state: generation 5164 (cycle)

This commit is contained in:
2026-09-10 12:42:26 +00:00
parent b4a26a341d
commit 73b0bc6299
9 changed files with 2234 additions and 2234 deletions

View File

@@ -1313,7 +1313,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-09-10T12:39:41.604476+00:00",
"generatedAt": "2026-09-10T12:42:25.523700+00:00",
"summary": {
"activeBlockCount": 66,
"byGpuFramework": {

View File

@@ -51,7 +51,7 @@
"4": {
"complete": false,
"lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 367,
"listingErrors": 368,
"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": "2026-09-10T12:39:41.579898+00:00",
"updatedAt": "2026-09-10T12:42:25.498814+00:00",
"version": 1
}

View File

@@ -416,121 +416,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T12:38:07.019121+00:00",
"generatedAt": "2026-09-10T12:40:49.626524+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 981.1048951048951,
"backlogHours": 981.0209790209791,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.8089244111646527,
"queueFactor": 0.9596723705970147,
"queueWeight": 0.9596723705970147,
"qualityFactor": 0.7588848470744471,
"queueFactor": 0.9655398341868783,
"queueWeight": 0.9655398341868783,
"recentSuccess": 53,
"recentSuccessRate": 0.3706293706293706,
"recentTerminal": 143,
"recentWilsonLowerBound": 0.29582198022284456,
"running": 8,
"selectionWeight": 0.7763024072961765,
"selectionWeight": 0.7327335494111962,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.833333333333332,
"waiting": 23383
"waiting": 23381
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1004.8170731707318,
"backlogHours": 1010.8711656441717,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.71073082595532,
"queueFactor": 0.9562407717067459,
"queueWeight": 0.9562407717067459,
"recentSuccess": 57,
"recentSuccessRate": 0.3475609756097561,
"recentTerminal": 164,
"recentWilsonLowerBound": 0.27892260810607894,
"qualityFactor": 0.7068528380018103,
"queueFactor": 0.9612084246519172,
"queueWeight": 0.9612084246519172,
"recentSuccess": 58,
"recentSuccessRate": 0.3558282208588957,
"recentTerminal": 163,
"recentWilsonLowerBound": 0.28642382027658386,
"running": 8,
"selectionWeight": 0.6796297934872881,
"selectionWeight": 0.679432902876457,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 27.333333333333332,
"waiting": 27465
"throughputPerHour": 27.166666666666668,
"waiting": 27462
},
"Biren_166m": {
"available": true,
"backlogHours": 128.63768115942028,
"backlogHours": 125.54716981132074,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.19172811769169357,
"qualityFactor": 0.20339070227308378,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 42,
"recentSuccessRate": 0.2028985507246377,
"recentTerminal": 207,
"recentWilsonLowerBound": 0.1537582973984552,
"recentSuccess": 45,
"recentSuccessRate": 0.21226415094339623,
"recentTerminal": 212,
"recentWilsonLowerBound": 0.16259268092113363,
"running": 8,
"selectionWeight": 0.24924655299920165,
"selectionWeight": 0.26440791295500893,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 34.5,
"waiting": 4438
"throughputPerHour": 35.333333333333336,
"waiting": 4436
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 833.0588235294117,
"backlogHours": 867.1224489795919,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.1005076603987606,
"queueFactor": 0.9835104019602197,
"queueWeight": 0.9835104019602197,
"recentSuccess": 18,
"recentSuccessRate": 0.17647058823529413,
"recentTerminal": 102,
"recentWilsonLowerBound": 0.11464223172099423,
"qualityFactor": 0.08820936674631448,
"queueFactor": 0.9835804216218148,
"queueWeight": 0.9835804216218148,
"recentSuccess": 17,
"recentSuccessRate": 0.17346938775510204,
"recentTerminal": 98,
"recentWilsonLowerBound": 0.11122039941721076,
"running": 7,
"selectionWeight": 0.0988503294788663,
"selectionWeight": 0.08676100613533329,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.0,
"waiting": 14162
"throughputPerHour": 16.333333333333332,
"waiting": 14163
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 473.1428571428571,
"backlogHours": 473.0357142857143,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.3217242612631654,
"queueFactor": 1.0706104167122041,
"queueWeight": 1.0706104167122041,
"recentSuccess": 30,
"recentSuccessRate": 0.26785714285714285,
