state: generation 7638 (cycle)

This commit is contained in:
2026-09-15 10:24:58 +00:00
parent 5508a93938
commit b0b2e2dfb9
9 changed files with 3279 additions and 2892 deletions

View File

@@ -1591,7 +1591,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-15T10:22:00.371272+00:00", "generatedAt": "2026-09-15T10:24:57.508741+00:00",
"summary": { "summary": {
"activeBlockCount": 78, "activeBlockCount": 78,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -35,7 +35,7 @@
"2": { "2": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 555, "listingErrors": 556,
"nextPage": 1, "nextPage": 1,
"recordsScanned": 0, "recordsScanned": 0,
"uniqueRecords": 0 "uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00", "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0, "failureLogsInspected": 0,
"mode": "incremental_decision_only", "mode": "incremental_decision_only",
"nextAccountIndex": 2, "nextAccountIndex": 3,
"recordsScanned": 0, "recordsScanned": 0,
"seenTaskIds": [], "seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00", "startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0, "terminalRecords": 0,
"uniqueRecords": 0, "uniqueRecords": 0,
"updatedAt": "2026-09-15T10:22:00.347086+00:00", "updatedAt": "2026-09-15T10:24:57.484455+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,121 +416,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T10:19:40.190555+00:00", "generatedAt": "2026-09-15T10:23:13.926408+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1056.5820895522388, "backlogHours": 1064.5714285714284,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b3", "gpu": "Ascend_910-b3",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 1.85689959619709, "qualityFactor": 1.5337135295704454,
"queueFactor": 0.9900317570967277, "queueFactor": 0.9959552197537077,
"queueWeight": 0.9900317570967277, "queueWeight": 0.9959552197537077,
"recentSuccess": 46, "recentSuccess": 43,
"recentSuccessRate": 0.34328358208955223, "recentSuccessRate": 0.3233082706766917,
"recentTerminal": 134, "recentTerminal": 133,
"recentWilsonLowerBound": 0.26826599296332926, "recentWilsonLowerBound": 0.24974159584989838,
"running": 8, "running": 9,
"selectionWeight": 1.8383895699752093, "selectionWeight": 1.5275099953825677,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.333333333333332, "throughputPerHour": 22.166666666666668,
"waiting": 23597 "waiting": 23598
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1216.7826086956522, "backlogHours": 1234.941176470588,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b4", "gpu": "Ascend_910-b4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.9692876141680068, "queueFactor": 0.9740227311009731,
"queueWeight": 0.9692876141680068, "queueWeight": 0.9740227311009731,
"recentSuccess": 53, "recentSuccess": 53,
"recentSuccessRate": 0.38405797101449274, "recentSuccessRate": 0.3897058823529412,
"recentTerminal": 138, "recentTerminal": 136,
"recentWilsonLowerBound": 0.30709368733232695, "recentWilsonLowerBound": 0.3118483860305096,
"running": 8, "running": 10,
"selectionWeight": 2.423219035420017, "selectionWeight": 2.4350568277524327,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.0, "throughputPerHour": 22.666666666666668,
"waiting": 27986 "waiting": 27992
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 920.0571428571429, "backlogHours": 1007.8125,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 1.0644592271005426, "qualityFactor": 0.7418759535103232,
"queueFactor": 1.010793387391533, "queueFactor": 1.004174229920547,
"queueWeight": 1.010793387391533, "queueWeight": 1.004174229920547,
"recentSuccess": 12, "recentSuccess": 10,
"recentSuccessRate": 0.34285714285714286, "recentSuccessRate": 0.3125,
"recentTerminal": 35, "recentTerminal": 32,
"recentWilsonLowerBound": 0.20831495282688925, "recentWilsonLowerBound": 0.17952352116618736,
"running": 2, "running": 2,
"selectionWeight": 1.0759483479011305, "selectionWeight": 0.7449727143128003,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 5.833333333333333, "throughputPerHour": 5.333333333333333,
"waiting": 5367 "waiting": 5375
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1487.4193548387095, "backlogHours": 1487.225806451613,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x4", "gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.7606794259445725, "qualityFactor": 0.6207165855915062,
