state: generation 8424 (cycle)

This commit is contained in:
2026-09-16 22:45:57 +00:00
parent 02cf1c6afe
commit 4e711d4c12
9 changed files with 2086 additions and 2089 deletions

View File

@@ -1714,7 +1714,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-16T22:42:35.550249+00:00", "generatedAt": "2026-09-16T22:45:56.558870+00:00",
"summary": { "summary": {
"activeBlockCount": 83, "activeBlockCount": 83,
"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": 615, "listingErrors": 616,
"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": "2026-09-16T22:42:35.526537+00:00", "updatedAt": "2026-09-16T22:45:56.534100+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,55 +416,55 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-16T22:40:49.189945+00:00", "generatedAt": "2026-09-16T22:43:45.194754+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1018.3404255319149, "backlogHours": 997.0,
"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": 1.8925214744379781, "qualityFactor": 1.9397868940261964,
"queueFactor": 0.9973297397447004, "queueFactor": 1.0016389760322806,
"queueWeight": 0.9973297397447004, "queueWeight": 1.0016389760322806,
"recentSuccess": 47, "recentSuccess": 48,
"recentSuccessRate": 0.3333333333333333, "recentSuccessRate": 0.3333333333333333,
"recentTerminal": 141, "recentTerminal": 144,
"recentWilsonLowerBound": 0.2608545832736055, "recentWilsonLowerBound": 0.26155165289307214,
"running": 8, "running": 8,
"selectionWeight": 1.8874679495624853, "selectionWeight": 1.9429661582532374,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.5, "throughputPerHour": 24.0,
"waiting": 23931 "waiting": 23928
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1391.016393442623, "backlogHours": 1414.2,
"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": 0.9517499880950643, "queueFactor": 0.9504709864771154,
"queueWeight": 0.9517499880950643, "queueWeight": 0.9504709864771154,
"recentSuccess": 46, "recentSuccess": 45,
"recentSuccessRate": 0.3770491803278688, "recentSuccessRate": 0.375,
"recentTerminal": 122, "recentTerminal": 120,
"recentWilsonLowerBound": 0.296041536912028, "recentWilsonLowerBound": 0.2935229130478532,
"running": 8, "running": 8,
"selectionWeight": 2.3793749702376608, "selectionWeight": 2.3761774661927886,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.333333333333332, "throughputPerHour": 20.0,
"waiting": 28284 "waiting": 28284
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 129.24513618677042, "backlogHours": 125.3433962264151,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
@@ -473,64 +473,64 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 17, "recentSuccess": 18,
"recentSuccessRate": 0.06614785992217899, "recentSuccessRate": 0.06792452830188679,
"recentTerminal": 257, "recentTerminal": 265,
"recentWilsonLowerBound": 0.04170582799576833, "recentWilsonLowerBound": 0.04339366080690426,
"running": 7, "running": 7,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 42.833333333333336, "throughputPerHour": 44.166666666666664,
"waiting": 5536 "waiting": 5536
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1416.8307692307692, "backlogHours": 1438.96875,
"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": 0.8669898342374942, "qualityFactor": 0.9156047572190368,
"queueFactor": 0.9491285129617714, "queueFactor": 0.9479987942120239,
"queueWeight": 0.9491285129617714, "queueWeight": 0.9479987942120239,
"recentSuccess": 18, "recentSuccess": 18,
"recentSuccessRate": 0.27692307692307694, "recentSuccessRate": 0.28125,
"recentTerminal": 65, "recentTerminal": 64,
"recentWilsonLowerBound": 0.18293439815390553, "recentWilsonLowerBound": 0.18593226105484584,
"running": 7, "running": 7,
"selectionWeight": 0.8228847721228055, "selectionWeight": 0.8679922058184398,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.833333333333334, "throughputPerHour": 10.666666666666666,
"waiting": 15349 "waiting": 15349
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 448.83720930232556, "backlogHours": 452.34375,
"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": 0.2432543118189551, "qualityFactor": 0.21945379455748992,
"queueFactor": 1.127741050401604, "queueFactor": 1.1277042059553204,
