state: generation 7446 (cycle)

This commit is contained in:
2026-09-15 00:23:55 +00:00
parent a803753d44
commit d414c168d4
9 changed files with 2209 additions and 2210 deletions

View File

@@ -1556,7 +1556,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-15T00:21:03.229587+00:00", "generatedAt": "2026-09-15T00:23:55.154195+00:00",
"summary": { "summary": {
"activeBlockCount": 77, "activeBlockCount": 77,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -11,7 +11,7 @@
"1": { "1": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 540, "listingErrors": 541,
"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": 1, "nextAccountIndex": 2,
"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": "2026-09-15T00:21:03.204956+00:00", "updatedAt": "2026-09-15T00:23:55.127937+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,99 +416,99 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T00:19:17.957483+00:00", "generatedAt": "2026-09-15T00:22:15.627320+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1129.344, "backlogHours": 1138.2096774193549,
"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": 0.9079771402764801, "qualityFactor": 0.8559518119273546,
"queueFactor": 0.9751164096327553, "queueFactor": 0.9767453882057644,
"queueWeight": 0.9751164096327553, "queueWeight": 0.9767453882057644,
"recentSuccess": 42, "recentSuccess": 40,
"recentSuccessRate": 0.336, "recentSuccessRate": 0.3225806451612903,
"recentTerminal": 125, "recentTerminal": 124,
"recentWilsonLowerBound": 0.25918260494074635, "recentWilsonLowerBound": 0.24670272784213756,
"running": 8, "running": 9,
"selectionWeight": 0.8853834090550179, "selectionWeight": 0.8360469848264114,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.833333333333332, "throughputPerHour": 20.666666666666668,
"waiting": 23528 "waiting": 23523
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1364.5853658536585, "backlogHours": 1375.5737704918033,
"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": 1.9864924857768966, "qualityFactor": 2.3297900451191214,
"queueFactor": 0.9478296624596503, "queueFactor": 0.9493844792509307,
"queueWeight": 0.9478296624596503, "queueWeight": 0.9493844792509307,
"recentSuccess": 56, "recentSuccess": 58,
"recentSuccessRate": 0.45528455284552843, "recentSuccessRate": 0.47540983606557374,
"recentTerminal": 123, "recentTerminal": 122,
"recentWilsonLowerBound": 0.3699616988205246, "recentWilsonLowerBound": 0.38890272235052964,
"running": 8, "running": 8,
"selectionWeight": 1.8828565022725476, "selectionWeight": 2.2118665087494196,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.5, "throughputPerHour": 20.333333333333332,
"waiting": 27974 "waiting": 27970
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 638.5, "backlogHours": 666.2608695652174,
"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": 0.0550354852829996, "qualityFactor": 0.06367272734847293,
"queueFactor": 1.0621999265815618, "queueFactor": 1.0584444361073848,
"queueWeight": 1.0621999265815618, "queueWeight": 1.0584444361073848,
"recentSuccess": 7, "recentSuccess": 7,
"recentSuccessRate": 0.14583333333333334, "recentSuccessRate": 0.15217391304347827,
"recentTerminal": 48, "recentTerminal": 46,
"recentWilsonLowerBound": 0.07248157413793963, "recentWilsonLowerBound": 0.07572186234017478,
"running": 2, "running": 2,
"selectionWeight": 0.0584586884269828, "selectionWeight": 0.06739404399377369,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.0, "throughputPerHour": 7.666666666666667,
"waiting": 5108 "waiting": 5108
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1133.4814814814815, "backlogHours": 1147.2749999999999,
"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": 0.4981424941821372, "qualityFactor": 0.5386431483736486,
"queueFactor": 0.9745816678766775, "queueFactor": 0.9755838019044596,
"queueWeight": 0.9745816678766775, "queueWeight": 0.9755838019044596,
"recentSuccess": 23, "recentSuccess": 23,
"recentSuccessRate": 0.2839506172839506, "recentSuccessRate": 0.2875,
"recentTerminal": 81, "recentTerminal": 80,