"queueFactor": 0.940523384578165, "queueFactor": 0.9472388373816631,
"queueWeight": 0.940523384578165, "queueWeight": 0.9472388373816631,
"recentSuccess": 17, "recentSuccess": 16,
"recentSuccessRate": 0.27419354838709675, "recentSuccessRate": 0.25806451612903225,
"recentTerminal": 62, "recentTerminal": 62,
"recentWilsonLowerBound": 0.17880918599092133, "recentWilsonLowerBound": 0.16554737249309678,
"running": 8, "running": 7,
"selectionWeight": 0.7154367882683649, "selectionWeight": 0.5879668568792139,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.333333333333334, "throughputPerHour": 10.333333333333334,
"waiting": 15370 "waiting": 15368
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 542.6796116504854, "backlogHours": 536.377358490566,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x8", "gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.3731810900113872, "qualityFactor": 0.385940905950578,
"queueFactor": 1.094090095421724, "queueFactor": 1.1038129055091737,
"queueWeight": 1.094090095421724, "queueWeight": 1.1038129055091737,
"recentSuccess": 20, "recentSuccess": 21,
"recentSuccessRate": 0.1941747572815534, "recentSuccessRate": 0.19811320754716982,
"recentTerminal": 103, "recentTerminal": 106,
"recentWilsonLowerBound": 0.12936210686118582, "recentWilsonLowerBound": 0.1333879484800526,
"running": 7, "running": 7,
"selectionWeight": 0.40829373438014166, "selectionWeight": 0.4260065527521502,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.166666666666668, "throughputPerHour": 17.666666666666668,
"waiting": 9316 "waiting": 9476
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 51.0, "backlogHours": 51.57692307692308,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -539,197 +539,197 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 14, "recentSuccess": 15,
"recentSuccessRate": 0.04430379746835443, "recentSuccessRate": 0.04807692307692308,
"recentTerminal": 316, "recentTerminal": 312,
"recentWilsonLowerBound": 0.026571266147141746, "recentWilsonLowerBound": 0.029348428122836608,
"running": 26, "running": 25,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 52.666666666666664, "throughputPerHour": 52.0,
"waiting": 2686 "waiting": 2682
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 110.81012658227849, "backlogHours": 134.7076923076923,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-150", "gpu": "Iluvatar_bi-150",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 50, "maxConcurrentTasks": 50,
"qualityFactor": 0.7990502329160637, "qualityFactor": 1.0424761535427711,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 55, "recentSuccess": 52,
"recentSuccessRate": 0.2320675105485232, "recentSuccessRate": 0.26666666666666666,
"recentTerminal": 237, "recentTerminal": 195,
"recentWilsonLowerBound": 0.18285403952084475, "recentWilsonLowerBound": 0.20954319212829256,
"running": 7, "running": 5,
"selectionWeight": 1.0387653027908827, "selectionWeight": 1.3552189996056025,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 39.5, "throughputPerHour": 32.5,
"waiting": 4377 "waiting": 4378
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2652.6666666666665, "backlogHours": 2580.6486486486483,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_mrv-100", "gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.9963205889406412, "qualityFactor": 1.1402011207481557,
"queueFactor": 0.862347304677018, "queueFactor": 0.8720807517235599,
"queueWeight": 0.862347304677018, "queueWeight": 0.8720807517235599,
"recentSuccess": 12, "recentSuccess": 13,
"recentSuccessRate": 0.3333333333333333, "recentSuccessRate": 0.35135135135135137,
"recentTerminal": 36, "recentTerminal": 37,
"recentWilsonLowerBound": 0.20214424774586046, "recentWilsonLowerBound": 0.21825406631100872,
"running": 2, "running": 2,
"selectionWeight": 0.8591743744671811, "selectionWeight": 0.9943474504980971,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.0, "throughputPerHour": 6.166666666666667,
"waiting": 15916 "waiting": 15914
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 742.4516129032259, "backlogHours": 735.6382978723404,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.40906838689571956, "qualityFactor": 0.4440445296813977,
