state: generation 7207 (cycle)

This commit is contained in:
2026-09-14 13:58:11 +00:00
parent fa281f0cae
commit d4d6e4e87f
9 changed files with 2125 additions and 2130 deletions

View File

@@ -1502,7 +1502,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-14T13:55:19.890384+00:00", "generatedAt": "2026-09-14T13:58:10.674992+00:00",
"summary": { "summary": {
"activeBlockCount": 75, "activeBlockCount": 75,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -19,7 +19,7 @@
"10": { "10": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 523, "listingErrors": 524,
"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": 10, "nextAccountIndex": 11,
"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": "2026-09-14T13:55:19.863396+00:00", "updatedAt": "2026-09-14T13:58:10.650505+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,61 +416,61 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-14T13:53:30.656549+00:00", "generatedAt": "2026-09-14T13:56:30.149034+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 844.1204819277108, "backlogHours": 870.3354037267081,
"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": 1.306880696626297, "qualityFactor": 1.4896652425886021,
"queueFactor": 0.9888858667807126, "queueFactor": 0.985380918005141,
"queueWeight": 0.9888858667807126, "queueWeight": 0.985380918005141,
"recentSuccess": 51, "recentSuccess": 51,
"recentSuccessRate": 0.3072289156626506, "recentSuccessRate": 0.3167701863354037,
"recentTerminal": 166, "recentTerminal": 161,
"recentWilsonLowerBound": 0.24206818397022814, "recentWilsonLowerBound": 0.24989246350892488,
"running": 8, "running": 8,
"selectionWeight": 1.292355850462277, "selectionWeight": 1.467887704262308,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 27.666666666666668, "throughputPerHour": 26.833333333333332,
"waiting": 23354 "waiting": 23354
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1350.0487804878048, "backlogHours": 1350.1463414634147,
"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": 2.478603003883419, "qualityFactor": 2.5,
"queueFactor": 0.9216253600420968, "queueFactor": 0.9225714671121739,
"queueWeight": 0.9216253600420968, "queueWeight": 0.9225714671121739,
"recentSuccess": 50, "recentSuccess": 49,
"recentSuccessRate": 0.4065040650406504, "recentSuccessRate": 0.3983739837398374,
"recentTerminal": 123, "recentTerminal": 123,
"recentWilsonLowerBound": 0.32380845131879504, "recentWilsonLowerBound": 0.3161974081257675,
"running": 9, "running": 8,
"selectionWeight": 2.284343385855479, "selectionWeight": 2.306428667780435,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.5, "throughputPerHour": 20.5,
"waiting": 27676 "waiting": 27678
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 135.21531100478467, "backlogHours": 135.35885167464113,
"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": 0.06716089941923989, "qualityFactor": 0.07137978952360001,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 20, "recentSuccess": 20,
@@ -478,59 +478,59 @@
"recentTerminal": 209, "recentTerminal": 209,
"recentWilsonLowerBound": 0.06280212376163305, "recentWilsonLowerBound": 0.06280212376163305,
"running": 2, "running": 2,
"selectionWeight": 0.08730916924501186, "selectionWeight": 0.09279372638068002,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 34.833333333333336, "throughputPerHour": 34.833333333333336,
"waiting": 4710 "waiting": 4715
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1304.8695652173913, "backlogHours": 1324.1470588235293,
"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": 0.8228329860259592, "qualityFactor": 1.0344712583624167,
"queueFactor": 0.926342885598623, "queueFactor": 0.9252662313183135,
"queueWeight": 0.926342885598623, "queueWeight": 0.9252662313183135,
"recentSuccess": 20, "recentSuccess": 21,
"recentSuccessRate": 0.2898550724637681, "recentSuccessRate": 0.3088235294117647,
"recentTerminal": 69, "recentTerminal": 68,
"recentWilsonLowerBound": 0.19615912140759176, "recentWilsonLowerBound": 0.21172233668927842,
"running": 8, "running": 7,
"selectionWeight": 0.7622254826410185, "selectionWeight": 0.9571613226321067,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.5, "throughputPerHour": 11.333333333333334,
