state: generation 7603 (cycle)

This commit is contained in:
2026-09-15 08:37:02 +00:00
parent a6e6d20e0e
commit 3803ee10af
9 changed files with 2215 additions and 2215 deletions

View File

@@ -1589,7 +1589,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-15T08:33:59.298479+00:00", "generatedAt": "2026-09-15T08:37:01.637007+00:00",
"summary": { "summary": {
"activeBlockCount": 78, "activeBlockCount": 78,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": { "5": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 552, "listingErrors": 553,
"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": 5, "nextAccountIndex": 6,
"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": "2026-09-15T08:33:59.272751+00:00", "updatedAt": "2026-09-15T08:37:01.609629+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,121 +416,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T08:31:41.122445+00:00", "generatedAt": "2026-09-15T08:35:09.286296+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 984.25, "backlogHours": 977.1724137931034,
"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": 1.301395872158169, "qualityFactor": 1.271603841406794,
"queueFactor": 0.9820456287163918, "queueFactor": 0.9816298751650823,
"queueWeight": 0.9820456287163918, "queueWeight": 0.9816298751650823,
"recentSuccess": 47, "recentSuccess": 48,
"recentSuccessRate": 0.3263888888888889, "recentSuccessRate": 0.3310344827586207,
"recentTerminal": 144, "recentTerminal": 145,
"recentWilsonLowerBound": 0.2551815623223416, "recentWilsonLowerBound": 0.25966796165988626,
"running": 8, "running": 9,
"selectionWeight": 1.2780301274824861, "selectionWeight": 1.2482443200995903,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.0, "throughputPerHour": 24.166666666666668,
"waiting": 23622 "waiting": 23615
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1262.390977443609, "backlogHours": 1234.3235294117646,
"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": 1.7401549884929826, "qualityFactor": 1.7230256577103809,
"queueFactor": 0.9460593845036932, "queueFactor": 0.9478270435023143,
"queueWeight": 0.9460593845036932, "queueWeight": 0.9478270435023143,
"recentSuccess": 49, "recentSuccess": 51,
"recentSuccessRate": 0.3684210526315789, "recentSuccessRate": 0.375,
"recentTerminal": 133, "recentTerminal": 136,
"recentWilsonLowerBound": 0.2912079039326208, "recentWilsonLowerBound": 0.29811996168499116,
"running": 8, "running": 9,
"selectionWeight": 1.6462899573547023, "selectionWeight": 1.6331303150262608,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.166666666666668, "throughputPerHour": 22.666666666666668,
"waiting": 27983 "waiting": 27978
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 751.5714285714286, "backlogHours": 717.5454545454546,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 1, "maxConcurrentTasks": 1,
"qualityFactor": 0.1650475417710333, "qualityFactor": 0.1396043766820291,
"queueFactor": 1.0225909411225904, "queueFactor": 1.0281726197261076,
"queueWeight": 1.0225909411225904, "queueWeight": 1.0281726197261076,
"recentSuccess": 8, "recentSuccess": 8,
"recentSuccessRate": 0.19047619047619047, "recentSuccessRate": 0.18181818181818182,
"recentTerminal": 42, "recentTerminal": 44,
"recentWilsonLowerBound": 0.09981889609856437, "recentWilsonLowerBound": 0.09512692558258554,
"running": 1, "running": 1,
"selectionWeight": 0.168776121069611, "selectionWeight": 0.1435373976983922,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 7.0, "throughputPerHour": 7.333333333333333,
"waiting": 5261 "waiting": 5262
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1487.9032258064515, "backlogHours": 1441.21875,
"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": 0.8109371290530965, "qualityFactor": 0.7085136151415251,
"queueFactor": 0.9230203531174571, "queueFactor": 0.9260489880969293,
"queueWeight": 0.9230203531174571, "queueWeight": 0.9260489880969293,
"recentSuccess": 19, "recentSuccess": 19,
"recentSuccessRate": 0.3064516129032258, "recentSuccessRate": 0.296875,
"recentTerminal": 62, "recentTerminal": 64,
"recentWilsonLowerBound": 0.20581430019850633, "recentWilsonLowerBound": 0.19904999589075245,