"queueWeight": 1.127741050401604, "queueWeight": 1.1277042059553204,
"recentSuccess": 20, "recentSuccess": 19,
"recentSuccessRate": 0.15503875968992248, "recentSuccessRate": 0.1484375,
"recentTerminal": 129, "recentTerminal": 128,
"recentWilsonLowerBound": 0.10266146097337198, "recentWilsonLowerBound": 0.09713386823483508,
"running": 7, "running": 7,
"selectionWeight": 0.2743278731254278, "selectionWeight": 0.24747896713533618,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 21.5, "throughputPerHour": 21.333333333333332,
"waiting": 9650 "waiting": 9650
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 41.536, "backlogHours": 40.59574468085106,
"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": 12, "recentSuccess": 13,
"recentSuccessRate": 0.032, "recentSuccessRate": 0.034574468085106384,
"recentTerminal": 375, "recentTerminal": 376,
"recentWilsonLowerBound": 0.018398213936240047, "recentWilsonLowerBound": 0.020314744255732004,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 62.5, "throughputPerHour": 62.666666666666664,
"waiting": 2596 "waiting": 2544
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 116.18181818181819, "backlogHours": 125.29411764705883,
"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": 0.39864909911733815, "qualityFactor": 0.2837432744544756,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 38, "recentSuccess": 31,
"recentSuccessRate": 0.17272727272727273, "recentSuccessRate": 0.15196078431372548,
"recentTerminal": 220, "recentTerminal": 204,
"recentWilsonLowerBound": 0.12850534319158355, "recentWilsonLowerBound": 0.10916665273100525,
"running": 2, "running": 1,
"selectionWeight": 0.5182438288525396, "selectionWeight": 0.3688662567908183,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 36.666666666666664, "throughputPerHour": 34.0,
"waiting": 4260 "waiting": 4260
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2600.5945945945946, "backlogHours": 2600.4324324324325,
"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": 1.2784428972526407, "qualityFactor": 1.614835737285106,
"queueFactor": 0.8664865363993688, "queueFactor": 0.8674783669713882,
"queueWeight": 0.8664865363993688, "queueWeight": 0.8674783669713882,
"recentSuccess": 13, "recentSuccess": 14,
"recentSuccessRate": 0.35135135135135137, "recentSuccessRate": 0.3783783783783784,
"recentTerminal": 37, "recentTerminal": 37,
"recentWilsonLowerBound": 0.21825406631100872, "recentWilsonLowerBound": 0.2406378746389103,
"running": 2, "running": 2,
"selectionWeight": 1.1077535580248148, "selectionWeight": 1.4008350683071216,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.166666666666667, "throughputPerHour": 6.166666666666667,
"waiting": 16037 "waiting": 16036
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 550.5483870967741, "backlogHours": 559.5245901639345,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.5382654222366332, "qualityFactor": 0.5690941536915818,
"queueFactor": 1.0937130475423256, "queueFactor": 1.0923017077561994,
"queueWeight": 1.0937130475423256, "queueWeight": 1.0923017077561994,
"recentSuccess": 26, "recentSuccess": 26,
"recentSuccessRate": 0.20967741935483872, "recentSuccessRate": 0.21311475409836064,
"recentTerminal": 124, "recentTerminal": 122,
"recentWilsonLowerBound": 0.1472978818443016, "recentWilsonLowerBound": 0.14978911098268174,
"running": 8, "running": 8,
"selectionWeight": 0.5887079153410848, "selectionWeight": 0.6216225159513837,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.666666666666668, "throughputPerHour": 20.333333333333332,
"waiting": 11378 "waiting": 11377
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 877.05, "backlogHours": 866.2222222222222,
"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": 1.4684142780524725, "qualityFactor": 1.609648405361403,
"queueFactor": 1.0199269426329827, "queueFactor": 1.0229892998932673,
"queueWeight": 1.0199269426329827, "queueWeight": 1.0229892998932673,
"recentSuccess": 26, "recentSuccess": 27,
"recentSuccessRate": 0.325, "recentSuccessRate": 0.3333333333333333,
"recentTerminal": 80, "recentTerminal": 81,
"recentWilsonLowerBound": 0.23244012494227473, "recentWilsonLowerBound": 0.24028620252704977,