"waiting": 15006 "waiting": 15007
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 433.584, "backlogHours": 430.0952380952381,
"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": 0.523907963930986, "qualityFactor": 0.6563890025275056,
"queueFactor": 1.0928129896040808, "queueFactor": 1.0952731725858118,
"queueWeight": 1.0928129896040808, "queueWeight": 1.0952731725858118,
"recentSuccess": 28, "recentSuccess": 30,
"recentSuccessRate": 0.224, "recentSuccessRate": 0.23809523809523808,
"recentTerminal": 125, "recentTerminal": 126,
"recentWilsonLowerBound": 0.15976874687261633, "recentWilsonLowerBound": 0.17217416354451306,
"running": 9, "running": 7,
"selectionWeight": 0.5725334283408078, "selectionWeight": 0.7189252652487376,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.833333333333332, "throughputPerHour": 21.0,
"waiting": 9033 "waiting": 9032
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 51.63461538461539, "backlogHours": 52.51465798045603,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -539,38 +539,38 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 15, "recentSuccess": 14,
"recentSuccessRate": 0.04807692307692308, "recentSuccessRate": 0.04560260586319218,
"recentTerminal": 312, "recentTerminal": 307,
"recentWilsonLowerBound": 0.029348428122836608, "recentWilsonLowerBound": 0.027355744698489087,
"running": 25, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 52.0, "throughputPerHour": 51.166666666666664,
"waiting": 2685 "waiting": 2687
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 124.05797101449275, "backlogHours": 124.60194174757281,
"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": 0.872012238528105, "qualityFactor": 0.937027481988646,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 53, "recentSuccess": 53,
"recentSuccessRate": 0.2560386473429952, "recentSuccessRate": 0.25728155339805825,
"recentTerminal": 207, "recentTerminal": 206,
"recentWilsonLowerBound": 0.2014039582415214, "recentWilsonLowerBound": 0.20241217560552674,
"running": 8, "running": 9,
"selectionWeight": 1.1336159100865366, "selectionWeight": 1.21813572658524,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 34.5, "throughputPerHour": 34.333333333333336,
"waiting": 4280 "waiting": 4278
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
@@ -580,15 +580,15 @@
"gpu": "Iluvatar_mrv-100", "gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 1.2571091822886784, "qualityFactor": 1.587321736614446,
"queueFactor": 0.8613095252390045, "queueFactor": 0.8622030599156864,
"queueWeight": 0.8613095252390045, "queueWeight": 0.8622030599156864,
"recentSuccess": 16, "recentSuccess": 17,
"recentSuccessRate": 0.36363636363636365, "recentSuccessRate": 0.38636363636363635,
"recentTerminal": 44, "recentTerminal": 44,
"recentWilsonLowerBound": 0.23783334127491426, "recentWilsonLowerBound": 0.25720998886701985,
"running": 2, "running": 2,
"selectionWeight": 1.0827601129706548, "selectionWeight": 1.3685936583796565,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 7.333333333333333, "throughputPerHour": 7.333333333333333,
@@ -596,140 +596,140 @@
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 722.9032258064516, "backlogHours": 707.5578947368421,
"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": 0.47426544977717333, "qualityFactor": 0.48020504312884266,
"queueFactor": 1.012149841180428, "queueFactor": 1.0164659808942966,
"queueWeight": 1.012149841180428, "queueWeight": 1.0164659808942966,
"recentSuccess": 21, "recentSuccess": 21,
"recentSuccessRate": 0.22580645161290322, "recentSuccessRate": 0.22105263157894736,
"recentTerminal": 93, "recentTerminal": 95,
"recentWilsonLowerBound": 0.15270042020646624, "recentWilsonLowerBound": 0.14937242983925722,
"running": 7, "running": 7,
"selectionWeight": 0.48002769966933023, "selectionWeight": 0.4881120901943471,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.5, "throughputPerHour": 15.833333333333334,
"waiting": 11205 "waiting": 11203
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 632.9174311926605, "backlogHours": 638.7222222222222,
"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": 0.47400778309141145, "qualityFactor": 0.5144567630772092,
"queueFactor": 1.0325349887432103, "queueFactor": 1.032191649939593,
