccessRate": 0.2696629213483146,
|
||||
"recentTerminal": 89,
|
||||
"recentWilsonLowerBound": 0.18841924495236884,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.48657706936262785,
|
||||
"selectionWeight": 0.5436471234490152,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 15.0,
|
||||
"throughputPerHour": 14.833333333333334,
|
||||
"waiting": 11378
|
||||
},
|
||||
"Mthreads_s4000": {
|
||||
"available": true,
|
||||
"backlogHours": 1739.8356164383563,
|
||||
"backlogHours": 1763.75,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Mthreads_s4000",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 4,
|
||||
"qualityFactor": 0.7866299523933046,
|
||||
"queueFactor": 0.885108398044168,
|
||||
"queueWeight": 0.885108398044168,
|
||||
"qualityFactor": 0.8870809524820971,
|
||||
"queueFactor": 0.8822408719429823,
|
||||
"queueWeight": 0.8822408719429823,
|
||||
"recentSuccess": 24,
|
||||
"recentSuccessRate": 0.3287671232876712,
|
||||
"recentTerminal": 73,
|
||||
"recentWilsonLowerBound": 0.2319433057283529,
|
||||
"recentSuccessRate": 0.3333333333333333,
|
||||
"recentTerminal": 72,
|
||||
"recentWilsonLowerBound": 0.2353448606571184,
|
||||
"running": 4,
|
||||
"selectionWeight": 0.6962527770163979,
|
||||
"selectionWeight": 0.7826190730018165,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.166666666666666,
|
||||
"waiting": 21168
|
||||
"throughputPerHour": 12.0,
|
||||
"waiting": 21165
|
||||
},
|
||||
"Sunrise_pt-200-x1": {
|
||||
"available": true,
|
||||
"backlogHours": 4373.0526315789475,
|
||||
"backlogHours": 4616.0,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Sunrise_pt-200-x1",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 2,
|
||||
"qualityFactor": 0.7827024782327442,
|
||||
"queueFactor": 0.7708235743230443,
|
||||
"queueWeight": 0.7708235743230443,
|
||||
"recentSuccess": 8,
|
||||
"recentSuccessRate": 0.42105263157894735,
|
||||
"recentTerminal": 19,
|
||||
"recentWilsonLowerBound": 0.2314162039203038,
|
||||
"qualityFactor": 0.6411196370224538,
|
||||
"queueFactor": 0.7636825332474312,
|
||||
"queueWeight": 0.7636825332474312,
|
||||
"recentSuccess": 7,
|
||||
"recentSuccessRate": 0.3888888888888889,
|
||||
"recentTerminal": 18,
|
||||
"recentWilsonLowerBound": 0.2030499192693116,
|
||||
"running": 2,
|
||||
"selectionWeight": 0.6033255219028686,
|
||||
"selectionWeight": 0.4896118685159811,
|
||||
"stale": false,
|
||||
"submissionEligible": false,
|
||||
"throughputPerHour": 3.1666666666666665,
|
||||
"throughputPerHour": 3.0,
|
||||
"waiting": 13848
|
||||
},
|
||||
"Vastai_va16": {
|
||||
"available": true,
|
||||
"backlogHours": 783.8108108108107,
|
||||
"backlogHours": 763.0263157894738,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "Vastai_va16",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 16,
|
||||
"qualityFactor": 0.9472232008940819,
|
||||
"queueFactor": 0.9975645481198707,
|
||||
"queueWeight": 0.9975645481198707,
|
||||
"recentSuccess": 26,
|
||||
"recentSuccessRate": 0.35135135135135137,
|
||||
"recentTerminal": 74,
|
||||
"recentWilsonLowerBound": 0.25238027534892055,
|
||||
"qualityFactor": 1.0767773346519607,
|
||||
"queueFactor": 1.000395662822683,
|
||||
"queueWeight": 1.000395662822683,
|
||||
"recentSuccess": 27,
|
||||
"recentSuccessRate": 0.35526315789473684,
|
||||
"recentTerminal": 76,
|
||||
"recentWilsonLowerBound": 0.25701618295439105,
