state: generation 5720 (cycle)

This commit is contained in:
2026-09-11 14:15:45 +00:00
parent 58930a51df
commit d68b1f202f
9 changed files with 2392 additions and 2394 deletions

View File

@@ -1307,7 +1307,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-11T14:12:27.956877+00:00",
"generatedAt": "2026-09-11T14:15:45.002406+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 410,
"listingErrors": 411,
"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": 5,
"nextAccountIndex": 6,
"recordsScanned": 0,
"seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0,
"uniqueRecords": 0,
"updatedAt": "2026-09-11T14:12:27.933619+00:00",
"updatedAt": "2026-09-11T14:15:44.977617+00:00",
"version": 1
}

View File

@@ -416,320 +416,320 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-11T14:10:37.793455+00:00",
"generatedAt": "2026-09-11T14:13:42.056344+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 2135.0,
"backlogHours": 2272.354838709677,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.2531441467693327,
"queueFactor": 0.8336220084133963,
"queueWeight": 0.8336220084133963,
"recentSuccess": 22,
"recentSuccessRate": 0.3333333333333333,
"recentTerminal": 66,
"recentWilsonLowerBound": 0.23156267004508024,
"qualityFactor": 1.193637349760836,
"queueFactor": 0.8234098140639223,
"queueWeight": 0.8234098140639223,
"recentSuccess": 20,
"recentSuccessRate": 0.3225806451612903,
"recentTerminal": 62,
"recentWilsonLowerBound": 0.21954328640542628,
"running": 8,
"selectionWeight": 1.044648540461343,
"selectionWeight": 0.9828527082263229,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.0,
"waiting": 23485
"throughputPerHour": 10.333333333333334,
"waiting": 23481
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1134.8275862068965,
"backlogHours": 1167.1489361702127,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.3955290831597225,
"queueFactor": 0.9165145652026064,
"queueWeight": 0.9165145652026064,
"recentSuccess": 56,
"recentSuccessRate": 0.38620689655172413,
"recentTerminal": 145,
"recentWilsonLowerBound": 0.31086929582821293,
"qualityFactor": 2.49332257897891,
"queueFactor": 0.9099520748514482,
"queueWeight": 0.9099520748514482,
"recentSuccess": 54,
"recentSuccessRate": 0.3829787234042553,
"recentTerminal": 141,
"recentWilsonLowerBound": 0.3068541569806433,
"running": 8,
"selectionWeight": 2.1955372960823314,
"selectionWeight": 2.268804054015823,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.166666666666668,
"waiting": 27425
"throughputPerHour": 23.5,
"waiting": 27428
},
"Biren_166m": {
"available": true,
"backlogHours": 116.69603524229075,
"backlogHours": 119.24324324324324,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.2585231436230541,
"queueFactor": 1.2892004209091106,
"queueWeight": 1.2892004209091106,
"recentSuccess": 35,
"recentSuccessRate": 0.15418502202643172,
"recentTerminal": 227,
"recentWilsonLowerBound": 0.11299960138067465,
"qualityFactor": 0.27000109618047924,
"queueFactor": 1.281216120569007,
"queueWeight": 1.281216120569007,
"recentSuccess": 34,
"recentSuccessRate": 0.15315315315315314,
"recentTerminal": 222,
"recentWilsonLowerBound": 0.1117140884792264,
"running": 8,
"selectionWeight": 0.3332881455735878,
"selectionWeight": 0.34592975699773293,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 37.833333333333336,
"waiting": 4415
"throughputPerHour": 37.0,
"waiting": 4412
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1404.688524590164,
"backlogHours": 1452.6101694915253,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.8639544608658046,
"queueFactor": 0.8876501864230156,
"queueWeight": 0.8876501864230156,
"qualityFactor": 0.9996016856874237,
"queueFactor": 0.8805724612388987,
"queueWeight": 0.8805724612388987,
"recentSuccess": 18,
"recentSuccessRate": 0.29508196721311475,
"recentTerminal": 61,
"recentWilsonLowerBound": 0.19554865403985322,
"recentSuccessRate": 0.3050847457627119,
"recentTerminal": 59,
"recentWilsonLowerBound": 0.20253473477602127,
"running": 7,
"selectionWeight": 0.7668893382485275,
"selectionWeight": 0.8802217166243267,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.166666666666666,
"waiting": 14281
"throughputPerHour": 9.833333333333334,
"waiting": 14284
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 453.8974358974359,