"running": 4, "running": 4,
"selectionWeight": 1.4976752851326767, "selectionWeight": 1.6466530952749758,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 13.333333333333334, "throughputPerHour": 13.5,
"waiting": 11694 "waiting": 11694
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1939.342105263158, "backlogHours": 1865.3924050632913,
"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": 1.6540135903396471, "qualityFactor": 1.881545192679758,
"queueFactor": 0.9054710162979266, "queueFactor": 0.9118007785435498,
"queueWeight": 0.9054710162979266, "queueWeight": 0.9118007785435498,
"recentSuccess": 26, "recentSuccess": 28,
"recentSuccessRate": 0.34210526315789475, "recentSuccessRate": 0.35443037974683544,
"recentTerminal": 76, "recentTerminal": 79,
"recentWilsonLowerBound": 0.2453616992261352, "recentWilsonLowerBound": 0.2579524012236301,
"running": 4, "running": 4,
"selectionWeight": 1.4976613666154226, "selectionWeight": 1.7155943715502766,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.666666666666666, "throughputPerHour": 13.166666666666666,
"waiting": 24565 "waiting": 24561
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 2387.3846153846152, "backlogHours": 2387.6923076923076,
"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": 0.6949192508581546, "qualityFactor": 0.7081051511118663,
"queueFactor": 0.8776762746467824, "queueFactor": 0.878655709211265,
"queueWeight": 0.8776762746467824, "queueWeight": 0.878655709211265,
"recentSuccess": 11, "recentSuccess": 11,
"recentSuccessRate": 0.28205128205128205, "recentSuccessRate": 0.28205128205128205,
"recentTerminal": 39, "recentTerminal": 39,
"recentWilsonLowerBound": 0.16543325013943294, "recentWilsonLowerBound": 0.16543325013943294,
"running": 2, "running": 2,
"selectionWeight": 0.609914139273518, "selectionWeight": 0.6221806337463469,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.5, "throughputPerHour": 6.5,
"waiting": 15518 "waiting": 15520
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 2283.081081081081, "backlogHours": 2223.0,
"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": 0.20414008207075734, "qualityFactor": 0.19575209813047234,
"queueFactor": 0.8835772331323674, "queueFactor": 0.888125970638775,
"queueWeight": 0.8835772331323674, "queueWeight": 0.888125970638775,
"recentSuccess": 7, "recentSuccess": 7,
"recentSuccessRate": 0.1891891891891892, "recentSuccessRate": 0.18421052631578946,
"recentTerminal": 37, "recentTerminal": 38,
"recentWilsonLowerBound": 0.09479858757337126, "recentWilsonLowerBound": 0.0922164845325749,
"running": 16, "running": 16,
"selectionWeight": 0.18037352888749417, "selectionWeight": 0.17385252215670247,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.166666666666667, "throughputPerHour": 6.333333333333333,
"waiting": 14079 "waiting": 14079
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 982.3571428571429, "backlogHours": 1018.8888888888889,
"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": 1.1799870994591934, "qualityFactor": 1.170822204608418,
"queueFactor": 1.0027260696185933, "queueFactor": 0.9983813630919961,
"queueWeight": 1.0027260696185933, "queueWeight": 0.9983813630919961,
"recentSuccess": 25, "recentSuccess": 24,
"recentSuccessRate": 0.2976190476190476, "recentSuccessRate": 0.2962962962962963,
"recentTerminal": 84, "recentTerminal": 81,
"recentWilsonLowerBound": 0.2104467918626258, "recentWilsonLowerBound": 0.207918166563683,
"running": 6, "running": 6,
"selectionWeight": 1.1832038264413611, "selectionWeight": 1.1689270685753284,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.0, "throughputPerHour": 13.5,
"waiting": 13753 "waiting": 13755
} }
}, },
"queueAttemptedAt": "2026-09-16T22:32:45.469024+00:00", "queueAttemptedAt": "2026-09-16T22:43:45.194754+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-16T22:32:45.469024+00:00", "queueUpdatedAt": "2026-09-16T22:43:45.194754+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Kunlunxin_p-800", "Kunlunxin_p-800",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-16T22:18:06.003398+00:00", "generatedAt": "2026-09-16T22:43:36.393977+00:00",