"queueWeight": 1.0325349887432103, "queueWeight": 1.032191649939593,
"recentSuccess": 24, "recentSuccess": 24,
"recentSuccessRate": 0.22018348623853212, "recentSuccessRate": 0.2222222222222222,
"recentTerminal": 109, "recentTerminal": 108,
"recentWilsonLowerBound": 0.1526627048081528, "recentWilsonLowerBound": 0.15412441082279263,
"running": 4, "running": 4,
"selectionWeight": 0.4894296209784846, "selectionWeight": 0.5310179751032468,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.166666666666668, "throughputPerHour": 18.0,
"waiting": 11498 "waiting": 11497
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2220.4918032786886, "backlogHours": 2184.774193548387,
"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": 2.5, "qualityFactor": 2.070714385700624,
"queueFactor": 0.8553413338444222, "queueFactor": 0.8583139316687185,
"queueWeight": 0.8553413338444222, "queueWeight": 0.8583139316687185,
"recentSuccess": 27, "recentSuccess": 25,
"recentSuccessRate": 0.4426229508196721, "recentSuccessRate": 0.4032258064516129,
"recentTerminal": 61, "recentTerminal": 62,
"recentWilsonLowerBound": 0.32507608033920443, "recentWilsonLowerBound": 0.2902468291165249,
"running": 4, "running": 4,
"selectionWeight": 2.1383533346110557, "selectionWeight": 1.7773230057536777,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.166666666666666, "throughputPerHour": 10.333333333333334,
"waiting": 22575 "waiting": 22576
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 6812.307692307692, "backlogHours": 8052.0,
"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": 1.1909224824757947, "qualityFactor": 1.914603322082336,
"queueFactor": 0.7229573832937585, "queueFactor": 0.7057836290031392,
"queueWeight": 0.7229573832937585, "queueWeight": 0.7057836290031392,
"recentSuccess": 6, "recentSuccess": 6,
"recentSuccessRate": 0.46153846153846156, "recentSuccessRate": 0.5454545454545454,
"recentTerminal": 13, "recentTerminal": 11,
"recentWilsonLowerBound": 0.23205754301488138, "recentWilsonLowerBound": 0.2800877556899882,
"running": 2, "running": 2,
"selectionWeight": 0.8609862016364075, "selectionWeight": 1.3512956807607373,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 2.1666666666666665, "throughputPerHour": 1.8333333333333333,
"waiting": 14760 "waiting": 14762
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1467.0588235294117, "backlogHours": 1411.5849056603772,
"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": 1.23984453147889, "qualityFactor": 1.2043023027333526,
"queueFactor": 0.9102060262555041, "queueFactor": 0.9164337916397762,
"queueWeight": 0.9102060262555041, "queueWeight": 0.9164337916397762,
"recentSuccess": 18, "recentSuccess": 18,
"recentSuccessRate": 0.35294117647058826, "recentSuccessRate": 0.33962264150943394,
"recentTerminal": 51, "recentTerminal": 53,
"recentWilsonLowerBound": 0.23634305381259785, "recentWilsonLowerBound": 0.22686862857429077,
"running": 17, "running": 16,
"selectionWeight": 1.1285139641720177, "selectionWeight": 1.10366332557444,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.5, "throughputPerHour": 8.833333333333334,
"waiting": 12470 "waiting": 12469
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 657.6880733944954, "backlogHours": 669.9252336448599,
"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": 0.5873979677977028, "qualityFactor": 0.6512275803257138,
"queueFactor": 1.0266061006548735, "queueFactor": 1.0248332207262554,
"queueWeight": 1.0266061006548735, "queueWeight": 1.0248332207262554,
"recentSuccess": 26, "recentSuccess": 26,
"recentSuccessRate": 0.23853211009174313, "recentSuccessRate": 0.24299065420560748,
"recentTerminal": 109, "recentTerminal": 107,
"recentWilsonLowerBound": 0.16829549205620983, "recentWilsonLowerBound": 0.17155744423820674,
"running": 6, "running": 6,
"selectionWeight": 0.6030263372533966, "selectionWeight": 0.6673996585709675,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.166666666666668, "throughputPerHour": 17.833333333333332,
"waiting": 11948 "waiting": 11947
} }
}, },