"qualityFactor": 0.2758647629308549,
"queueFactor": 1.0771789308477744,
"queueWeight": 1.0771789308477744,
"recentSuccess": 29,
"recentSuccessRate": 0.25892857142857145,
"recentTerminal": 112,
"recentWilsonLowerBound": 0.19454473061185254,
"recentWilsonLowerBound": 0.18675273129699618,
"running": 7,
"selectionWeight": 0.3444413454173835,
"selectionWeight": 0.297155710392433,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.666666666666668,
"waiting": 8832
"waiting": 8830
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 54.758620689655174,
"backlogHours": 54.11363636363637,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -540,196 +540,196 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 21,
"recentSuccessRate": 0.08045977011494253,
"recentTerminal": 261,
"recentWilsonLowerBound": 0.05322533693345441,
"recentSuccessRate": 0.07954545454545454,
"recentTerminal": 264,
"recentWilsonLowerBound": 0.05261357852368633,
"running": 7,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 43.5,
"waiting": 2382
"throughputPerHour": 44.0,
"waiting": 2381
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 88.33204633204633,
"backlogHours": 89.01945525291828,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.13811088511591166,
"qualityFactor": 0.13184352833914287,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 45,
"recentSuccessRate": 0.17374517374517376,
"recentTerminal": 259,
"recentWilsonLowerBound": 0.13246006700318616,
"running": 3,
"selectionWeight": 0.17954415065068516,
"recentSuccessRate": 0.17509727626459143,
"recentTerminal": 257,
"recentWilsonLowerBound": 0.13351273220466534,
"running": 2,
"selectionWeight": 0.17139658684088574,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 43.166666666666664,
"throughputPerHour": 42.833333333333336,
"waiting": 3813
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 1934.125,
"backlogHours": 1856.5199999999998,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.0775789407655146,
"queueFactor": 0.8667774955505997,
"queueWeight": 0.8667774955505997,
"recentSuccess": 9,
"recentSuccessRate": 0.1875,
"recentTerminal": 48,
"recentWilsonLowerBound": 0.10191276348200173,
"qualityFactor": 0.09034483086797271,
"queueFactor": 0.8774391237719955,
"queueWeight": 0.8774391237719955,
"recentSuccess": 10,
"recentSuccessRate": 0.2,
"recentTerminal": 50,
"recentWilsonLowerBound": 0.11243629945973886,
"running": 2,
"selectionWeight": 0.06724367998420107,
"selectionWeight": 0.0792720892341231,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.0,
"waiting": 15473
"throughputPerHour": 8.333333333333334,
"waiting": 15471
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 658.2424242424242,
"backlogHours": 685.8947368421052,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.1858029952252438,
"queueFactor": 1.018878568970374,
"queueWeight": 1.018878568970374,
"qualityFactor": 0.1914859805697329,
"queueFactor": 1.0187868234556945,
"queueWeight": 1.0187868234556945,
"recentSuccess": 22,
"recentSuccessRate": 0.2222222222222222,
"recentTerminal": 99,
"recentWilsonLowerBound": 0.1515799287727833,
"recentSuccessRate": 0.23157894736842105,
"recentTerminal": 95,
"recentWilsonLowerBound": 0.15819566451338007,
"running": 7,
"selectionWeight": 0.18931068988550565,
"selectionWeight": 0.195083393880937,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 16.5,
"waiting": 10861
"throughputPerHour": 15.833333333333334,
"waiting": 10860
},
"MetaX_c-500": {
"available": true,
"backlogHours": 536.0625,
"backlogHours": 548.688,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.28125148525201055,
"queueFactor": 1.0507466007984554,
"queueWeight": 1.0507466007984554,
"recentSuccess": 32,
"recentSuccessRate": 0.25,
"recentTerminal": 128,
"recentWilsonLowerBound": 0.183011770761507,
"qualityFactor": 0.25615930009239335,
"queueFactor": 1.053472299588357,
"queueWeight": 1.053472299588357,
"recentSuccess": 31,
"recentSuccessRate": 0.248,
"recentTerminal": 125,
"recentWilsonLowerBound": 0.18056639010525916,
"running": 4,
"selectionWeight": 0.295524042098067,
"selectionWeight": 0.26985672692927765,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.333333333333332,
"waiting": 11436
"throughputPerHour": 20.833333333333332,
"waiting": 11431
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1780.9166666666667,