|
||||
"running": 16,
|
||||
"selectionWeight": 0.9449162843685622,
|
||||
"selectionWeight": 1.0772033754115902,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 12.333333333333334,
|
||||
"waiting": 9667
|
||||
"throughputPerHour": 12.666666666666666,
|
||||
"waiting": 9665
|
||||
},
|
||||
"hygon_k100-ai": {
|
||||
"available": true,
|
||||
"backlogHours": 496.2857142857143,
|
||||
"backlogHours": 477.96330275229354,
|
||||
"canVerify": true,
|
||||
"error": null,
|
||||
"gpu": "hygon_k100-ai",
|
||||
"healthFactor": 1.0,
|
||||
"maxConcurrentTasks": 6,
|
||||
"qualityFactor": 2.5,
|
||||
"queueFactor": 1.0683484588928251,
|
||||
"queueWeight": 1.0683484588928251,
|
||||
"queueFactor": 1.073108277009467,
|
||||
"queueWeight": 1.073108277009467,
|
||||
"recentSuccess": 51,
|
||||
"recentSuccessRate": 0.4857142857142857,
|
||||
"recentTerminal": 105,
|
||||
"recentWilsonLowerBound": 0.3923202449996005,
|
||||
"recentSuccessRate": 0.46788990825688076,
|
||||
"recentTerminal": 109,
|
||||
"recentWilsonLowerBound": 0.37691168989272644,
|
||||
"running": 6,
|
||||
"selectionWeight": 2.670871147232063,
|
||||
"selectionWeight": 2.682770692523668,
|
||||
"stale": false,
|
||||
"submissionEligible": true,
|
||||
"throughputPerHour": 17.5,
|
||||
"waiting": 8685
|
||||
"throughputPerHour": 18.166666666666668,
|
||||
"waiting": 8683
|
||||
}
|
||||
},
|
||||
"queueAttemptedAt": "2026-09-09T21:54:15.287880+00:00",
|
||||
"queueAttemptedAt": "2026-09-09T22:06:33.965297+00:00",
|
||||
"queueError": null,
|
||||
"queueUpdatedAt": "2026-09-09T21:54:15.287880+00:00",
|
||||
"queueUpdatedAt": "2026-09-09T22:06:33.965297+00:00",
|
||||
"supportedGpus": [
|
||||
"Vastai_va16",
|
||||
"Iluvatar_mrv-100",
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,6 +1,6 @@
|
||||
{
|
||||
"generatedAt": "2026-09-09T21:47:28.483336+00:00",
|
||||
"lastSyncTime": "2026-09-09T21:47:28.214740+00:00",
|
||||
"generatedAt": "2026-09-09T22:06:26.542677+00:00",
|
||||
"lastSyncTime": "2026-09-09T22:06:26.296264+00:00",
|
||||
"recentLimit": 300,
|
||||
"report": {
|
||||
"architectureCompatibilityBlocks": {
|
||||
@@ -2230,14 +2230,14 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 35,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"ambiguous_runtime": 7,
|
||||
"framework_architecture_unsupported": 27,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
"repository_structure": 3,
|
||||
"runtime_memory": 1
|
||||
},
|
||||
"failureCount": 41,
|
||||
"failureCount": 42,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"pendingCount": 0,
|
||||
@@ -2247,8 +2247,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 41,
|
||||
"unresolvedFailureCount": 6
|
||||
"total": 42,
|
||||
"unresolvedFailureCount": 7
|
||||
}
|
||||
},
|
||||
"frameworkSummaries": {
|
||||
@@ -2320,7 +2320,7 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 223,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 115,
|
||||
"ambiguous_runtime": 116,
|
||||
"backend_operator": 18,
|
||||
"framework_architecture_unsupported": 168,
|
||||
"memory_capacity": 6,
|
||||
@@ -2331,15 +2331,15 @@
|
||||
"tokenizer_compatibility": 3,
|
||||
"参数/模板问题": 21
|
||||
},
|
||||
"failureCount": 360,
|
||||
"failureCount": 361,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 1,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 360,
|
||||