"recentWilsonLowerBound": 0.19728595019327252, "recentWilsonLowerBound": 0.19986786008396254,
"running": 7, "running": 7,
"selectionWeight": 0.4854805428202754, "selectionWeight": 0.525491530560152,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 13.5, "throughputPerHour": 13.333333333333334,
"waiting": 15302 "waiting": 15297
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 139.37055837563452, "backlogHours": 139.00253164556963,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x8", "gpu": "Cambricon_mlu-370-x8",
@@ -518,19 +518,19 @@
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 24, "recentSuccess": 24,
"recentSuccessRate": 0.06091370558375635, "recentSuccessRate": 0.060759493670886074,
"recentTerminal": 394, "recentTerminal": 395,
"recentWilsonLowerBound": 0.041271844300837045, "recentWilsonLowerBound": 0.04116648907862537,
"running": 7, "running": 7,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 65.66666666666667, "throughputPerHour": 65.83333333333333,
"waiting": 9152 "waiting": 9151
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 53.423841059602644, "backlogHours": 53.84,
"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": 7, "recentSuccess": 8,
"recentSuccessRate": 0.023178807947019868, "recentSuccessRate": 0.02666666666666667,
"recentTerminal": 302, "recentTerminal": 300,
"recentWilsonLowerBound": 0.011272069203454542, "recentWilsonLowerBound": 0.013572906766976815,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 50.333333333333336, "throughputPerHour": 50.0,
"waiting": 2689 "waiting": 2692
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 164.6625, "backlogHours": 160.7926829268293,
"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": 0.0943084786629145, "qualityFactor": 0.11831633964272184,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 22, "recentSuccess": 24,
"recentSuccessRate": 0.1375, "recentSuccessRate": 0.14634146341463414,
"recentTerminal": 160, "recentTerminal": 164,
"recentWilsonLowerBound": 0.09258687095890997, "recentWilsonLowerBound": 0.10035418805722283,
"running": 2, "running": 5,
"selectionWeight": 0.12260102226178886, "selectionWeight": 0.1538112415355384,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.666666666666668, "throughputPerHour": 27.333333333333332,
"waiting": 4391 "waiting": 4395
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2890.909090909091, "backlogHours": 2981.0625,
"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": 1.2381850166185084, "qualityFactor": 1.145594713096168,
"queueFactor": 0.8468865529158565, "queueFactor": 0.8453937800450837,
"queueWeight": 0.8468865529158565, "queueWeight": 0.8453937800450837,
"recentSuccess": 15, "recentSuccess": 14,
"recentSuccessRate": 0.45454545454545453, "recentSuccessRate": 0.4375,
"recentTerminal": 33, "recentTerminal": 32,
"recentWilsonLowerBound": 0.298426891258915, "recentWilsonLowerBound": 0.28165085969443177,
"running": 2, "running": 2,
"selectionWeight": 1.048602240596111, "selectionWeight": 0.9684786449040326,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 5.5, "throughputPerHour": 5.333333333333333,
"waiting": 15900 "waiting": 15899
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 567.8181818181818, "backlogHours": 602.6315789473684,
"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": 0.13674685852246898, "qualityFactor": 0.1643934892500295,
"queueFactor": 1.081058032658039, "queueFactor": 1.0745012561735712,
"queueWeight": 1.081058032658039, "queueWeight": 1.0745012561735712,
"recentSuccess": 20, "recentSuccess": 20,
"recentSuccessRate": 0.1652892561983471, "recentSuccessRate": 0.17543859649122806,
"recentTerminal": 121, "recentTerminal": 114,
"recentWilsonLowerBound": 0.10962203759241998, "recentWilsonLowerBound": 0.11653670199867362,
"running": 7, "running": 7,
"selectionWeight": 0.1478312898464675, "selectionWeight": 0.17664101070591318,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.166666666666668, "throughputPerHour": 19.0,
"waiting": 11451 "waiting": 11450
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 780.0666666666667, "backlogHours": 807.7241379310345,