"queueAttemptedAt": "2026-09-14T13:45:17.065899+00:00", "queueAttemptedAt": "2026-09-14T13:56:30.149034+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-14T13:45:17.065899+00:00", "queueUpdatedAt": "2026-09-14T13:56:30.149034+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": "2026-09-14T13:39:17.251234+00:00", "generatedAt": "2026-09-14T13:56:20.950497+00:00",
"lastSyncTime": "2026-09-14T13:39:17.210528+00:00", "lastSyncTime": "2026-09-14T13:56:20.710643+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1987,30 +1987,30 @@
"unresolvedFailureCount": 7 "unresolvedFailureCount": 7
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 97, "attributableFailureCount": 98,
"decisionFailureRate": 0.8661, "decisionFailureRate": 0.8673,
"decisionSuccessRate": 0.1339, "decisionSuccessRate": 0.1327,
"decisionTotal": 112, "decisionTotal": 113,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 23, "ambiguous_runtime": 23,
"framework_architecture_unsupported": 53, "framework_architecture_unsupported": 54,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 43, "model_load": 43,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"参数/模板问题": 2, "参数/模板问题": 2,
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 170, "failureCount": 171,
"failureRate": 0.9189, "failureRate": 0.9194,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 15, "successCount": 15,
"successRate": 0.0811, "successRate": 0.0806,
"targetGpu": "Iluvatar_mrv-100", "targetGpu": "Iluvatar_mrv-100",
"taskType": "text-generation", "taskType": "text-generation",
"total": 185, "total": 186,
"unresolvedFailureCount": 72 "unresolvedFailureCount": 72
}, },
"Iluvatar_mrv-100|vllm|text-generation": { "Iluvatar_mrv-100|vllm|text-generation": {
@@ -2515,14 +2515,14 @@
"unresolvedFailureCount": 8 "unresolvedFailureCount": 8
}, },
"unknown": { "unknown": {
"attributableFailureCount": 160, "attributableFailureCount": 161,
"decisionFailureRate": 0.7442, "decisionFailureRate": 0.7454,
"decisionSuccessRate": 0.2558, "decisionSuccessRate": 0.2546,
"decisionTotal": 215, "decisionTotal": 216,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 149, "ambiguous_runtime": 149,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 103, "framework_architecture_unsupported": 104,
"memory_capacity": 5, "memory_capacity": 5,
"model_load": 45, "model_load": 45,
"platform_infrastructure": 1, "platform_infrastructure": 1,
@@ -2530,14 +2530,14 @@
"参数/模板问题": 61, "参数/模板问题": 61,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1044, "failureCount": 1045,
"failureRate": 0.95, "failureRate": 0.95,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 55, "successCount": 55,
"successRate": 0.05, "successRate": 0.05,
"total": 1099, "total": 1100,
"unresolvedFailureCount": 883 "unresolvedFailureCount": 883
}, },
"vllm": { "vllm": {
@@ -2672,7 +2672,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-14T13:39:17.246661+00:00", "generatedAt": "2026-09-14T13:56:20.945773+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 35, "attributableFailureCount": 35,
@@ -2836,27 +2836,27 @@
"unresolvedFailureCount": 46 "unresolvedFailureCount": 46
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"attributableFailureCount": 100, "attributableFailureCount": 101,
"decisionFailureRate": 0.8696, "decisionFailureRate": 0.8707,
"decisionSuccessRate": 0.1304, "decisionSuccessRate": 0.1293,
"decisionTotal": 115, "decisionTotal": 116,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 23, "ambiguous_runtime": 23,
"framework_architecture_unsupported": 55, "framework_architecture_unsupported": 56,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 44, "model_load": 44,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"参数/模板问题": 2, "参数/模板问题": 2,
"验证失败": 47 "验证失败": 47
}, },
"failureCount": 173, "failureCount": 174,
"failureRate": 0.9202, "failureRate": 0.9206,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 15, "successCount": 15,
"successRate": 0.0798, "successRate": 0.0794,
"total": 188, "total": 189,
"unresolvedFailureCount": 72 "unresolvedFailureCount": 72
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
@@ -5210,22 +5210,22 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Iluvatar_mrv-100|unknown|text-generation": { "Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 11, "attributableFailureCount": 12,
"consecutiveFailures": 5, "consecutiveFailures": 6,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.7333, "decisionFailureRate": 0.75,