"lastSyncTime": "2026-09-16T22:18:05.914670+00:00", "lastSyncTime": "2026-09-16T22:43:36.337604+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2583,22 +2583,22 @@
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0, "decisionSuccessRate": 1.0,
"decisionTotal": 16, "decisionTotal": 17,
"failureBreakdown": { "failureBreakdown": {
"参数/模板问题": 15, "参数/模板问题": 15,
"验证失败": 130 "验证失败": 130
}, },
"failureCount": 145, "failureCount": 145,
"failureRate": 0.9006, "failureRate": 0.8951,
"framework": "unknown", "framework": "unknown",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 16, "successCount": 17,
"successRate": 0.0994, "successRate": 0.1049,
"targetGpu": "Vastai_va16", "targetGpu": "Vastai_va16",
"taskType": "text-generation", "taskType": "text-generation",
"total": 161, "total": 162,
"unresolvedFailureCount": 145 "unresolvedFailureCount": 145
}, },
"Vastai_va16|vllm_fix_tokenizer|text-generation": { "Vastai_va16|vllm_fix_tokenizer|text-generation": {
@@ -2782,9 +2782,9 @@
}, },
"unknown": { "unknown": {
"attributableFailureCount": 185, "attributableFailureCount": 185,
"decisionFailureRate": 0.74, "decisionFailureRate": 0.7371,
"decisionSuccessRate": 0.26, "decisionSuccessRate": 0.2629,
"decisionTotal": 250, "decisionTotal": 251,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 157, "ambiguous_runtime": 157,
"backend_operator": 4, "backend_operator": 4,
@@ -2798,13 +2798,13 @@
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1089, "failureCount": 1089,
"failureRate": 0.9437, "failureRate": 0.9429,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 65, "successCount": 66,
"successRate": 0.0563, "successRate": 0.0571,
"total": 1154, "total": 1155,
"unresolvedFailureCount": 903 "unresolvedFailureCount": 903
}, },
"vllm": { "vllm": {
@@ -2943,7 +2943,7 @@
"unresolvedFailureCount": 6 "unresolvedFailureCount": 6
} }
}, },
"generatedAt": "2026-09-16T22:18:05.998104+00:00", "generatedAt": "2026-09-16T22:43:36.385059+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 51, "attributableFailureCount": 51,
@@ -3234,9 +3234,9 @@
}, },
"Vastai_va16": { "Vastai_va16": {
"attributableFailureCount": 60, "attributableFailureCount": 60,
"decisionFailureRate": 0.7895, "decisionFailureRate": 0.7792,
"decisionSuccessRate": 0.2105, "decisionSuccessRate": 0.2208,
"decisionTotal": 76, "decisionTotal": 77,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 68, "ambiguous_runtime": 68,
"framework_architecture_unsupported": 53, "framework_architecture_unsupported": 53,
@@ -3246,13 +3246,13 @@
"验证失败": 130 "验证失败": 130
}, },
"failureCount": 273, "failureCount": 273,
"failureRate": 0.9446, "failureRate": 0.9414,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 16, "successCount": 17,
"successRate": 0.0554, "successRate": 0.0586,
"total": 289, "total": 290,
"unresolvedFailureCount": 213 "unresolvedFailureCount": 213
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
@@ -6737,11 +6737,11 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 8, "decisionTotal": 8,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 11, "ambiguous_runtime": 10,
"framework_architecture_unsupported": 7, "framework_architecture_unsupported": 7,
"tokenizer_compatibility": 1 "tokenizer_compatibility": 1
}, },
"failureCount": 19, "failureCount": 18,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -6753,8 +6753,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Mthreads_s4000", "targetGpu": "Mthreads_s4000",
"taskType": "text-generation", "taskType": "text-generation",
"total": 19, "total": 18,
"unresolvedFailureCount": 11 "unresolvedFailureCount": 10
}, },
"Sunrise_pt-200-x1|unknown|text-generation": { "Sunrise_pt-200-x1|unknown|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -6844,23 +6844,23 @@
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
"decisionSuccessRate": 1.0, "decisionSuccessRate": 1.0,
"decisionTotal": 3, "decisionTotal": 4,
"failureBreakdown": { "failureBreakdown": {
"参数/模板问题": 2 "参数/模板问题": 2
}, },
"failureCount": 2, "failureCount": 2,
"failureRate": 0.4, "failureRate": 0.3333,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-16T22:18:05.914670+00:00", "lastTerminalAt": "2026-09-16T22:43:36.337604+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 3, "successCount": 4,