"backlogHours": 1780.3333333333333,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.8172941861157234,
"queueFactor": 0.8775740408944683,
"queueWeight": 0.8775740408944683,
"recentSuccess": 29,
"recentSuccessRate": 0.4027777777777778,
"qualityFactor": 0.697287236025227,
"queueFactor": 0.8829716128344076,
"queueWeight": 0.8829716128344076,
"recentSuccess": 28,
"recentSuccessRate": 0.3888888888888889,
"recentTerminal": 72,
"recentWilsonLowerBound": 0.297209352009533,
"running": 4,
"selectionWeight": 0.717236161509131,
"recentWilsonLowerBound": 0.2846554187000152,
"running": 6,
"selectionWeight": 0.615684835402041,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.0,
"waiting": 21371
"waiting": 21364
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 4034.285714285714,
"backlogHours": 4034.5714285714284,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.15146815659851331,
"queueFactor": 0.7762744817880867,
"queueWeight": 0.7762744817880867,
"qualityFactor": 0.1420984300515989,
"queueFactor": 0.7810023283337604,
"queueWeight": 0.7810023283337604,
"recentSuccess": 6,
"recentSuccessRate": 0.2857142857142857,
"recentTerminal": 21,
"recentWilsonLowerBound": 0.138136757456282,
"running": 2,
"selectionWeight": 0.11758086477090768,
"selectionWeight": 0.11097920472287072,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 3.5,
"waiting": 14120
"waiting": 14121
},
"Vastai_va16": {
"available": true,
"backlogHours": 899.0149253731344,
"backlogHours": 885.6176470588235,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.3506680513165325,
"queueFactor": 0.9723335530705913,
"queueWeight": 0.9723335530705913,
"recentSuccess": 20,
"recentSuccessRate": 0.29850746268656714,
"recentTerminal": 67,
"recentWilsonLowerBound": 0.20231361154976887,
"qualityFactor": 0.36357633383122445,
"queueFactor": 0.9804715595159602,
"queueWeight": 0.9804715595159602,
"recentSuccess": 21,
"recentSuccessRate": 0.3088235294117647,
"recentTerminal": 68,
"recentWilsonLowerBound": 0.21172233668927842,
"running": 16,
"selectionWeight": 0.3409663122849445,
"selectionWeight": 0.356476255034596,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 11.166666666666666,
"waiting": 10039
"throughputPerHour": 11.333333333333334,
"waiting": 10037
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 486.16822429906546,
"backlogHours": 490.64150943396226,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 2.5,
"queueFactor": 1.0662580482789175,
"queueWeight": 1.0662580482789175,
"recentSuccess": 63,
"recentSuccessRate": 0.5887850467289719,
"recentTerminal": 107,
"recentWilsonLowerBound": 0.4940515755657606,
"queueFactor": 1.0712906061952046,
"queueWeight": 1.0712906061952046,
"recentSuccess": 64,
"recentSuccessRate": 0.6037735849056604,
"recentTerminal": 106,
"recentWilsonLowerBound": 0.5086016567776961,
"running": 6,
"selectionWeight": 2.6656451206972935,
"selectionWeight": 2.6782265154880114,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.833333333333332,
"waiting": 8670
"throughputPerHour": 17.666666666666668,
"waiting": 8668
}
},
"queueAttemptedAt": "2026-09-10T12:29:21.493262+00:00",
"queueAttemptedAt": "2026-09-10T12:40:49.626524+00:00",
"queueError": null,
"queueUpdatedAt": "2026-09-10T12:29:21.493262+00:00",
"queueUpdatedAt": "2026-09-10T12:40:49.626524+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": "2026-09-10T12:32:30.185165+00:00",
"lastSyncTime": "2026-09-10T12:32:29.847014+00:00",
"generatedAt": "2026-09-10T12:40:43.152635+00:00",
"lastSyncTime": "2026-09-10T12:40:42.405633+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -1793,29 +1793,29 @@
"unresolvedFailureCount": 7
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 71,
"decisionFailureRate": 0.8765,
"decisionSuccessRate": 0.1235,
"decisionTotal": 81,
"attributableFailureCount": 72,
"decisionFailureRate": 0.878,
"decisionSuccessRate": 0.122,
"decisionTotal": 82,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 23,
"model_load": 24,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 137,
"failureRate": 0.932,
"failureCount": 138,
"failureRate": 0.9324,
"framework": "unknown",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.068,
"successRate": 0.0676,
"targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation",