"running": 7, "running": 7,
"selectionWeight": 0.748511475214646, "selectionWeight": 0.6561183163547065,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.333333333333334, "throughputPerHour": 10.666666666666666,
"waiting": 15375 "waiting": 15373
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 427.37404580152673, "backlogHours": 427.3282442748092,
"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": 0.10888834818715337, "qualityFactor": 0.10239337240585693,
"queueFactor": 1.1129515502411453, "queueFactor": 1.1112946083240067,
"queueWeight": 1.1129515502411453, "queueWeight": 1.1112946083240067,
"recentSuccess": 17, "recentSuccess": 17,
"recentSuccessRate": 0.1297709923664122, "recentSuccessRate": 0.1297709923664122,
"recentTerminal": 131, "recentTerminal": 131,
"recentWilsonLowerBound": 0.08262458385262629, "recentWilsonLowerBound": 0.08262458385262629,
"running": 7, "running": 7,
"selectionWeight": 0.12118745591808995, "selectionWeight": 0.11378920268274094,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 21.833333333333332, "throughputPerHour": 21.833333333333332,
"waiting": 9331 "waiting": 9330
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 55.17123287671233, "backlogHours": 54.4054054054054,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -540,196 +540,196 @@
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 15, "recentSuccess": 15,
"recentSuccessRate": 0.05136986301369863, "recentSuccessRate": 0.05067567567567568,
"recentTerminal": 292, "recentTerminal": 296,
"recentWilsonLowerBound": 0.0313744398851562, "recentWilsonLowerBound": 0.03094716228930041,
"running": 24, "running": 25,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 48.666666666666664, "throughputPerHour": 49.333333333333336,
"waiting": 2685 "waiting": 2684
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 113.12068965517243, "backlogHours": 112.15384615384616,
"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": 0.4644281361398912, "qualityFactor": 0.4283542999144282,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 48, "recentSuccess": 48,
"recentSuccessRate": 0.20689655172413793, "recentSuccessRate": 0.20512820512820512,
"recentTerminal": 232, "recentTerminal": 234,
"recentWilsonLowerBound": 0.15975127623422933, "recentWilsonLowerBound": 0.15835198253118216,
"running": 3, "running": 7,
"selectionWeight": 0.6037565769818586, "selectionWeight": 0.5568605898887566,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 38.666666666666664, "throughputPerHour": 39.0,
"waiting": 4374 "waiting": 4374
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2730.0, "backlogHours": 2810.1176470588234,
"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": 1.3050280732865773, "qualityFactor": 1.0595108213200861,
"queueFactor": 0.8427001734541311, "queueFactor": 0.8377892273467443,
"queueWeight": 0.8427001734541311, "queueWeight": 0.8377892273467443,
"recentSuccess": 14, "recentSuccess": 13,
"recentSuccessRate": 0.4, "recentSuccessRate": 0.38235294117647056,
"recentTerminal": 35, "recentTerminal": 34,
"recentWilsonLowerBound": 0.25550504933307244, "recentWilsonLowerBound": 0.23899964851608782,
"running": 2, "running": 2,
"selectionWeight": 1.0997473837211091, "selectionWeight": 0.8876467523592695,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 5.833333333333333, "throughputPerHour": 5.666666666666667,
"waiting": 15925 "waiting": 15924
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 760.2857142857143, "backlogHours": 743.6774193548387,
"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": 0.44189558425407827, "qualityFactor": 0.39543939275431045,
"queueFactor": 1.020824197201031, "queueFactor": 1.0226705691251752,
"queueWeight": 1.020824197201031, "queueWeight": 1.0226705691251752,
"recentSuccess": 21, "recentSuccess": 21,
"recentSuccessRate": 0.23076923076923078, "recentSuccessRate": 0.22580645161290322,
"recentTerminal": 91, "recentTerminal": 93,
"recentWilsonLowerBound": 0.15618045094358188, "recentWilsonLowerBound": 0.15270042020646624,
"running": 7, "running": 8,