"queueFactor": 1.0438410912518685, "queueFactor": 1.052728506877127,
"queueWeight": 1.0438410912518685, "queueWeight": 1.052728506877127,
"recentSuccess": 19, "recentSuccess": 20,
"recentSuccessRate": 0.20430107526881722, "recentSuccessRate": 0.2127659574468085,
"recentTerminal": 93, "recentTerminal": 94,
"recentWilsonLowerBound": 0.1348753753056426, "recentWilsonLowerBound": 0.14216772302859196,
"running": 7, "running": 7,
"selectionWeight": 0.42700239137386947, "selectionWeight": 0.4674583347184539,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.5, "throughputPerHour": 15.666666666666666,
"waiting": 11508 "waiting": 11525
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 777.6923076923077, "backlogHours": 786.8,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "MetaX_c-500", "gpu": "MetaX_c-500",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 0.9055063308730318, "qualityFactor": 0.8979056554663979,
"queueFactor": 1.0366053401478634, "queueFactor": 1.0421647517608266,
"queueWeight": 1.0366053401478634, "queueWeight": 1.0421647517608266,
"recentSuccess": 25, "recentSuccess": 25,
"recentSuccessRate": 0.27472527472527475, "recentSuccessRate": 0.2777777777777778,
"recentTerminal": 91, "recentTerminal": 90,
"recentWilsonLowerBound": 0.19355049670786545, "recentWilsonLowerBound": 0.1957955914762625,
"running": 6, "running": 4,
"selectionWeight": 0.9386526981206829, "selectionWeight": 0.9357656245337809,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.166666666666666, "throughputPerHour": 15.0,
"waiting": 11795 "waiting": 11802
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1596.3409090909092, "backlogHours": 1635.8372093023256,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Mthreads_s4000", "gpu": "Mthreads_s4000",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 2.227843459631498, "qualityFactor": 1.9333405485250128,
"queueFactor": 0.9306058232532681, "queueFactor": 0.9338024748683792,
"queueWeight": 0.9306058232532681, "queueWeight": 0.9338024748683792,
"recentSuccess": 34, "recentSuccess": 32,
"recentSuccessRate": 0.38636363636363635, "recentSuccessRate": 0.37209302325581395,
"recentTerminal": 88, "recentTerminal": 86,
"recentWilsonLowerBound": 0.29141940235595687, "recentWilsonLowerBound": 0.27746093282766765,
"running": 4, "running": 4,
"selectionWeight": 2.0732440968297796, "selectionWeight": 1.8053581889760466,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.666666666666666, "throughputPerHour": 14.333333333333334,
"waiting": 23413 "waiting": 23447
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 3523.153846153846, "backlogHours": 3522.923076923077,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Sunrise_pt-200-x1", "gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.9113798269486645, "qualityFactor": 0.8810887699110597,
"queueFactor": 0.8264086819971208, "queueFactor": 0.8323012730873462,
"queueWeight": 0.8264086819971208, "queueWeight": 0.8323012730873462,
"recentSuccess": 9, "recentSuccess": 9,
"recentSuccessRate": 0.34615384615384615, "recentSuccessRate": 0.34615384615384615,
"recentTerminal": 26, "recentTerminal": 26,
"recentWilsonLowerBound": 0.1941201497285213, "recentWilsonLowerBound": 0.1941201497285213,
"running": 2, "running": 2,
"selectionWeight": 0.7531722015874098, "selectionWeight": 0.7333313048999388,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 4.333333333333333, "throughputPerHour": 4.333333333333333,
"waiting": 15267 "waiting": 15266
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1576.0408163265308, "backlogHours": 1576.1632653061226,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Vastai_va16", "gpu": "Vastai_va16",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 16, "maxConcurrentTasks": 16,
"qualityFactor": 0.3788289484447225, "qualityFactor": 0.36623800782312227,
"queueFactor": 0.9323940494869327, "queueFactor": 0.9390221848041673,
"queueWeight": 0.9323940494869327, "queueWeight": 0.9390221848041673,
"recentSuccess": 11, "recentSuccess": 11,
"recentSuccessRate": 0.22448979591836735, "recentSuccessRate": 0.22448979591836735,
"recentTerminal": 49, "recentTerminal": 49,
"recentWilsonLowerBound": 0.1302483771472861, "recentWilsonLowerBound": 0.1302483771472861,
"running": 16, "running": 16,