"backlogHours": 453.79487179487177,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.5285292699045032,
"queueFactor": 1.0515627521799848,
"queueWeight": 1.0515627521799848,
"recentSuccess": 26,
"recentSuccessRate": 0.2222222222222222,
"qualityFactor": 0.6259720028826878,
"queueFactor": 1.0484760725773414,
"queueWeight": 1.0484760725773414,
"recentSuccess": 27,
"recentSuccessRate": 0.23076923076923078,
"recentTerminal": 117,
"recentWilsonLowerBound": 0.15640294212046033,
"recentWilsonLowerBound": 0.1637205217381598,
"running": 7,
"selectionWeight": 0.5557816936684574,
"selectionWeight": 0.6563166671258128,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.5,
"waiting": 8851
"waiting": 8849
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 109.45454545454545,
"backlogHours": 111.76744186046511,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 24,
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"queueFactor": 1.2937196206610455,
"queueWeight": 1.2937196206610455,
"recentSuccess": 3,
"recentSuccessRate": 0.022727272727272728,
"recentTerminal": 132,
"recentWilsonLowerBound": 0.007758843642427892,
"recentSuccessRate": 0.023255813953488372,
"recentTerminal": 129,
"recentWilsonLowerBound": 0.007939993605110279,
"running": 24,
"selectionWeight": 0.065,
"selectionWeight": 0.06468598103305227,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 22.0,
"waiting": 2408
"throughputPerHour": 21.5,
"waiting": 2403
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 193.14049586776858,
"backlogHours": 201.41379310344828,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.10985612931814379,
"queueFactor": 1.1953576148164502,
"queueWeight": 1.1953576148164502,
"qualityFactor": 0.12935016525776655,
"queueFactor": 1.1843336806424103,
"queueWeight": 1.1843336806424103,
"recentSuccess": 15,
"recentSuccessRate": 0.12396694214876033,
"recentTerminal": 121,
"recentWilsonLowerBound": 0.07658322802477276,
"running": 5,
"selectionWeight": 0.13131736071470387,
"recentSuccessRate": 0.12931034482758622,
"recentTerminal": 116,
"recentWilsonLowerBound": 0.07995320598677602,
"running": 6,
"selectionWeight": 0.15319375731143467,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.166666666666668,
"waiting": 3895
"throughputPerHour": 19.333333333333332,
"waiting": 3894
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2021.6086956521738,
"backlogHours": 1937.125,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.5255927507531698,
"queueFactor": 0.8404740118757393,
"queueWeight": 0.8404740118757393,
"recentSuccess": 12,
"recentSuccessRate": 0.2608695652173913,
"recentTerminal": 46,
"recentWilsonLowerBound": 0.15600735194449333,
"qualityFactor": 0.6423852512861494,
"queueFactor": 0.8433615838237553,
"queueWeight": 0.8433615838237553,
"recentSuccess": 13,
"recentSuccessRate": 0.2708333333333333,
"recentTerminal": 48,
"recentWilsonLowerBound": 0.16565803561632889,
"running": 2,
"selectionWeight": 0.44174704783832214,
"selectionWeight": 0.541763042949708,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.666666666666667,
"waiting": 15499
"throughputPerHour": 8.0,
"waiting": 15497
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 646.6930693069307,
"backlogHours": 621.9428571428572,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.4713812981175189,
"queueFactor": 0.9971812934922436,
"queueWeight": 0.9971812934922436,
"qualityFactor": 0.462191684930107,
"queueFactor": 1.0000573100277284,
"queueWeight": 1.0000573100277284,
"recentSuccess": 22,
"recentSuccessRate": 0.21782178217821782,
"recentTerminal": 101,
"recentWilsonLowerBound": 0.14847574440775013,
"recentSuccessRate": 0.20952380952380953,
"recentTerminal": 105,
"recentWilsonLowerBound": 0.1426344996383833,
"running": 7,
"selectionWeight": 0.4700526125848804,
"selectionWeight": 0.46221817314838615,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.833333333333332,
"waiting": 10886
"throughputPerHour": 17.5,
"waiting": 10884
},
"MetaX_c-500": {
"available": true,
"backlogHours": 622.5818181818182,
"backlogHours": 622.4181818181819,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.4908223979986181,
"queueFactor": 1.0028809660146938,
"queueWeight": 1.0028809660146938,
"qualityFactor": 0.5256808971985348,
"queueFactor": 0.9999427151419141,
"queueWeight": 0.9999427151419141,
"recentSuccess": 24,