"selectionWeight": 0.45109770504285, "selectionWeight": 0.40440422884256433,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.166666666666666, "throughputPerHour": 15.5,
"waiting": 11531 "waiting": 11527
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 742.2947368421052, "backlogHours": 749.936170212766,
"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": 0.5750543158639744, "qualityFactor": 0.43786810482927707,
"queueFactor": 1.0244977835924791, "queueFactor": 1.021385767691018,
"queueWeight": 1.0244977835924791, "queueWeight": 1.021385767691018,
"recentSuccess": 24, "recentSuccess": 22,
"recentSuccessRate": 0.25263157894736843, "recentSuccessRate": 0.23404255319148937,
"recentTerminal": 95, "recentTerminal": 94,
"recentWilsonLowerBound": 0.1760442180666685, "recentWilsonLowerBound": 0.1599410529376495,
"running": 4, "running": 4,
"selectionWeight": 0.5891418720479311, "selectionWeight": 0.4472322503984623,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.833333333333334, "throughputPerHour": 15.666666666666666,
"waiting": 11753 "waiting": 11749
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1801.076923076923, "backlogHours": 1848.3947368421054,
"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": 0.8969487750853185, "queueFactor": 0.8921219778856063,
"queueWeight": 0.8969487750853185, "queueWeight": 0.8921219778856063,
"recentSuccess": 35, "recentSuccess": 35,
"recentSuccessRate": 0.44871794871794873, "recentSuccessRate": 0.4605263157894737,
"recentTerminal": 78, "recentTerminal": 76,
"recentWilsonLowerBound": 0.3433419189622355, "recentWilsonLowerBound": 0.3530754655326989,
"running": 4, "running": 4,
"selectionWeight": 2.2423719377132962, "selectionWeight": 2.2303049447140157,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 13.0, "throughputPerHour": 12.666666666666666,
"waiting": 23414 "waiting": 23413
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 3263.785714285714, "backlogHours": 3384.6666666666665,
"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": 0.4195402960798209, "qualityFactor": 0.4294056856096667,
"queueFactor": 0.8204256594269763, "queueFactor": 0.8147344145787095,
"queueWeight": 0.8204256594269763, "queueWeight": 0.8147344145787095,
"recentSuccess": 8, "recentSuccess": 8,
"recentSuccessRate": 0.2857142857142857, "recentSuccessRate": 0.2962962962962963,
"recentTerminal": 28, "recentTerminal": 27,
"recentWilsonLowerBound": 0.15253815848329966, "recentWilsonLowerBound": 0.15852853317647564,
"running": 2, "running": 2,
"selectionWeight": 0.34420162406747595, "selectionWeight": 0.3498515898819612,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 4.666666666666667, "throughputPerHour": 4.5,
"waiting": 15231 "waiting": 15231
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1456.8679245283017, "backlogHours": 1403.7818181818184,
"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": 0.18779326396236312, "qualityFactor": 0.1623252014770643,
"queueFactor": 0.9259434270312282, "queueFactor": 0.9297121467599777,
"queueWeight": 0.9259434270312282, "queueWeight": 0.9297121467599777,
"recentSuccess": 10, "recentSuccess": 10,
"recentSuccessRate": 0.18867924528301888, "recentSuccessRate": 0.18181818181818182,
"recentTerminal": 53, "recentTerminal": 55,
"recentWilsonLowerBound": 0.10585211943149556, "recentWilsonLowerBound": 0.10187561448030713,
"running": 16, "running": 16,
"selectionWeight": 0.17388593840669056, "selectionWeight": 0.15091571153848737,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.833333333333334, "throughputPerHour": 9.166666666666666,
"waiting": 12869 "waiting": 12868
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 707.6697247706421, "backlogHours": 688.4464285714286,
"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": 0.696768102613484, "qualityFactor": 0.7348252282176054,
"queueFactor": 1.0318650145936485, "queueFactor": 1.0345772504007573,
"queueWeight": 1.0318650145936485, "queueWeight": 1.0345772504007573,
"recentSuccess": 29, "recentSuccess": 31,
"recentSuccessRate": 0.26605504587155965, "recentSuccessRate": 0.2767857142857143,
"recentTerminal": 109, "recentTerminal": 112,