"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": 0.6025394766487631, "qualityFactor": 0.7548720061427249,
"queueFactor": 1.030767327759664, "queueFactor": 1.02831282234366,
"queueWeight": 1.030767327759664, "queueWeight": 1.02831282234366,
"recentSuccess": 27, "recentSuccess": 28,
"recentSuccessRate": 0.3, "recentSuccessRate": 0.3218390804597701,
"recentTerminal": 90, "recentTerminal": 87,
"recentWilsonLowerBound": 0.21510778051256527, "recentWilsonLowerBound": 0.23300577279734025,
"running": 4, "running": 4,
"selectionWeight": 0.621078006214952, "selectionWeight": 0.776244563144846,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.0, "throughputPerHour": 14.5,
"waiting": 11701 "waiting": 11712
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2179.125, "backlogHours": 2286.4918032786886,
"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": 2.5,
"queueFactor": 0.8835641387477201, "queueFactor": 0.8797094617822865,
"queueWeight": 0.8835641387477201, "queueWeight": 0.8797094617822865,
"recentSuccess": 34, "recentSuccess": 32,
"recentSuccessRate": 0.53125, "recentSuccessRate": 0.5245901639344263,
"recentTerminal": 64, "recentTerminal": 61,
"recentWilsonLowerBound": 0.41071875000475133, "recentWilsonLowerBound": 0.4015694171531101,
"running": 4, "running": 4,
"selectionWeight": 2.2089103468693003, "selectionWeight": 2.199273654455716,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.666666666666666, "throughputPerHour": 10.166666666666666,
"waiting": 23244 "waiting": 23246
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 3232.285714285714, "backlogHours": 3232.5,
"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": 0.11700809680387113, "qualityFactor": 0.12295338618604668,
"queueFactor": 0.8328253593747341, "queueFactor": 0.8351873935080912,
"queueWeight": 0.8328253593747341, "queueWeight": 0.8351873935080912,
"recentSuccess": 6, "recentSuccess": 6,
"recentSuccessRate": 0.21428571428571427, "recentSuccessRate": 0.21428571428571427,
"recentTerminal": 28, "recentTerminal": 28,
"recentWilsonLowerBound": 0.10212321701189421, "recentWilsonLowerBound": 0.10212321701189421,
"running": 2, "running": 2,
"selectionWeight": 0.09744731027043765, "selectionWeight": 0.10268911813171808,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 4.666666666666667, "throughputPerHour": 4.666666666666667,
"waiting": 15084 "waiting": 15085
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1221.142857142857, "backlogHours": 1241.1290322580644,
"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": 0.05, "qualityFactor": 0.05,
"queueFactor": 0.9637523083814532, "queueFactor": 0.9641445933827136,
"queueWeight": 0.9637523083814532, "queueWeight": 0.9641445933827136,
"recentSuccess": 8, "recentSuccess": 7,
"recentSuccessRate": 0.12698412698412698, "recentSuccessRate": 0.11290322580645161,
"recentTerminal": 63, "recentTerminal": 62,
"recentWilsonLowerBound": 0.06577246340780173, "recentWilsonLowerBound": 0.05577792691334925,
"running": 16, "running": 16,
"selectionWeight": 0.04818761541907266, "selectionWeight": 0.04820722966913568,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.5, "throughputPerHour": 10.333333333333334,
"waiting": 12822 "waiting": 12825
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 641.6974789915967, "backlogHours": 652.9230769230769,
"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": 0.49873295773855, "qualityFactor": 0.5009832618949059,
"queueFactor": 1.061404323494213, "queueFactor": 1.0616598846221474,
"queueWeight": 1.061404323494213, "queueWeight": 1.0616598846221474,
"recentSuccess": 32, "recentSuccess": 31,
"recentSuccessRate": 0.2689075630252101, "recentSuccessRate": 0.26495726495726496,
"recentTerminal": 119, "recentTerminal": 117,
"recentWilsonLowerBound": 0.19739221088821968, "recentWilsonLowerBound": 0.19339035715571287,
"running": 6, "running": 6,
"selectionWeight": 0.5293573176127535, "selectionWeight": 0.5318738320209729,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 19.833333333333332, "throughputPerHour": 19.5,