"decisionSuccessRate": 0.2667, "decisionSuccessRate": 0.25,
"decisionTotal": 15, "decisionTotal": 16,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 5, "ambiguous_runtime": 4,
"framework_architecture_unsupported": 4, "framework_architecture_unsupported": 5,
"model_load": 7 "model_load": 7
}, },
"failureCount": 16, "failureCount": 16,
"failureRate": 0.8, "failureRate": 0.8,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-14T07:52:30.913060+00:00", "lastTerminalAt": "2026-09-14T13:56:20.710643+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -5234,7 +5234,7 @@
"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,
@@ -8354,17 +8354,17 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1839, "terminalRecords": 1840,
"totalRecords": 1932, "totalRecords": 1933,
"totals": { "totals": {
"attributableFailureCount": 553, "attributableFailureCount": 554,
"decisionFailureRate": 0.9007, "decisionFailureRate": 0.9008,
"decisionSuccessRate": 0.0993, "decisionSuccessRate": 0.0992,
"decisionTotal": 614, "decisionTotal": 615,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 437, "ambiguous_runtime": 437,
"backend_operator": 43, "backend_operator": 43,
"framework_architecture_unsupported": 352, "framework_architecture_unsupported": 353,
"memory_capacity": 12, "memory_capacity": 12,
"model_load": 77, "model_load": 77,
"platform_infrastructure": 6, "platform_infrastructure": 6,
@@ -8374,14 +8374,14 @@
"参数/模板问题": 109, "参数/模板问题": 109,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1778, "failureCount": 1779,
"failureRate": 0.9668, "failureRate": 0.9668,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 6, "platformFailureCount": 6,
"successCount": 61, "successCount": 61,
"successRate": 0.0332, "successRate": 0.0332,
"total": 1839, "total": 1840,
"unresolvedFailureCount": 1219 "unresolvedFailureCount": 1219
}, },
"warnings": [ "warnings": [
@@ -8420,6 +8420,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1932, "summarizedRecords": 1933,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,4 @@
{"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": ["rwkv7"], "framework": "", "lastSyncTime": "2026-09-14T13:56:20.710643+00:00", "modelId": "RWKV/RWKV7-13.3B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T13:51:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4584251", "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": "2026-09-14T12:43:55.116312+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T12:41:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4610343", "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": "2026-09-14T12:43:55.116312+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T12:41:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4610343", "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": "2026-09-14T12:43:55.116339+00:00", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T12:37:22+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4586733", "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": "2026-09-14T12:43:55.116339+00:00", "modelId": "cyankiwi/Ornith-1.5-35B-A3B-AWQ-INT4", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T12:37:22+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4586733", "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": "2026-09-14T12:26:52.201763+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T12:19:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4375377", "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": "2026-09-14T12:26:52.201763+00:00", "modelId": "siliconflow/gpt-oss-20b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T12:19:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4375377", "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": "2026-09-09T23:55:17.200912+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T23:51:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505073", "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": "2026-09-09T23:55:17.200912+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T23:51:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4505073", "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": "2026-09-09T23:14:19.142084+