"recentSuccessRate": 0.21818181818181817,
"recentTerminal": 110,
"recentWilsonLowerBound": 0.15122852088416214,
"running": 4,
"selectionWeight": 0.4922364406465026,
"selectionWeight": 0.5256507836429404,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.333333333333332,
"waiting": 11414
"waiting": 11411
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 383.71084337349396,
"backlogHours": 388.2621951219512,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.06187130511524395,
"queueFactor": 1.0783959370892462,
"queueWeight": 1.0783959370892462,
"recentSuccess": 28,
"recentSuccessRate": 0.08433734939759036,
"recentTerminal": 332,
"recentWilsonLowerBound": 0.058992876105824515,
"qualityFactor": 0.08151998288019378,
"queueFactor": 1.0732939851607535,
"queueWeight": 1.0732939851607535,
"recentSuccess": 30,
"recentSuccessRate": 0.09146341463414634,
"recentTerminal": 328,
"recentWilsonLowerBound": 0.06481838370768772,
"running": 4,
"selectionWeight": 0.06672176405868817,
"selectionWeight": 0.08749490729571958,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 55.333333333333336,
"waiting": 21232
"throughputPerHour": 54.666666666666664,
"waiting": 21225
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 4768.333333333333,
"backlogHours": 4768.666666666667,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.577145160518289,
"queueFactor": 0.7389649889876184,
"queueWeight": 0.7389649889876184,
"recentSuccess": 6,
"recentSuccessRate": 0.3333333333333333,
"qualityFactor": 0.16785897672248196,
"queueFactor": 0.7367631846982691,
"queueWeight": 0.7367631846982691,
"recentSuccess": 4,
"recentSuccessRate": 0.2222222222222222,
"recentTerminal": 18,
"recentWilsonLowerBound": 0.16278554363662856,
"recentWilsonLowerBound": 0.09000781913382,
"running": 2,
"selectionWeight": 0.4264900671866547,
"selectionWeight": 0.12367231427024843,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 3.0,
"waiting": 14305
"waiting": 14306
},
"Vastai_va16": {
"available": true,
"backlogHours": 964.875,
"backlogHours": 1013.4098360655738,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.6595138044731024,
"queueFactor": 0.9390921185860541,
"queueWeight": 0.9390921185860541,
"recentSuccess": 17,
"recentSuccessRate": 0.265625,
"recentTerminal": 64,
"recentWilsonLowerBound": 0.1729623856953776,
"qualityFactor": 0.6658919534098263,
"queueFactor": 0.9294364366449989,
"queueWeight": 0.9294364366449989,
"recentSuccess": 16,
"recentSuccessRate": 0.26229508196721313,
"recentTerminal": 61,
"recentWilsonLowerBound": 0.16838645195913182,
"running": 16,
"selectionWeight": 0.6193442158793944,
"selectionWeight": 0.6189042443678066,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 10.666666666666666,
"waiting": 10292
"throughputPerHour": 10.166666666666666,
"waiting": 10303
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 550.0421052631579,
"backlogHours": 549.9157894736842,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"queueFactor": 1.0216907546807028,
"queueWeight": 1.0216907546807028,
"recentSuccess": 39,
"recentSuccessRate": 0.4105263157894737,
"queueFactor": 1.018692322239144,
"queueWeight": 1.018692322239144,
"recentSuccess": 38,
"recentSuccessRate": 0.4,
"recentTerminal": 95,
"recentWilsonLowerBound": 0.31695999256461327,
"recentWilsonLowerBound": 0.3072274266777599,
"running": 6,
"selectionWeight": 2.5542268867017572,
"selectionWeight": 2.5467308055978597,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 15.833333333333334,
"waiting": 8709
"waiting": 8707
}
},
"queueAttemptedAt": "2026-09-11T14:01:24.876789+00:00",
"queueAttemptedAt": "2026-09-11T14:13:42.056344+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-11T14:01:24.876789+00:00",
"queueUpdatedAt": "2026-09-11T14:13:42.056344+00:00",
"supportedGpus": [
"Vastai_va16",
"Iluvatar_mrv-100",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-09-11T13:55:09.160805+00:00",
"lastSyncTime": "2026-09-11T13:55:08.941364+00:00",
"generatedAt": "2026-09-11T14:13:29.530050+00:00",
"lastSyncTime": "2026-09-11T14:13:29.151029+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1792,7 +1792,7 @@
"decisionSuccessRate": 0.1134,
"decisionTotal": 97,
"failureBreakdown": {
"ambiguous_runtime": 18,
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 36,
@@ -1800,18 +1800,18 @@
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 154,