"recentWilsonLowerBound": 0.19209740149947543, "recentWilsonLowerBound": 0.2023765976068205,
"running": 6, "running": 8,
"selectionWeight": 0.7189706283716515, "selectionWeight": 0.7602334641344792,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.166666666666668, "throughputPerHour": 18.666666666666668,
"waiting": 12856 "waiting": 12851
} }
}, },
"queueAttemptedAt": "2026-09-15T08:24:38.376700+00:00", "queueAttemptedAt": "2026-09-15T08:35:09.286296+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-15T08:24:38.376700+00:00", "queueUpdatedAt": "2026-09-15T08:35:09.286296+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": "2026-09-15T06:27:28.925726+00:00", "generatedAt": "2026-09-15T08:35:01.513704+00:00",
"lastSyncTime": "2026-09-15T06:27:28.885169+00:00", "lastSyncTime": "2026-09-15T08:35:00.090935+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1750,13 +1750,13 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 52, "decisionTotal": 52,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 38, "ambiguous_runtime": 39,
"framework_architecture_unsupported": 48, "framework_architecture_unsupported": 48,
"memory_capacity": 1, "memory_capacity": 1,
"repository_structure": 1, "repository_structure": 1,
"tokenizer_compatibility": 2 "tokenizer_compatibility": 2
}, },
"failureCount": 90, "failureCount": 91,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -1766,8 +1766,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b4", "targetGpu": "Ascend_910-b4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 90, "total": 91,
"unresolvedFailureCount": 38 "unresolvedFailureCount": 39
}, },
"Biren_166m|unknown|text-generation": { "Biren_166m|unknown|text-generation": {
"attributableFailureCount": 32, "attributableFailureCount": 32,
@@ -2637,7 +2637,7 @@
"decisionSuccessRate": 0.0174, "decisionSuccessRate": 0.0174,
"decisionTotal": 344, "decisionTotal": 344,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 217, "ambiguous_runtime": 218,
"backend_operator": 34, "backend_operator": 34,
"framework_architecture_unsupported": 249, "framework_architecture_unsupported": 249,
"memory_capacity": 7, "memory_capacity": 7,
@@ -2648,15 +2648,15 @@
"tokenizer_compatibility": 7, "tokenizer_compatibility": 7,
"参数/模板问题": 30 "参数/模板问题": 30
}, },
"failureCount": 587, "failureCount": 588,
"failureRate": 0.9899, "failureRate": 0.9899,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 6, "successCount": 6,
"successRate": 0.0101, "successRate": 0.0101,
"total": 593, "total": 594,
"unresolvedFailureCount": 247 "unresolvedFailureCount": 248
}, },
"vllm-mlu": { "vllm-mlu": {
"attributableFailureCount": 8, "attributableFailureCount": 8,
@@ -2764,7 +2764,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-15T06:27:28.920746+00:00", "generatedAt": "2026-09-15T08:35:01.508593+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 40, "attributableFailureCount": 40,
@@ -2795,7 +2795,7 @@
"decisionSuccessRate": 0.0364, "decisionSuccessRate": 0.0364,
"decisionTotal": 55, "decisionTotal": 55,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 39, "ambiguous_runtime": 40,
"framework_architecture_unsupported": 48, "framework_architecture_unsupported": 48,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 1, "model_load": 1,
@@ -2804,15 +2804,15 @@
"参数/模板问题": 12, "参数/模板问题": 12,
"验证失败": 175 "验证失败": 175
}, },
"failureCount": 279, "failureCount": 280,
"failureRate": 0.9929, "failureRate": 0.9929,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 2,
"successRate": 0.0071, "successRate": 0.0071,
"total": 281, "total": 282,
"unresolvedFailureCount": 226 "unresolvedFailureCount": 227
}, },
"Biren_166m": { "Biren_166m": {
"attributableFailureCount": 39, "attributableFailureCount": 39,
@@ -5512,21 +5512,21 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Ascend_910-b4|vllm|text-generation": { "Ascend_910-b4|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": 15 "framework_architecture_unsupported": 14
}, },
"failureCount": 20, "failureCount": 20,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-15T06:05:16.606079+00:00", "lastTerminalAt": "2026-09-15T08:35:00.090935+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -5535,7 +5535,7 @@