"unresolvedFailureCount": 136
|
||||
"total": 361,
|
||||
"unresolvedFailureCount": 137
|
||||
},
|
||||
"vllm-mlu": {
|
||||
"attributableFailureCount": 7,
|
||||
@@ -2442,7 +2442,7 @@
|
||||
"unresolvedFailureCount": 1
|
||||
}
|
||||
},
|
||||
"generatedAt": "2026-09-09T21:47:28.479448+00:00",
|
||||
"generatedAt": "2026-09-09T22:06:26.538602+00:00",
|
||||
"gpuSummaries": {
|
||||
"Ascend_910-b3": {
|
||||
"attributableFailureCount": 26,
|
||||
@@ -2749,7 +2749,7 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 38,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 8,
|
||||
"ambiguous_runtime": 9,
|
||||
"framework_architecture_unsupported": 30,
|
||||
"memory_capacity": 1,
|
||||
"model_load": 3,
|
||||
@@ -2758,15 +2758,15 @@
|
||||
"参数/模板问题": 8,
|
||||
"验证失败": 27
|
||||
},
|
||||
"failureCount": 81,
|
||||
"failureCount": 82,
|
||||
"failureRate": 1.0,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
"successCount": 0,
|
||||
"successRate": 0.0,
|
||||
"total": 81,
|
||||
"unresolvedFailureCount": 43
|
||||
"total": 82,
|
||||
"unresolvedFailureCount": 44
|
||||
}
|
||||
},
|
||||
"observedGpuMemoryGiB": {
|
||||
@@ -4433,18 +4433,18 @@
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
|
||||
"attributableFailureCount": 14,
|
||||
"consecutiveFailures": 14,
|
||||
"attributableFailureCount": 13,
|
||||
"consecutiveFailures": 13,
|
||||
"consecutivePlatformFailures": 0,
|
||||
"decisionFailureRate": 1.0,
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 14,
|
||||
"decisionTotal": 13,
|
||||
"failureBreakdown": {
|
||||
"framework_architecture_unsupported": 1,
|
||||
"platform_infrastructure": 1,
|
||||
"tokenizer_compatibility": 13
|
||||
"tokenizer_compatibility": 12
|
||||
},
|
||||
"failureCount": 15,
|
||||
"failureCount": 14,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm_fix_tokenizer",
|
||||
"lastPlatformFailureAt": "2026-09-08T18:27:21+00:00",
|
||||
@@ -4456,7 +4456,7 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "Sunrise_pt-200-x1",
|
||||
"taskType": "text-generation",
|
||||
"total": 15,
|
||||
"total": 14,
|
||||
"unresolvedFailureCount": 0
|
||||
},
|
||||
"Sunrise_pt-200-x1|vllm|text-generation": {
|
||||
@@ -4620,16 +4620,16 @@
|
||||
"decisionSuccessRate": 0.0,
|
||||
"decisionTotal": 10,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 6,
|
||||
"ambiguous_runtime": 7,
|
||||
"framework_architecture_unsupported": 8,
|
||||
"model_load": 1,
|
||||
"repository_structure": 1
|
||||
},
|
||||
"failureCount": 16,
|
||||
"failureCount": 17,
|
||||
"failureRate": 1.0,
|
||||
"framework": "vllm",
|
||||
"lastPlatformFailureAt": null,
|
||||
"lastTerminalAt": "2026-09-09T19:08:24.911910+00:00",
|
||||
"lastTerminalAt": "2026-09-09T22:06:26.296264+00:00",
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 0,
|
||||
@@ -4637,8 +4637,8 @@
|
||||
"successRate": 0.0,
|
||||
"targetGpu": "hygon_k100-ai",
|
||||
"taskType": "text-generation",
|
||||
"total": 16,
|
||||
"unresolvedFailureCount": 6
|
||||
"total": 17,
|
||||
"unresolvedFailureCount": 7
|
||||
}
|
||||
},
|
||||
"recentProfileCombinationStats": {
|
||||
@@ -6633,15 +6633,15 @@
|
||||
"unresolvedFailureCount": 0
|
||||
}
|
||||
},
|
||||
"terminalRecords": 1450,
|
||||
"totalRecords": 1534,
|
||||
"terminalRecords": 1451,
|
||||
"totalRecords": 1535,
|
||||
"totals": {
|
||||
"attributableFailureCount": 386,
|
||||