"failureRate": 0.9333,
"failureCount": 155,
"failureRate": 0.9337,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 11,
"successRate": 0.0667,
"successRate": 0.0663,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 165,
"unresolvedFailureCount": 67
"total": 166,
"unresolvedFailureCount": 68
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 1,
@@ -2295,7 +2295,7 @@
"decisionSuccessRate": 0.2593,
"decisionTotal": 189,
"failureBreakdown": {
"ambiguous_runtime": 129,
"ambiguous_runtime": 130,
"backend_operator": 4,
"framework_architecture_unsupported": 90,
"memory_capacity": 5,
@@ -2305,15 +2305,15 @@
"参数/模板问题": 57,
"验证失败": 673
},
"failureCount": 1000,
"failureCount": 1001,
"failureRate": 0.9533,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 49,
"successRate": 0.0467,
"total": 1049,
"unresolvedFailureCount": 859
"total": 1050,
"unresolvedFailureCount": 860
},
"vllm": {
"attributableFailureCount": 241,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-11T13:55:09.156645+00:00",
"generatedAt": "2026-09-11T14:13:29.526269+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2611,7 +2611,7 @@
"decisionSuccessRate": 0.1134,
"decisionTotal": 97,
"failureBreakdown": {
"ambiguous_runtime": 18,
"ambiguous_runtime": 19,
"framework_architecture_unsupported": 49,
"memory_capacity": 1,
"model_load": 36,
@@ -2619,15 +2619,15 @@
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 154,
"failureRate": 0.9333,
"failureCount": 155,
"failureRate": 0.9337,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 11,
"successRate": 0.0667,
"total": 165,
"unresolvedFailureCount": 67
"successRate": 0.0663,
"total": 166,
"unresolvedFailureCount": 68
},
"Kunlunxin_p-800": {
"attributableFailureCount": 1,
@@ -4236,23 +4236,23 @@
"unresolvedFailureCount": 3
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 17,
"attributableFailureCount": 16,
"consecutiveFailures": 0,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.9444,
"decisionSuccessRate": 0.0556,
"decisionTotal": 18,
"decisionFailureRate": 0.9412,
"decisionSuccessRate": 0.0588,
"decisionTotal": 17,
"failureBreakdown": {
"ambiguous_runtime": 1,
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 3,
"model_load": 14,
"model_load": 13,
"platform_infrastructure": 1
},
"failureCount": 19,
"failureRate": 0.95,
"framework": "unknown",
"lastPlatformFailureAt": "2026-09-10T18:33:21+00:00",
"lastTerminalAt": "2026-09-11T13:55:08.941364+00:00",
"lastTerminalAt": "2026-09-11T14:13:29.151029+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
@@ -4261,7 +4261,7 @@
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 20,
"unresolvedFailureCount": 1
"unresolvedFailureCount": 2
},
"Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -6937,15 +6937,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1660,
"totalRecords": 1747,
"terminalRecords": 1661,
"totalRecords": 1748,
"totals": {
"attributableFailureCount": 438,
"decisionFailureRate": 0.8902,
"decisionSuccessRate": 0.1098,
"decisionTotal": 492,
"failureBreakdown": {
"ambiguous_runtime": 392,
"ambiguous_runtime": 393,
"backend_operator": 40,
"framework_architecture_unsupported": 274,
"memory_capacity": 11,
@@ -6957,30 +6957,31 @@
"参数/模板问题": 99,
"验证失败": 673
},
"failureCount": 1606,
"failureCount": 1607,
"failureRate": 0.9675,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 4,
"successCount": 54,
"successRate": 0.0325,
"total": 1660,
"unresolvedFailureCount": 1164
"total": 1661,
"unresolvedFailureCount": 1165
},
"warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU 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 Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -6995,11 +6996,10 @@
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1747,