"waiting": 12727 "waiting": 12732
} }
}, },
"queueAttemptedAt": "2026-09-15T00:09:46.508134+00:00", "queueAttemptedAt": "2026-09-15T00:22:15.627320+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-15T00:09:46.508134+00:00", "queueUpdatedAt": "2026-09-15T00:22:15.627320+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": "2026-09-15T00:03:42.478895+00:00", "generatedAt": "2026-09-15T00:22:04.571941+00:00",
"lastSyncTime": "2026-09-15T00:03:42.210393+00:00", "lastSyncTime": "2026-09-15T00:22:04.249561+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2512,14 +2512,14 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 50, "decisionTotal": 50,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 20, "ambiguous_runtime": 22,
"framework_architecture_unsupported": 38, "framework_architecture_unsupported": 38,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 5, "model_load": 5,
"repository_structure": 4, "repository_structure": 4,
"runtime_memory": 2 "runtime_memory": 2
}, },
"failureCount": 70, "failureCount": 72,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -2529,8 +2529,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 70, "total": 72,
"unresolvedFailureCount": 20 "unresolvedFailureCount": 22
} }
}, },
"frameworkSummaries": { "frameworkSummaries": {
@@ -2603,7 +2603,7 @@
"decisionSuccessRate": 0.0122, "decisionSuccessRate": 0.0122,
"decisionTotal": 329, "decisionTotal": 329,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 214, "ambiguous_runtime": 216,
"backend_operator": 34, "backend_operator": 34,
"framework_architecture_unsupported": 236, "framework_architecture_unsupported": 236,
"memory_capacity": 7, "memory_capacity": 7,
@@ -2614,15 +2614,15 @@
"tokenizer_compatibility": 7, "tokenizer_compatibility": 7,
"参数/模板问题": 30 "参数/模板问题": 30
}, },
"failureCount": 570, "failureCount": 572,
"failureRate": 0.993, "failureRate": 0.9931,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 4, "successCount": 4,
"successRate": 0.007, "successRate": 0.0069,
"total": 574, "total": 576,
"unresolvedFailureCount": 244 "unresolvedFailureCount": 246
}, },
"vllm-mlu": { "vllm-mlu": {
"attributableFailureCount": 8, "attributableFailureCount": 8,
@@ -2730,7 +2730,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-15T00:03:42.473117+00:00", "generatedAt": "2026-09-15T00:22:04.564736+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 38, "attributableFailureCount": 38,
@@ -3045,7 +3045,7 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 55, "decisionTotal": 55,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 22, "ambiguous_runtime": 24,
"framework_architecture_unsupported": 43, "framework_architecture_unsupported": 43,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 5, "model_load": 5,
@@ -3054,15 +3054,15 @@
"参数/模板问题": 9, "参数/模板问题": 9,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 113, "failureCount": 115,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 113, "total": 115,
"unresolvedFailureCount": 58 "unresolvedFailureCount": 60
} }
}, },
"observedGpuMemoryGiB": { "observedGpuMemoryGiB": {
@@ -5819,24 +5819,23 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"hygon_k100-ai|vllm|text-generation": { "hygon_k100-ai|vllm|text-generation": {
"attributableFailureCount": 15, "attributableFailureCount": 14,
"consecutiveFailures": 15, "consecutiveFailures": 14,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 15, "decisionTotal": 14,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 5, "ambiguous_runtime": 6,
"framework_architecture_unsupported": 11, "framework_architecture_unsupported": 11,
"model_load": 2, "model_load": 2,
"repository_structure": 1, "repository_structure": 1
"runtime_memory": 1
}, },
"failureCount": 20, "failureCount": 20,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-15T00:03:42.210358+00:00", "lastTerminalAt": "2026-09-15T00:22:04.249561+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -5845,7 +5844,7 @@
"targetGpu": "hygon_k100-ai", "targetGpu": "hygon_k100-ai",
"taskType": "text-generation", "taskType": "text-generation",