"successRate": 0.6, "successRate": 0.6667,
"targetGpu": "Vastai_va16", "targetGpu": "Vastai_va16",
"taskType": "text-generation", "taskType": "text-generation",
"total": 5, "total": 6,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 2
}, },
"Vastai_va16|vllm|text-generation": { "Vastai_va16|vllm|text-generation": {
@@ -11423,13 +11423,13 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 2060, "terminalRecords": 2061,
"totalRecords": 2163, "totalRecords": 2164,
"totals": { "totals": {
"attributableFailureCount": 669, "attributableFailureCount": 669,
"decisionFailureRate": 0.8884, "decisionFailureRate": 0.8873,
"decisionSuccessRate": 0.1116, "decisionSuccessRate": 0.1127,
"decisionTotal": 753, "decisionTotal": 754,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 500, "ambiguous_runtime": 500,
"backend_operator": 45, "backend_operator": 45,
@@ -11444,13 +11444,13 @@
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1976, "failureCount": 1976,
"failureRate": 0.9592, "failureRate": 0.9588,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 10, "platformFailureCount": 10,
"successCount": 84, "successCount": 85,
"successRate": 0.0408, "successRate": 0.0412,
"total": 2060, "total": 2061,
"unresolvedFailureCount": 1297 "unresolvedFailureCount": 1297
}, },
"warnings": [ "warnings": [
@@ -11458,14 +11458,14 @@
"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。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。", "GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。", "GPU Vastai_va16 本地统计失败率偏高≥50%),建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Biren_166m|unknown|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Biren_166m|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -11490,6 +11490,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 2163, "summarizedRecords": 2164,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,4 @@
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-16T22:43:36.337604+00:00", "modelId": "BAAI/Automobile-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-16T22:43:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4471936", "taskType": "text-generation", "verifyResult": 1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-16T22:18:05.914670+00:00", "modelId": "BAAI/CareBot_Medical_multi-llama3-8b-rl", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-16T22:17:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471939", "taskType": "text-generation", "verifyResult": 1} {"failReason": null, "framework": "", "lastSyncTime": "2026-09-16T22:18:05.914670+00:00", "modelId": "BAAI/CareBot_Medical_multi-llama3-8b-rl", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-16T22:17:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471939", "taskType": "text-generation", "verifyResult": 1}
{"failReason": null, "framework": "", "lastSyncTime": "2026-09-16T21:51:28.830496+00:00", "modelId": "BAAI/Hospitality-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-16T21:43:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4471934", "taskType": "text-generation", "verifyResult": 1} {"failReason": null, "framework": "", "lastSyncTime": "2026-09-16T21:51:28.830496+00:00", "modelId": "BAAI/Hospitality-llama3_1_8B_instruct", "modelProfile": {}, "outcome": "success", "status": "success", "submitTime": "2026-09-16T21:43:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4471934", "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": "2026-09-16T20:58:05.809820+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-16T20:53:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4583446", "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": "2026-09-16T20:58:05.809820+00:00", "modelId": "r0b0tlab/Qwen3.8-27B-NVFP4-MTP-sm121", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-16T20:53:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4583446", "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", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T18:58:50.012601+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:57:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532024", "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": "2026-09-10T18:58