"selectionWeight": 0.3532178573032513, "selectionWeight": 0.343905614264394,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.166666666666666, "throughputPerHour": 8.166666666666666,
"waiting": 12871 "waiting": 12872
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 734.9714285714285, "backlogHours": 744.3461538461539,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "hygon_k100-ai", "gpu": "hygon_k100-ai",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 6, "maxConcurrentTasks": 6,
"qualityFactor": 1.1582233717614714, "qualityFactor": 1.1446276916546212,
"queueFactor": 1.0454277979538638, "queueFactor": 1.0508719276189027,
"queueWeight": 1.0454277979538638, "queueWeight": 1.0508719276189027,
"recentSuccess": 31, "recentSuccess": 31,
"recentSuccessRate": 0.29523809523809524, "recentSuccessRate": 0.2980769230769231,
"recentTerminal": 105, "recentTerminal": 104,
"recentWilsonLowerBound": 0.2164639494567783, "recentWilsonLowerBound": 0.21863880553781623,
"running": 6, "running": 7,
"selectionWeight": 1.2108389090792944, "selectionWeight": 1.2028571087350668,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.5, "throughputPerHour": 17.333333333333332,
"waiting": 12862 "waiting": 12902
} }
}, },
"queueAttemptedAt": "2026-09-15T10:10:46.949206+00:00", "queueAttemptedAt": "2026-09-15T10:23:13.926408+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-15T10:10:46.949206+00:00", "queueUpdatedAt": "2026-09-15T10:23:13.926408+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Iluvatar_mrv-100", "Iluvatar_mrv-100",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-15T09:34:13.223752+00:00", "generatedAt": "2026-09-15T10:23:01.298200+00:00",
"lastSyncTime": "2026-09-15T09:34:12.938183+00:00", "lastSyncTime": "2026-09-15T10:23:01.246264+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2080,9 +2080,9 @@
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 103, "attributableFailureCount": 103,
"decisionFailureRate": 0.8729, "decisionFailureRate": 0.8655,
"decisionSuccessRate": 0.1271, "decisionSuccessRate": 0.1345,
"decisionTotal": 118, "decisionTotal": 119,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 23, "ambiguous_runtime": 23,
"framework_architecture_unsupported": 58, "framework_architecture_unsupported": 58,
@@ -2094,16 +2094,16 @@
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 177, "failureCount": 177,
"failureRate": 0.9219, "failureRate": 0.9171,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 15, "successCount": 16,
"successRate": 0.0781, "successRate": 0.0829,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 192, "total": 193,
"unresolvedFailureCount": 73 "unresolvedFailureCount": 73
}, },
"Iluvatar_mrv-100|vllm|text-generation": { "Iluvatar_mrv-100|vllm|text-generation": {
@@ -2609,9 +2609,9 @@
}, },
"unknown": { "unknown": {
"attributableFailureCount": 170, "attributableFailureCount": 170,
"decisionFailureRate": 0.7489, "decisionFailureRate": 0.7456,
"decisionSuccessRate": 0.2511, "decisionSuccessRate": 0.2544,
"decisionTotal": 227, "decisionTotal": 228,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 156, "ambiguous_runtime": 156,
"backend_operator": 4, "backend_operator": 4,
@@ -2624,13 +2624,13 @@
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1066, "failureCount": 1066,
"failureRate": 0.9492, "failureRate": 0.9484,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 57, "successCount": 58,
"successRate": 0.0508, "successRate": 0.0516,
"total": 1123, "total": 1124,
"unresolvedFailureCount": 895 "unresolvedFailureCount": 895
}, },
"vllm": { "vllm": {
@@ -2766,7 +2766,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-15T09:34:13.219285+00:00", "generatedAt": "2026-09-15T10:23:01.290338+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 40, "attributableFailureCount": 40,
@@ -2933,9 +2933,9 @@
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"attributableFailureCount": 106, "attributableFailureCount": 106,
"decisionFailureRate": 0.876, "decisionFailureRate": 0.8689,
"decisionSuccessRate": 0.124, "decisionSuccessRate": 0.1311,
"decisionTotal": 121, "decisionTotal": 122,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 23, "ambiguous_runtime": 23,
"framework_architecture_unsupported": 60, "framework_architecture_unsupported": 60,