"summarizedRecords": 1748,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-11T14:13:29.151029+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T14:11:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523303", "taskType": "text-generation", "verifyResult": -1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-11T13:55:08.941364+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-11T13:53:22+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523314", "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": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-11T13:55:08.941340+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:47:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4332898", "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": "2026-09-11T13:46:06.650683+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-11T13:43:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523302", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "backend_operator", "failureAction": "prefer_other_proven_framework_or_gpu", "failureCategory": "backend_operator", "failureClassificationReason": "backend_version_dependent", "failureCode": "MISSING_OPERATOR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T10:53:19.117696+00:00", "modelId": "cyankiwi/Ornith-1.0-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:27:22+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4079920", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T10:26:32.495882+00:00", "modelId": "amd/Qwen2.5_3B_Instruct-onnx-ryzenai-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:15:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4080079", "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": "2026-09-08T10:26:32.495858+00:00", "modelId": "ModelCloud.AI/Marin-32B-Base-GPTQMODEL-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T10:07:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4079252", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T10:00:15.603821+00:00", "modelId": "ModelCloud.AI/Marin-32B-Base-GPTQMODEL-W4A16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T09:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079974", "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

View File

@@ -1,24 +1,24 @@
{
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "738c68727d5e46cb0c804d5688a3fcf73b48cd8fbba642535600470b9a5013be",
".modelhub_state/architecture_history_backfill.json": "82090935d69cab61e45cef156844eb06f79b87f08d3890e3de4008d11a4c1567",
".modelhub_state/market_intelligence.json": "ef2c17a7ffed95e20910b8f09ba238b5ed56d853e092bc19265a4b4d8f3d9ea1",
".modelhub_state/official_capabilities.json": "7ba6fb19ae1f168b1bb3357b611852897e727b9454d203c1a5a88baeac9a03f5",
".modelhub_state/outcome_checkpoint.json": "647455760c8596dccd6c2b8e5cc62e668e84142084d2d6703ed11291a9715de7",
".modelhub_state/architecture_compatibility_blacklist.json": "988ca54885f92de5cd18ce3b20b1c466cfd7fee247f9ce1c91e766c8fccd9fad",
".modelhub_state/architecture_history_backfill.json": "efb775205782f52444780593318d00480391cc63e106fdb6abb01eeb2379fc36",
".modelhub_state/market_intelligence.json": "ac1803b06c9c29f7d88dea4c3af5dbe79ada0161277a8e277540769a70a65706",
".modelhub_state/official_capabilities.json": "d8f010256424908356dc98402340b550ac7fbdc843e86211c0860bb93e61240d",
".modelhub_state/outcome_checkpoint.json": "1ce46ad7474fca3f2ea7fc962298a0b8c20f69db412eed990e65356e74576a27",
".modelhub_state/queue_cleanup_latest.json": "9092a0b045d21453d0210c81bf56fa209d341915359e8357a6e260c821f48c9b",
".modelhub_state/recent_outcomes.jsonl": "520cfcb8d2676632a8af1cc3c530a71e976bf7ce75f013ab6b5dde24170f7d33",
".modelhub_state/recovery_active_tasks.jsonl": "34e1233f466edfa67373f0a7b8985e6a91cbe2a6449224d6dde0f9dc790925ac",
".modelhub_state/recovery_intents.jsonl": "49314e44242bd05c4022529c1969f5c720978419e06a2fb30116e44927093632",
".modelhub_state/recent_outcomes.jsonl": "120eccf9fa38b19d315a7cd6d5484fed6a29bc5c3a6301a857e192af6e539172",
".modelhub_state/recovery_active_tasks.jsonl": "e5f9dced755e1a69d4d3085b8e45578c59524ddd0751b677f1dc83e6279f2146",
".modelhub_state/recovery_intents.jsonl": "12c1ff48ba494d0f8412ae509606f558e993fd3a29f9884a0a605d814343c5f8",
".modelhub_state/routing_intelligence.json": "01755a7ae15e8408cf0586a62b0684ec4e7e2d46c2715b9b2bfe968c7d40353e",
".modelhub_state/submission_exclusions.jsonl": "3790b5c148f222a4de26d50a3d8afc58891c8da251a82d20dbaf4fc35e6dbd89",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "0f2922a5f34c5777fcbb7e7ea1512bd1784eed2b74f5d6c3f05103cb3bbea37e",
"outcomes/submissions.jsonl": "9b436339a59d073250c1f14e08f71c1148a29e5b3db2301e39b71ed36893e02b"
},
"generation": 5719,
"generation": 5720,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-11T14:12:28.018109+00:00",
"updatedAt": "2026-09-11T14:15:45.590566+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42"
}