"decisionFailureRate": 0.8915,
|
||||
"decisionSuccessRate": 0.1085,
|
||||
"decisionTotal": 433,
|
||||
"failureBreakdown": {
|
||||
"ambiguous_runtime": 248,
|
||||
"ambiguous_runtime": 249,
|
||||
"backend_operator": 21,
|
||||
"framework_architecture_unsupported": 266,
|
||||
"memory_capacity": 11,
|
||||
@@ -6653,21 +6653,21 @@
|
||||
"参数/模板问题": 94,
|
||||
"验证失败": 673
|
||||
},
|
||||
"failureCount": 1403,
|
||||
"failureCount": 1404,
|
||||
"failureRate": 0.9676,
|
||||
"pendingCount": 0,
|
||||
"pendingRate": 0.0,
|
||||
"platformFailureCount": 2,
|
||||
"successCount": 47,
|
||||
"successRate": 0.0324,
|
||||
"total": 1450,
|
||||
"unresolvedFailureCount": 1015
|
||||
"total": 1451,
|
||||
"unresolvedFailureCount": 1016
|
||||
},
|
||||
"warnings": [
|
||||
"GPU Cambricon_mlu-370-x8 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 Iluvatar_mrv-100 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 Sunrise_pt-200-x1 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 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。",
|
||||
@@ -6675,7 +6675,7 @@
|
||||
"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。",
|
||||
"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 Iluvatar_bi-150 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-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 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。",
|
||||
@@ -6695,6 +6695,6 @@
|
||||
]
|
||||
},
|
||||
"storageMode": "decision_state_only",
|
||||
"summarizedRecords": 1534,
|
||||
"summarizedRecords": 1535,
|
||||
"version": 1
|
||||
}
|
||||
|
||||
@@ -1,3 +1,4 @@
|
||||
{"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": "2026-09-09T22:06:26.296264+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:01:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493490", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-09T21:47:28.214740+00:00", "modelId": "neuralmagic/SmolLM-1.7B-Instruct-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:41:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610342", "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": "2026-09-09T21:37:50.501060+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:29:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505065", "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": "2026-09-09T21:11:06.904677+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T21:05:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493675", "taskType": "text-generation", "verifyResult": -1}
|
||||
@@ -297,4 +298,3 @@
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T16:39:46.911859+00:00", "modelId": "RedHatAI/DeepSeek-R1-Distill-Qwen-1.5B-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-06T16:37:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4107037", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T16:32:45.701835+00:00", "modelId": "neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-06T16:31:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4100231", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T16:29:12.705614+00:00", "modelId": "neuralmagic/Mistral-Nemo-Instruct-2407-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-06T16:27:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4100460", "taskType": "text-generation", "verifyResult": -1}
|
||||