@@ -2947,13 +2947,13 @@
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 180, "failureCount": 180,
"failureRate": 0.9231, "failureRate": 0.9184,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 15, "successCount": 16,
"successRate": 0.0769, "successRate": 0.0816,
"total": 195, "total": 196,
"unresolvedFailureCount": 73 "unresolvedFailureCount": 73
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
@@ -5701,32 +5701,32 @@
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 13, "attributableFailureCount": 13,
"consecutiveFailures": 11, "consecutiveFailures": 0,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.8667, "decisionFailureRate": 0.8125,
"decisionSuccessRate": 0.1333, "decisionSuccessRate": 0.1875,
"decisionTotal": 15, "decisionTotal": 16,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4, "ambiguous_runtime": 3,
"framework_architecture_unsupported": 9, "framework_architecture_unsupported": 9,
"model_load": 3, "model_load": 3,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 18, "failureCount": 17,
"failureRate": 0.9, "failureRate": 0.85,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-15T09:34:12.938151+00:00", "lastTerminalAt": "2026-09-15T10:23:01.246264+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 3,
"successRate": 0.1, "successRate": 0.15,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 20, "total": 20,
"unresolvedFailureCount": 5 "unresolvedFailureCount": 4
}, },
"Kunlunxin_p-800|unknown|text-generation": { "Kunlunxin_p-800|unknown|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -9370,13 +9370,13 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1914, "terminalRecords": 1915,
"totalRecords": 2008, "totalRecords": 2009,
"totals": { "totals": {
"attributableFailureCount": 592, "attributableFailureCount": 592,
"decisionFailureRate": 0.8997, "decisionFailureRate": 0.8983,
"decisionSuccessRate": 0.1003, "decisionSuccessRate": 0.1017,
"decisionTotal": 658, "decisionTotal": 659,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 460, "ambiguous_runtime": 460,
"backend_operator": 44, "backend_operator": 44,
@@ -9391,13 +9391,13 @@
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1848, "failureCount": 1848,
"failureRate": 0.9655, "failureRate": 0.965,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 7, "platformFailureCount": 7,
"successCount": 66, "successCount": 67,
"successRate": 0.0345, "successRate": 0.035,
"total": 1914, "total": 1915,
"unresolvedFailureCount": 1249 "unresolvedFailureCount": 1249
}, },
"warnings": [ "warnings": [
@@ -9436,6 +9436,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 2008, "summarizedRecords": 2009,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,4 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-15T10:23:01.246264+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-15T10:15:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4590619", "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"], "framework": "", "lastSyncTime": "2026-09-15T09:34:12.938151+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4594446", "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"], "framework": "", "lastSyncTime": "2026-09-15T09:34:12.938151+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4594446", "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", "framework": "", "lastSyncTime": "2026-09-15T09:34:12.938183+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4590565", "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", "framework": "", "lastSyncTime": "2026-09-15T09:34:12.938183+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:27:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4590565", "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"], "framework": "vllm", "lastSyncTime": "2026-09-15T09:23:51.409303+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:17:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4595432", "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"], "framework": "vllm", "lastSyncTime": "2026-09-15T09:23:51.409303+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T09:17:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4595432", "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": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