"targetGpu": "Ascend_910-b4", "targetGpu": "Ascend_910-b4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 20, "total": 20,
"unresolvedFailureCount": 5 "unresolvedFailureCount": 6
}, },
"Biren_166m|unknown|text-generation": { "Biren_166m|unknown|text-generation": {
"attributableFailureCount": 8, "attributableFailureCount": 8,
@@ -9369,15 +9369,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1907, "terminalRecords": 1908,
"totalRecords": 2001, "totalRecords": 2002,
"totals": { "totals": {
"attributableFailureCount": 587, "attributableFailureCount": 587,
"decisionFailureRate": 0.8989, "decisionFailureRate": 0.8989,
"decisionSuccessRate": 0.1011, "decisionSuccessRate": 0.1011,
"decisionTotal": 653, "decisionTotal": 653,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 458, "ambiguous_runtime": 459,
"backend_operator": 44, "backend_operator": 44,
"framework_architecture_unsupported": 381, "framework_architecture_unsupported": 381,
"memory_capacity": 12, "memory_capacity": 12,
@@ -9389,15 +9389,15 @@
"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": 1841, "failureCount": 1842,
"failureRate": 0.9654, "failureRate": 0.9654,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 7, "platformFailureCount": 7,
"successCount": 66, "successCount": 66,
"successRate": 0.0346, "successRate": 0.0346,
"total": 1907, "total": 1908,
"unresolvedFailureCount": 1247 "unresolvedFailureCount": 1248
}, },
"warnings": [ "warnings": [
"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。",
@@ -9435,6 +9435,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 2001, "summarizedRecords": 2002,
"version": 1 "version": 1
} }

View File

@@ -1,3 +1,4 @@
{"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": "2026-09-15T08:35:00.090935+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T08:31:22+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4593061", "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": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-15T06:27:13.910681+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T06:23:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4544266", "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": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-15T06:27:13.910681+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T06:23:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4544266", "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": "2026-09-15T06:27:13.910666+00:00", "modelId": "douyamv/Qwen3.8-27B-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T06:19:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4609095", "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": "2026-09-15T06:27:13.910666+00:00", "modelId": "douyamv/Qwen3.8-27B-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T06:19:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4609095", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "no_idle_device", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-15T06:16:21.605532+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T06:15:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490279", "taskType": "text-generation", "verifyResult": -1} {"failReason": "platform_infrastructure", "failureAction": "open_short_gpu_framework_circuit_and_retry_other_models", "failureCategory": "platform_infrastructure", "failureClassificationReason": "no_idle_device", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm", "lastSyncTime": "2026-09-15T06:16:21.605532+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-15T06:15:21+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4490279", "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": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T06:11:26.144180+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:05:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610355", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "quantization_error", "failureCode": "QUANTIZATION_ERROR", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "", "lastSyncTime": "2026-09-10T06:11:26.144180+