{"failReason": "tokenizer_compatibility", "failureAction": "check_tokenizer_files_then_llm", "failureCategory": "tokenizer_compatibility", "failureClassificationReason": "broad_tokenizer_error", "failureCode": "TOKENIZER_FAILED", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_framework", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T16:10:47.211138+00:00", "modelId": "RedHatAI/granite-3.1-2b-instruct-quantized.w4a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-06T16:09:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4133257", "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": "fcefdf25b205c249ddd0241f7d966dca49f498805e62a7f89d0c8d95c452d649",
|
||||
".modelhub_state/architecture_history_backfill.json": "31ebfc1a398a4e68987926bf36ff5594dd0cc5a3e849df68934ea9edc61caa34",
|
||||
".modelhub_state/market_intelligence.json": "afe36b835ef47ded1e93900399d82f9913c530cffe7adf1c105a367c2ad6ed2d",
|
||||
".modelhub_state/official_capabilities.json": "f83b0a8c36e5759caddb14c00d8e9ea7af5a8eb81cbd305a9807d3f339d94965",
|
||||
".modelhub_state/outcome_checkpoint.json": "a715657904ac2e1571b293e219c49de9017f7477a589543409006091db895712",
|
||||
".modelhub_state/architecture_compatibility_blacklist.json": "57d358afcc4f365c6f81367ad1a6aaf93362dc14472f45c398eddb6e826c2818",
|
||||
".modelhub_state/architecture_history_backfill.json": "04018144663362409431c9ed9c26447bd52e5da117f94627d7dea62fe3b6f2c0",
|
||||
".modelhub_state/market_intelligence.json": "6b86d8f4fd6e545808affbea8a6faad710fa5ba7f416882a797f5c201fb9d183",
|
||||
".modelhub_state/official_capabilities.json": "d32aa482d2de2100d94d13e80e7ae85eff7ef5315d956289ce8c9c7a0ed4f0a0",
|
||||
".modelhub_state/outcome_checkpoint.json": "fbfcfdcc119cee3c42191ae2b6908292dc478215c2b9e17811e46d15a850ab88",
|
||||
".modelhub_state/queue_cleanup_latest.json": "9a11c448074d1c105fe90e48fb81cfc27bce5e7e08d76397232f05c4c9432a32",
|
||||
".modelhub_state/recent_outcomes.jsonl": "fea1f3496ea904d057c422260386f915847d0518250c2e5ea47eb839dfbc1095",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "6d3538059d57d3464a018b5cfd9301c7bdd3f9fcb898b2bb62589df1cc13f71f",
|
||||
".modelhub_state/recovery_intents.jsonl": "77328e4ad7cd389128a8484b01c1f70413fb8174becce3f113a6afcc372d5823",
|
||||
".modelhub_state/recent_outcomes.jsonl": "0ba62edeb0936c478c13e9ebb7a444549eb69e48501525583a4d8a935a6afd7b",
|
||||
".modelhub_state/recovery_active_tasks.jsonl": "0d223156f1f11a73b9e4d3c80f0c251a5dcc2574e526aa4c3585ccea5602668c",
|
||||
".modelhub_state/recovery_intents.jsonl": "b825c736945086f52a38f20fd55074fb32d9b900db8490d79976649ca5d51dcf",
|
||||
".modelhub_state/routing_intelligence.json": "4effdc96741bb83e9319ea4665226a7e2442dc48c76af38dae47ff1343260b42",
|
||||
".modelhub_state/submission_exclusions.jsonl": "363b21d9f5526f9b072e4f5ff55cc1ff126e844da64fb08a7b6e4d09b2559cdb",
|
||||
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
|
||||
"ledger/submissions.jsonl": "d1eb68b42e51d6dc5a0ba81a1cbbef0996396166e6e018aba45adb1171e43df7",
|
||||
"outcomes/submissions.jsonl": "4e38999f62295341ddbecc1076cd68dc379354519ca15c39c4f47636c09704e4"
|
||||
},
|
||||
"generation": 4805,
|
||||
"generation": 4806,
|
||||
"phase": "cycle",
|
||||
"schemaVersion": 1,
|
||||
"updatedAt": "2026-09-09T22:05:25.578733+00:00",
|
||||
"updatedAt": "2026-09-09T22:08:17.105776+00:00",
|
||||
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user