:50.012601+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:57:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532024", "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": "2026-09-10T18:58:50.012543+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:53:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4573325", "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": "2026-09-10T18:58:50.012543+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w8a16", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:53:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4573325", "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": "2026-09-10T18:58:50.012571+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:49:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493679", "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": "2026-09-10T18:58:50.012571+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:49:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4493679", "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": "2026-09-10T18:58:50.012583+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T18:49:21+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4532127", "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": "08a35d87e0ad8d7515b3f8d1d440658ef8436c9f558e5b1de115866c120b63f6", ".modelhub_state/architecture_compatibility_blacklist.json": "17625a042f72474564dae2ff7e35bc0778209ac54cfb5d916a3d1bac8eb077eb",
".modelhub_state/architecture_history_backfill.json": "3781c3732916b1623a6074b5eaad19239e4d959c6a6a7510eafd2d74323dc6f2", ".modelhub_state/architecture_history_backfill.json": "6ba23fac8c75f001ba024882dc7ccfce70eeb01c2bfc66479476cae0921cbde4",
".modelhub_state/market_intelligence.json": "d29a2f7f7fd4d5c2154cbbce3bfaed9032e8f45f1961fdc1a0e003d066924ef6", ".modelhub_state/market_intelligence.json": "2176ccc475f83ca88a67090dd1f5e0b3341631e491d43b27ca061fb4fe5aaa4d",
".modelhub_state/official_capabilities.json": "4a61c7b0e61cb55a15aa53ad23cb594909bd55a6c5b4c5b2891c2459a771582b", ".modelhub_state/official_capabilities.json": "d1892ee7d1b6f2115e666fa059d2b5c15cfc6c0449c29ebe3b27a6c2a06caa7c",
".modelhub_state/outcome_checkpoint.json": "b5cd416f635801cbd850c22a222de3255f27ac9b2587a685a43cf72ff479f7fa", ".modelhub_state/outcome_checkpoint.json": "cbdcbf9cda65e6b45ea9988e718df9627cb1dcf6db8a0959ae45c71585784ec2",
".modelhub_state/queue_cleanup_latest.json": "4b07ec677c9f7a1cef8978746f6e057a9979372430d32644646c3bd44e0a0546", ".modelhub_state/queue_cleanup_latest.json": "4b07ec677c9f7a1cef8978746f6e057a9979372430d32644646c3bd44e0a0546",
".modelhub_state/recent_outcomes.jsonl": "0720df84fa470376da438fe85229f6cda5ee033f2f64b1db12e2b7e5a93403df", ".modelhub_state/recent_outcomes.jsonl": "9c63c9e91a7286a339616cbabc063c26e3e231af972f7bb6a51a487a243e0757",
".modelhub_state/recovery_active_tasks.jsonl": "29a56f674904d9b0401fcd549c8b2169a271e2547690794cfefb6faa3e495f03", ".modelhub_state/recovery_active_tasks.jsonl": "dffa68600877ed5d2ee161d646ae7af3a19298955a96b79536256107a6fb1bdf",
".modelhub_state/recovery_intents.jsonl": "702781432887bd958398b477ecdecb9894d3132a7ba617bc0858db2b5202cd06", ".modelhub_state/recovery_intents.jsonl": "b3add8d105cc9f161ad931f50ca2a02e7e5ac7c2496e24dd58aa662eebdd0b3d",
".modelhub_state/routing_intelligence.json": "008e6b54a9b7e1bc15577d1efc269953cea31d9de94d820a59dc3a61a5e8019c", ".modelhub_state/routing_intelligence.json": "008e6b54a9b7e1bc15577d1efc269953cea31d9de94d820a59dc3a61a5e8019c",
".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": "812c72206635861ee11ade10194279e7d92bfd742b429b84fc1581281ed2535e", "ledger/submissions.jsonl": "812c72206635861ee11ade10194279e7d92bfd742b429b84fc1581281ed2535e",
"outcomes/submissions.jsonl": "9c5dcd4ffb1e833c7c3297ed6ef3213f76d1ea8482b738ac2eb86e3ae8868957" "outcomes/submissions.jsonl": "9c5dcd4ffb1e833c7c3297ed6ef3213f76d1ea8482b738ac2eb86e3ae8868957"
}, },
"generation": 8423, "generation": 8424,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-16T22:42:35.630887+00:00", "updatedAt": "2026-09-16T22:45:57.182756+00:00",
"writerId": "eccb3e0018f640d19e578c271a207b5c" "writerId": "eccb3e0018f640d19e578c271a207b5c"
} }