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T06:05:21+00:00", "targetGpu": "Biren_166m", "taskId": "4610355", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:03:48.106911+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471974", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:03:48.106911+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a16-per-channel", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:59:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4471974", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:03:48.106939+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:57:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493605", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-10T06:03:48.106939+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:57:21+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4493605", "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": "2026-09-10T05:56:10.303668+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-FP8-K-V", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-10T05:55:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4477782", "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": "405094fc5c8b5a92021b47c64cdf63a6cb4dd161f074211f1498fcfbb2c1c3e8", ".modelhub_state/architecture_compatibility_blacklist.json": "63193fa8a9387cce2e9b32b3046598cc96f09356a1e10a7382033bb47f275137",
".modelhub_state/architecture_history_backfill.json": "2a755b14f4182e956183e499bbdd679c127aa4e593aae974be7c73e58bb60552", ".modelhub_state/architecture_history_backfill.json": "a8f24235688f609a8d280ccaaca61d0c5fded960878613b067cd3ffbfb23d45c",
".modelhub_state/market_intelligence.json": "fd63fab1208511f8ab4764009e381245e6f6a4251867ddb264ba2e6232c8b1c7", ".modelhub_state/market_intelligence.json": "bb949d38c1a5f70ba02b16bc449e448a5ac97435c5ed10e1620989a7a1622748",
".modelhub_state/official_capabilities.json": "fdd0324a08ad883ee8e0173cd751fef45db5f5706ba26623ea65ab40cb646e1a", ".modelhub_state/official_capabilities.json": "35ba01eec0c30e1fa5fcf1b4b9f254914f06496c88e49ac44a4ee3909bdf166a",
".modelhub_state/outcome_checkpoint.json": "c3309bc564d2f370e7d305dc67ae19601789082263a38e0aa8dfb1541bf74658", ".modelhub_state/outcome_checkpoint.json": "d3b20aae18391ab1734ee14c64c1b6092d70f4f3c57b6ae94ccb06f8eec1061a",
".modelhub_state/queue_cleanup_latest.json": "3e511035a77fe68d9f1adfb35e149ee220beed7c3962d87b7d1892cc816fb69a", ".modelhub_state/queue_cleanup_latest.json": "3e511035a77fe68d9f1adfb35e149ee220beed7c3962d87b7d1892cc816fb69a",
".modelhub_state/recent_outcomes.jsonl": "b8471dd6f4fc32f402ad879b1f31be189c2becb4f90eea48f24aa6e04338a3ea", ".modelhub_state/recent_outcomes.jsonl": "e188326b569f2f05751a31a6304a4bf7c5a7b2734b67f075ee5d6ded2e2ff8e4",
".modelhub_state/recovery_active_tasks.jsonl": "2718a71fe16b6c9d84ab4d9fb6950bfba51b97f728be616af2774561280ed524", ".modelhub_state/recovery_active_tasks.jsonl": "42c5a321d81942917d611a10fc20c5a302266ad82e32167ab54d03430702a4cb",
".modelhub_state/recovery_intents.jsonl": "92a1bf59d60ad0b864cc6939821be065d87a3988ff9e0e4d8d55bcbc9bebb91a", ".modelhub_state/recovery_intents.jsonl": "56e10574cd5193859480d55366f8f691ad794a9963c088c113b5d2329a974c88",
".modelhub_state/routing_intelligence.json": "e2e6203553a870b58a0f2f64ef0b06f8d85cea236effe6439aef0de6d32972fb", ".modelhub_state/routing_intelligence.json": "e2e6203553a870b58a0f2f64ef0b06f8d85cea236effe6439aef0de6d32972fb",
".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": "5f1f6efc934b832c7fcfeecf6d4d8d29d3c706d7a77ba23bc7cd306dbcbdd85f", "ledger/submissions.jsonl": "5f1f6efc934b832c7fcfeecf6d4d8d29d3c706d7a77ba23bc7cd306dbcbdd85f",
"outcomes/submissions.jsonl": "ff30032fdc8c2669b97f2e7020f42866fd4dcea9be3bdc68ec77b643850e5cd8" "outcomes/submissions.jsonl": "ff30032fdc8c2669b97f2e7020f42866fd4dcea9be3bdc68ec77b643850e5cd8"
}, },
"generation": 7602, "generation": 7603,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-15T08:33:59.420802+00:00", "updatedAt": "2026-09-15T08:37:02.302532+00:00",
"writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c" "writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c"
} }