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T23:07:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481651", "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": "2026-09-09T23:14:19.142084+00:00", "modelId": "neuralmagic/starcoder2-15b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T23:07:21+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4481651", "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": "2026-09-09T22:57:38.803923+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:49:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471911", "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": "2026-09-09T22:57:38.803923+00:00", "modelId": "nm-testing/llama7b-one-shot-2_4-w4a16-marlin24-t-alt", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:49:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471911", "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": "2026-09-09T22:49:15.213951+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-09T22:47:23+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4471912", "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": "d38856aeb0c8e438c57da2df3ea384a01f03350015945c502e929c13d78f579d", ".modelhub_state/architecture_compatibility_blacklist.json": "412c75ee9b4674918166343a7762d05fc1efcc8ab27c84ec1d12687e12481d96",
".modelhub_state/architecture_history_backfill.json": "553c1ea38a34e23538593fddf0e37295391bbfeb1b6b8e92937cc3c25faeb808", ".modelhub_state/architecture_history_backfill.json": "e34d57b19963712bec1fd5451489a6d1480859a1c0ff0b4872cf1127b493348b",
".modelhub_state/market_intelligence.json": "0580c18958d98f6ceecba35d0d3cf6f8d97a8d4cb72d8366c77320a493e45f4f", ".modelhub_state/market_intelligence.json": "880d280fcb17807e6fbc72231e208dc2b6646a2ced6cc928e996321e5c4167d1",
".modelhub_state/official_capabilities.json": "9ac1a82985b2ef3ca46c50c250c11638335c1b81868835e9ae7c2a89b400b290", ".modelhub_state/official_capabilities.json": "2d8297c2a413a16a5492622d4a63d6296a631d5ee20aedd217246dc66884213d",
".modelhub_state/outcome_checkpoint.json": "5400831eb17708c18b4c1ea4977ee50ba893573990c2b74ef85dc40b2a1fe779", ".modelhub_state/outcome_checkpoint.json": "27724848fe2b3e67d9682f88f611a1cf6d46cda37234bd52d57ba6db9614d413",
".modelhub_state/queue_cleanup_latest.json": "e5d9b334b2784235be02767778d1d31aa5d889dbe0cdb9bf65bb77a097c78531", ".modelhub_state/queue_cleanup_latest.json": "e5d9b334b2784235be02767778d1d31aa5d889dbe0cdb9bf65bb77a097c78531",
".modelhub_state/recent_outcomes.jsonl": "f62e11c68c0ca50f8cfde5a7de13fe96489f8b54eeda09296048ebe1a3c99777", ".modelhub_state/recent_outcomes.jsonl": "7e4a2e3bad2ed6a552d6c73d380d69869839061f3ae01b22a0226c7b71c06187",
".modelhub_state/recovery_active_tasks.jsonl": "fbd5b29802164e6be702eb91b45e11159df97809a53e4a0d838680b9b62489f1", ".modelhub_state/recovery_active_tasks.jsonl": "be53991072a10c836ab3041b910c18c7494fe34d842b1c8e86c1145ba56542af",
".modelhub_state/recovery_intents.jsonl": "b673327ee3f908926b6bb1b2664ea4d530c96eca3898742aa0ef4af50b42d849", ".modelhub_state/recovery_intents.jsonl": "c65913a6b3b4e087aa8323cc647dfbd8ed6187c6e848a68cfd04564ce1a1df6e",
".modelhub_state/routing_intelligence.json": "8eb5d96052c3e5517c6ab8c0bc34461f31c6fdc56b67ee8697b74d0586de1e40", ".modelhub_state/routing_intelligence.json": "8eb5d96052c3e5517c6ab8c0bc34461f31c6fdc56b67ee8697b74d0586de1e40",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552", ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad", ".modelhub_state/worker_crashes.jsonl": "53505d335313446ff7094bcb58658b561de55799302fa7bfb49e418e414eebad",
"ledger/submissions.jsonl": "83ab45d57e7dca6a35c7d0505eafdd2503ce79e608ae693fe966b7812ea12df2", "ledger/submissions.jsonl": "83ab45d57e7dca6a35c7d0505eafdd2503ce79e608ae693fe966b7812ea12df2",
"outcomes/submissions.jsonl": "d0d6236f296f2e1980b869ded519eb08c413b3c7d23c2cc7d5594921570f68e3" "outcomes/submissions.jsonl": "d0d6236f296f2e1980b869ded519eb08c413b3c7d23c2cc7d5594921570f68e3"
}, },
"generation": 7206, "generation": 7207,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-14T13:55:19.987123+00:00", "updatedAt": "2026-09-14T13:58:11.248212+00:00",
"writerId": "69701e73196b4ac2b3fad0f412335168" "writerId": "69701e73196b4ac2b3fad0f412335168"
} }