"total": 20, "total": 20,
"unresolvedFailureCount": 5 "unresolvedFailureCount": 6
} }
}, },
"recentProfileCombinationStats": {}, "recentProfileCombinationStats": {},
@@ -9011,15 +9010,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1878, "terminalRecords": 1880,
"totalRecords": 1971, "totalRecords": 1973,
"totals": { "totals": {
"attributableFailureCount": 570, "attributableFailureCount": 570,
"decisionFailureRate": 0.9005, "decisionFailureRate": 0.9005,
"decisionSuccessRate": 0.0995, "decisionSuccessRate": 0.0995,
"decisionTotal": 633, "decisionTotal": 633,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 450, "ambiguous_runtime": 452,
"backend_operator": 44, "backend_operator": 44,
"framework_architecture_unsupported": 365, "framework_architecture_unsupported": 365,
"memory_capacity": 12, "memory_capacity": 12,
@@ -9031,15 +9030,15 @@
"参数/模板问题": 116, "参数/模板问题": 116,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1815, "failureCount": 1817,
"failureRate": 0.9665, "failureRate": 0.9665,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 6, "platformFailureCount": 6,
"successCount": 63, "successCount": 63,
"successRate": 0.0335, "successRate": 0.0335,
"total": 1878, "total": 1880,
"unresolvedFailureCount": 1239 "unresolvedFailureCount": 1241
}, },
"warnings": [ "warnings": [
"GPU Iluvatar_mrv-100 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。",
@@ -9077,6 +9076,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1971, "summarizedRecords": 1973,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,5 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-15T00:22:04.249561+00:00", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:19:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592892", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "unknown", "failureCode": "UNKNOWN", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-15T00:22:04.249539+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:17:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4595877", "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": "2026-09-15T00:03:42.210358+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:03:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592744", "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": "2026-09-15T00:03:42.210358+00:00", "modelId": "cyankiwi/Ornith-1.5-9B-AWQ-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T00:03:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4592744", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-15T00:03:42.210382+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T23:57:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4591876", "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": ["rwkv7"], "framework": "vllm", "lastSyncTime": "2026-09-15T00:03:42.210382+00:00", "modelId": "RWKV/RWKV7-7.2B-20260805", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T23:57:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4591876", "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": "2026-09-15T00:03:42.210393+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T23:55:23+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4592637", "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": "2026-09-15T00:03:42.210393+00:00", "modelId": "EschaLabs/Qwen3.8-27B-Escha-W2", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-14T23:55:23+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4592637", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943952+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-10T02:37:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483083", "taskType": "text-generation", "verifyResult": 1} {"failReason": null, "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943952+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-10T02:37:23+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483083", "taskType": "text-generation", "verifyResult": 