"total": 147,
"total": 148,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800|unknown|text-generation": {
@@ -2293,28 +2293,28 @@
"unresolvedFailureCount": 5
},
"unknown": {
"attributableFailureCount": 124,
"decisionFailureRate": 0.7209,
"decisionSuccessRate": 0.2791,
"decisionTotal": 172,
"attributableFailureCount": 125,
"decisionFailureRate": 0.7225,
"decisionSuccessRate": 0.2775,
"decisionTotal": 173,
"failureBreakdown": {
"ambiguous_runtime": 115,
"backend_operator": 3,
"framework_architecture_unsupported": 88,
"memory_capacity": 5,
"model_load": 25,
"model_load": 26,
"tokenizer_compatibility": 3,
"参数/模板问题": 56,
"验证失败": 673
},
"failureCount": 968,
"failureCount": 969,
"failureRate": 0.9528,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 48,
"successRate": 0.0472,
"total": 1016,
"total": 1017,
"unresolvedFailureCount": 844
},
"vllm": {
@@ -2445,7 +2445,7 @@
"unresolvedFailureCount": 1
}
},
"generatedAt": "2026-09-10T12:32:30.179883+00:00",
"generatedAt": "2026-09-10T12:40:43.148795+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 26,
@@ -2608,26 +2608,26 @@
"unresolvedFailureCount": 43
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 71,
"decisionFailureRate": 0.8765,
"decisionSuccessRate": 0.1235,
"decisionTotal": 81,
"attributableFailureCount": 72,
"decisionFailureRate": 0.878,
"decisionSuccessRate": 0.122,
"decisionTotal": 82,
"failureBreakdown": {
"ambiguous_runtime": 17,
"framework_architecture_unsupported": 47,
"memory_capacity": 1,
"model_load": 23,
"model_load": 24,
"参数/模板问题": 2,
"验证失败": 47
},
"failureCount": 137,
"failureRate": 0.932,
"failureCount": 138,
"failureRate": 0.9324,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 10,
"successRate": 0.068,
"total": 147,
"successRate": 0.0676,
"total": 148,
"unresolvedFailureCount": 66
},
"Kunlunxin_p-800": {
@@ -4125,11 +4125,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 15,
"ambiguous_runtime": 14,
"framework_architecture_unsupported": 1,
"tokenizer_compatibility": 1
},
"failureCount": 17,
"failureCount": 16,
"failureRate": 1.0,
"framework": "unknown",
"lastPlatformFailureAt": null,
@@ -4141,8 +4141,8 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 15
"total": 16,
"unresolvedFailureCount": 14
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 4,
@@ -4251,7 +4251,7 @@
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 16,
"consecutiveFailures": 4,
"consecutiveFailures": 5,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8421,
"decisionSuccessRate": 0.1579,
@@ -4265,7 +4265,7 @@
"failureRate": 0.85,
"framework": "unknown",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-10T12:15:14.346623+00:00",
"lastTerminalAt": "2026-09-10T12:40:42.405633+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -7031,19 +7031,19 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 1584,
"totalRecords": 1671,
"terminalRecords": 1585,
"totalRecords": 1672,
"totals": {
"attributableFailureCount": 414,
"decisionFailureRate": 0.8903,
"decisionSuccessRate": 0.1097,
"decisionTotal": 465,
"attributableFailureCount": 415,
"decisionFailureRate": 0.8906,
"decisionSuccessRate": 0.1094,
"decisionTotal": 466,
"failureBreakdown": {
"ambiguous_runtime": 345,
"backend_operator": 35,
"framework_architecture_unsupported": 272,
"memory_capacity": 11,
"model_load": 47,
"model_load": 48,
"platform_infrastructure": 3,
"repository_structure": 5,
"runtime_memory": 6,
@@ -7051,21 +7051,21 @@
"参数/模板问题": 98,
"验证失败": 673
},
"failureCount": 1533,
"failureCount": 1534,
"failureRate": 0.9678,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 3,
"successCount": 51,
"successRate": 0.0322,
"total": 1584,
"total": 1585,
"unresolvedFailureCount": 1116
},
"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 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。",
"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。",
@@ -7073,7 +7073,7 @@
"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 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。",
"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。",
@@ -7094,6 +7094,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 1671,
"summarizedRecords": 1672,
"version": 1
}