T06:56:22.046014+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496936", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T06:56:22.046014+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496936", "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": "2026-09-10T06:56:22.046035+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477785", "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": "2026-09-10T06:56:22.046035+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477785", "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": "2026-09-10T06:40:56.094753+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:35:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505108", "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": "2026-09-10T06:40:56.094753+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:35:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505108", "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": "2026-09-10T06:33:34.200730+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:33:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505109", "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", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "ddf818a4c1ccdcc03db1813707306f469d6561607f62ee7610341f5f970f5395", ".modelhub_state/architecture_compatibility_blacklist.json": "dd9d3d31df70d3a7e5370e3d471c76e971c7478fb4731ebbddad50d52929e06a",
".modelhub_state/architecture_history_backfill.json": "4af96544273a448e738b4024014e3bf1cf0a12b35a695a6161cf135d9e10d070", ".modelhub_state/architecture_history_backfill.json": "91ca71d0ef1eff50439b7e36106d87c3846fa0f9de6259505715f223bbd59690",
".modelhub_state/market_intelligence.json": "362a41f0b6288b612c4ef7c955c9334c409fd9606cca7ffde27465ff493cf8f1", ".modelhub_state/market_intelligence.json": "41bdacb774185038b994633f13f4c11c5201ab202a0b281c464af1d8ff4d0af8",
".modelhub_state/official_capabilities.json": "170887fcd1975295b6206b73bdd6757e245baad878cfdbe27337ee545cb28c2e", ".modelhub_state/official_capabilities.json": "652368c93af00b50f96dcd1222eff5322af26cce033226b69cd335d74aa19190",
".modelhub_state/outcome_checkpoint.json": "85c7047c14b05c4f0702e4fdb52f94a66755b9b2da4540e17afa12f933951ac0", ".modelhub_state/outcome_checkpoint.json": "bbb7888994bfd95bb7212c4a648fbc3b68053fcbf9a1a65bdac8c646d6f6b2ff",
".modelhub_state/queue_cleanup_latest.json": "3e511035a77fe68d9f1adfb35e149ee220beed7c3962d87b7d1892cc816fb69a", ".modelhub_state/queue_cleanup_latest.json": "3e511035a77fe68d9f1adfb35e149ee220beed7c3962d87b7d1892cc816fb69a",
".modelhub_state/recent_outcomes.jsonl": "77af9d8b75ad01058b1f6eca8d532641927017469807f2e010ee8f789b329728", ".modelhub_state/recent_outcomes.jsonl": "c682a7ee26c55220007fa5ddaa955de43e395442e948f31306061792c6e5f15b",
".modelhub_state/recovery_active_tasks.jsonl": "360a8d348bf1fcab1540c58614541e35ac1e08e9642b7d0e68060a7cfbcf582d", ".modelhub_state/recovery_active_tasks.jsonl": "819d2fac64bc0a84cd73d01e1159be88e0c44cd9a0338f3796301db466223d2e",
".modelhub_state/recovery_intents.jsonl": "425914e069abaef0eb4eff5f1f29a45ea6cfc086b51f72d87821800a91207252", ".modelhub_state/recovery_intents.jsonl": "1a5ddafdf7883a46aabe713703255cf4969c6a2c5b302d76ebd8354693f5502d",
".modelhub_state/routing_intelligence.json": "5c8070320d5755aaf914efa600b2d376703dd44fa4a64fb6e2078f23011d8cb3", ".modelhub_state/routing_intelligence.json": "5c8070320d5755aaf914efa600b2d376703dd44fa4a64fb6e2078f23011d8cb3",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552", ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983", ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "7a53355bf1c608ccb5042e684c700b49a1a628a9aae3574f4347b66b4db52401", "ledger/submissions.jsonl": "7a53355bf1c608ccb5042e684c700b49a1a628a9aae3574f4347b66b4db52401",
"outcomes/submissions.jsonl": "f1e64b3f4edb267833268a6800655e83ab445754fd47dd2aed3178b0cfa85b36" "outcomes/submissions.jsonl": "f1e64b3f4edb267833268a6800655e83ab445754fd47dd2aed3178b0cfa85b36"
}, },
"generation": 7637, "generation": 7638,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-15T10:22:00.459932+00:00", "updatedAt": "2026-09-15T10:24:58.163088+00:00",
"writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c" "writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c"
} }