1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943965+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483082", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943965+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:37:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4483082", "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": "2026-09-10T02:40:44.943974+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:35:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496938", "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": "2026-09-10T02:40:44.943974+00:00", "modelId": "neuralmagic/starcoder2-15b-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:35:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496938", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "", "lastSyncTime": "2026-09-10T02:40:44.943909+00:00", "modelId": "neuralmagic/starcoder2-3b-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:33:21+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4505137", "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": "2026-09-10T02:32:07.501704+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T02:29:21+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4496940", "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": "2d3e1f15b7e5283c20ab56533e6752723d2c0aeecf2d9f1d09b8880bf9334326", ".modelhub_state/architecture_compatibility_blacklist.json": "9b96804855714a13b6ff98d3ed0cf9edec319b2aeb25782dff68ce05db2db7fd",
".modelhub_state/architecture_history_backfill.json": "2b0ed9cbd5bd24c4f85ee1726886b5c80b9a8ad4dcc41a348cc0938263399e9a", ".modelhub_state/architecture_history_backfill.json": "b670ca06e99f8a76cef96268da20c4814eb4552b80aede7ae0e4835658ed9d90",
".modelhub_state/market_intelligence.json": "6a285bd69b1be437bf67b5e5bf87c5099809660d5dabb213398378ffcafe268a", ".modelhub_state/market_intelligence.json": "2f1d8126183d4efffba01611974714e652ef447766a0c9eb66c2a81f0524e0f9",
".modelhub_state/official_capabilities.json": "82371959fc3630686794657826774bb8b5198a93a43871fb97249027640c605a", ".modelhub_state/official_capabilities.json": "830e4316910e9d514ecea3ee2e7de8623e87a3aae9e941e38bebbd55fa2f865b",
".modelhub_state/outcome_checkpoint.json": "e11b836734dac41ef33b71694a61cccdb6f23c566c7ce0c0a3ddcec657736aff", ".modelhub_state/outcome_checkpoint.json": "7f6774b01534b40e8a3bcc1c37bff301522dddd9f6541a56749fc27fcbcc6faf",
".modelhub_state/queue_cleanup_latest.json": "31192efe87aeb0abfa466af5f4610a5ee2c42cd23042e3754ec5250cd5b2517d", ".modelhub_state/queue_cleanup_latest.json": "31192efe87aeb0abfa466af5f4610a5ee2c42cd23042e3754ec5250cd5b2517d",
".modelhub_state/recent_outcomes.jsonl": "f347d5809888e29e53cc04585d4fa7d58c061b57eab554b18e03c904f2671eb8", ".modelhub_state/recent_outcomes.jsonl": "76ce990037b9e3cd014c21d801612325dc0ded295b8e0f04fc41eba5d5b6f814",
".modelhub_state/recovery_active_tasks.jsonl": "6d85fb193d8ace96576c8ddfcacbb3229799fdb8c0f80dc1431973d13cd3f44a", ".modelhub_state/recovery_active_tasks.jsonl": "0a25a98019efc7918013615eab12b014c3dcd9687eb4c07d7d2d824c3e4454c2",
".modelhub_state/recovery_intents.jsonl": "27d58c8655d994efbe9e0729207ebbb0dd050ee38b1548b59f8fab0af123e682", ".modelhub_state/recovery_intents.jsonl": "eae622f71d495a54a42bc7a7dffc0fec66cca7ae8eeeda5b27876584ceefe842",
".modelhub_state/routing_intelligence.json": "5f7939a4bcc0cd3361fb3c8b9e46d01882b7482b42018a697367e830f28b1f09", ".modelhub_state/routing_intelligence.json": "5f7939a4bcc0cd3361fb3c8b9e46d01882b7482b42018a697367e830f28b1f09",
".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": "b8563512d893ae2a4f8a4d65881d0eab34d0b8d937550ac1fd54cdbaddb9db2b", "ledger/submissions.jsonl": "b8563512d893ae2a4f8a4d65881d0eab34d0b8d937550ac1fd54cdbaddb9db2b",
"outcomes/submissions.jsonl": "8fb1bca3e421116716deccb3142261e8474705ab5a5757dca848881a4970c52a" "outcomes/submissions.jsonl": "8fb1bca3e421116716deccb3142261e8474705ab5a5757dca848881a4970c52a"
}, },
"generation": 7445, "generation": 7446,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-15T00:21:03.365385+00:00", "updatedAt": "2026-09-15T00:23:55.904203+00:00",
"writerId": "69701e73196b4ac2b3fad0f412335168" "writerId": "69701e73196b4ac2b3fad0f412335168"
} }