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-10T12:40:42.405633+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4523210", "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": "2026-09-10T12:32:29.847014+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:27:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477841", "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": "2026-09-10T12:23:25.501701+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4-Group128-A16-Test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:23:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471971", "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": "2026-09-10T12:23:25.501713+00:00", "modelId": "nm-testing/llama3-8b-w8_channel-a8_tensor-compressed", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T12:19:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471969", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T01:18:10.323605+00:00", "modelId": "dickeyli/llmrec-onereason-8b-sh2-grpo4-step160", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T01:11:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4460690", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T00:41:43.539049+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T00:35:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4481795", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-08T00:32:26.904386+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T00:29:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4481796", "taskType": "text-generation", "verifyResult": -1}
{"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": "2026-09-08T00:22:46.993284+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T00:13:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4482440", "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": "3e2f8ec802d0dbdbc662260df7cbc6eed4d295b968e60fa35b3aebfa7cb9b08c",
".modelhub_state/architecture_history_backfill.json": "c0e8bc8aca602b1a20c79b07baf3a40ce3d5eb54f646ecdd9f738377b05e0646",
".modelhub_state/market_intelligence.json": "846b361fdec831c5670c9d38993e88c60cc287c10b6b4b4c859e56e878175469",
".modelhub_state/official_capabilities.json": "6a2299836b4f9b5c52dfb1ec31da2e165f8b1955ff81356134ac6d55edf04469",
".modelhub_state/outcome_checkpoint.json": "11adf97f277d22140193a2f9796e1217be2f6b9d5ae09527cb769bea9d9c9489",
".modelhub_state/architecture_compatibility_blacklist.json": "03b6b3e42de09d3f7508035f2c3b687222fab8987cb368a7809ee2b5298e8433",
".modelhub_state/architecture_history_backfill.json": "0011514951749b9d16454ffbd676063a40ce02f3f7bc5607e261f740834ead79",
".modelhub_state/market_intelligence.json": "13df3f334844f70b96064bdba044957c5db38abf516ade4b58e905082d2726ba",
".modelhub_state/official_capabilities.json": "4bb613e0e7355d2ed6c52ca71c85d402d6a04bb486dcb6aa3c0231c7edddd198",
".modelhub_state/outcome_checkpoint.json": "f9c5730dccc65409b4bf65c514648f463ac58acb4d968150f8e0d224ed820b76",
".modelhub_state/queue_cleanup_latest.json": "b9038630dc67feced29c6931cb43d6d94c28bb175e6dcf80fac9c625a52887d5",
".modelhub_state/recent_outcomes.jsonl": "46859aa57c7e6a38cf09bc7d4b199b76cdd8427bf6be340d93303deb2e1a83a3",
".modelhub_state/recovery_active_tasks.jsonl": "0c5cf3113245d143c00114624a023745c9718bf8b3dc19ee01500bfe3434f613",
".modelhub_state/recovery_intents.jsonl": "c6c1e6a5e633bcc9a5e51994d56e0435c85fc2579a5ddf3da63d96e36d2692b2",
".modelhub_state/recent_outcomes.jsonl": "edde5210dbc900b7a777583294e1f6bf9fbf1aadebd7f86b8df0e59991033546",
".modelhub_state/recovery_active_tasks.jsonl": "77f09e7e8326675dfec3b1f94b25f61dc7e8a4085c99a062aef828bb27365a45",
".modelhub_state/recovery_intents.jsonl": "b0e206b9fb7eb46acd2f878617ddccb2b7d3506c46e2a217cb3a4c5f5c661a53",
".modelhub_state/routing_intelligence.json": "f36cfaf9f9ff191164b0ce0a73a3ce4bbc3a2dc4589f252d583e33b427807fc0",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "d1c3f447ce0377ed5e820c2b5ff730d29f84a96af4fd14332b138f78c0ddde76",
"ledger/submissions.jsonl": "8a621da5637d481c7de4b4e3375f2a68cbdabf71fe459244a727034f36ab3eb9",
"outcomes/submissions.jsonl": "249bd947bbece33d1e7d20b546c76ca577966a52b7f8d45fcbf882be0353517a"
},
"generation": 5163,
"generation": 5164,
"phase": "cycle",
"schemaVersion": 1,
"updatedAt": "2026-09-10T12:39:41.751733+00:00",
"updatedAt": "2026-09-10T12:42:26.330991+00:00",
"writerId": "58ff5dc2a2d64b119ad1e4560700f977"
}