CoolBoy/submmit
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

state: generation 21648 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 01:57:00 +00:00
parent 985b7aa76e
commit d0f94ff231
8 changed files with 2048 additions and 2025 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2779,7 +2779,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-07T01:47:37.044879+00:00", "generatedAt": "2026-10-07T01:55:18.496779+00:00",
"summary": { "summary": {
"activeBlockCount": 140, "activeBlockCount": 140,
"byGpuFramework": { "byGpuFramework": {

272
.modelhub_state/market_intelligence.json
View File

@@ -434,121 +434,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-07T01:54:14.751477+00:00", "generatedAt": "2026-10-07T01:56:47.591304+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 977.5384615384615, "backlogHours": 989.2095808383234,
"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": 1.4094818889537137, "qualityFactor": 1.3609237651996209,
"queueFactor": 1.0025812084297403, "queueFactor": 1.001665887277555,
"queueWeight": 1.0025812084297403, "queueWeight": 1.001665887277555,
"recentSuccess": 54, "recentSuccess": 53,
"recentSuccessRate": 0.31952662721893493, "recentSuccessRate": 0.31736526946107785,
"recentTerminal": 169, "recentTerminal": 167,
"recentWilsonLowerBound": 0.253905220669305, "recentWilsonLowerBound": 0.2515549178173127,
"running": 8, "running": 8,
"selectionWeight": 1.4131200554870473, "selectionWeight": 1.3631909107857891,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 28.166666666666668, "throughputPerHour": 27.833333333333332,
"waiting": 27534 "waiting": 27533
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1134.4528301886792, "backlogHours": 1141.8987341772151,
"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": 0.9804414688459532, "queueFactor": 0.9803293204954554,
"queueWeight": 0.9804414688459532, "queueWeight": 0.9803293204954554,
"recentSuccess": 64, "recentSuccess": 64,
"recentSuccessRate": 0.4025157232704403, "recentSuccessRate": 0.4050632911392405,
"recentTerminal": 159, "recentTerminal": 158,
"recentWilsonLowerBound": 0.3294572998492744, "recentWilsonLowerBound": 0.3316508308477739,
"running": 7, "running": 8,
"selectionWeight": 2.451103672114883, "selectionWeight": 2.4508233012386387,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.5, "throughputPerHour": 26.333333333333332,
"waiting": 30063 "waiting": 30070
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 121.02777777777777, "backlogHours": 120.38709677419355,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.5068485139821515, "qualityFactor": 0.5523754791922271,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 45, "recentSuccess": 47,
"recentSuccessRate": 0.20833333333333334, "recentSuccessRate": 0.21658986175115208,
"recentTerminal": 216, "recentTerminal": 217,
"recentWilsonLowerBound": 0.15950379837548626, "recentWilsonLowerBound": 0.1669679372070296,
"running": 6, "running": 8,
"selectionWeight": 0.6589030681767969, "selectionWeight": 0.7180881229498952,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 36.0, "throughputPerHour": 36.166666666666664,
"waiting": 4357 "waiting": 4354
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1210.094117647059, "backlogHours": 1168.7045454545455,
"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": 0.3706925078772283, "qualityFactor": 0.33759935736441393,
"queueFactor": 0.9709944909509484, "queueFactor": 0.9769231942917355,
"queueWeight": 0.9709944909509484, "queueWeight": 0.9769231942917355,
"recentSuccess": 18, "recentSuccess": 18,
"recentSuccessRate": 0.21176470588235294, "recentSuccessRate": 0.20454545454545456,
"recentTerminal": 85, "recentTerminal": 88,
"recentWilsonLowerBound": 0.13836125681504122, "recentWilsonLowerBound": 0.13348619800482903,
"running": 5, "running": 7,
"selectionWeight": 0.3599403829855797, "selectionWeight": 0.3298086425872804,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.166666666666666, "throughputPerHour": 14.666666666666666,
"waiting": 17143 "waiting": 17141
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 412.0869565217391, "backlogHours": 424.43283582089555,
"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": 0.3338987614370027, "qualityFactor": 0.31680379698326333,
"queueFactor": 1.1412776386765129, "queueFactor": 1.1372207740230962,
"queueWeight": 1.1412776386765129, "queueWeight": 1.1372207740230962,
"recentSuccess": 26, "recentSuccess": 25,
"recentSuccessRate": 0.18840579710144928, "recentSuccessRate": 0.1865671641791045,
"recentTerminal": 138, "recentTerminal": 134,
"recentWilsonLowerBound": 0.13194064080494428, "recentWilsonLowerBound": 0.1296838224720284,
"running": 7, "running": 7,
"selectionWeight": 0.38107119000983475, "selectionWeight": 0.36027585921876254,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.0, "throughputPerHour": 22.333333333333332,
"waiting": 9478 "waiting": 9479
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 47.535, "backlogHours": 47.144999999999996,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -561,193 +561,193 @@
"recentSuccessRate": 0.0225, "recentSuccessRate": 0.0225,
"recentTerminal": 400, "recentTerminal": 400,
"recentWilsonLowerBound": 0.011881448169963291, "recentWilsonLowerBound": 0.011881448169963291,
"running": 18, "running": 23,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 66.66666666666667, "throughputPerHour": 66.66666666666667,
"waiting": 3169 "waiting": 3143
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 247.3161290322581, "backlogHours": 243.36305732484075,
"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": 0.14515561298023474, "qualityFactor": 0.1218537460986048,
"queueFactor": 1.2321164966194182, "queueFactor": 1.2361692405484843,
"queueWeight": 1.2321164966194182, "queueWeight": 1.2361692405484843,
"recentSuccess": 21, "recentSuccess": 20,
"recentSuccessRate": 0.13548387096774195, "recentSuccessRate": 0.12738853503184713,
"recentTerminal": 155, "recentTerminal": 157,
"recentWilsonLowerBound": 0.09035094342918001, "recentWilsonLowerBound": 0.08399849173135455,
"running": 5, "running": 10,
"selectionWeight": 0.178848625329851, "selectionWeight": 0.15063185277270014,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.833333333333332, "throughputPerHour": 26.166666666666668,
"waiting": 6389 "waiting": 6368
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2221.5714285714284, "backlogHours": 2275.4634146341464,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_mrv-100", "gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.7509306942392433, "qualityFactor": 0.7828338687897467,
"queueFactor": 0.8864221427578725, "queueFactor": 0.8840068946257164,
"queueWeight": 0.8864221427578725, "queueWeight": 0.8840068946257164,
"recentSuccess": 13, "recentSuccess": 13,
"recentSuccessRate": 0.30952380952380953, "recentSuccessRate": 0.3170731707317073,
"recentTerminal": 42, "recentTerminal": 41,
"recentWilsonLowerBound": 0.1907092651972273, "recentWilsonLowerBound": 0.19564433205311735,
"running": 1, "running": 2,
"selectionWeight": 0.6656415950502068, "selectionWeight": 0.6920305373566594,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 7.0, "throughputPerHour": 6.833333333333333,
"waiting": 15551 "waiting": 15549
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 351.525, "backlogHours": 351.3375,
"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": 0.1933127122317788, "qualityFactor": 0.1905110248867203,
"queueFactor": 1.1688161554943766, "queueFactor": 1.1699234734828168,
"queueWeight": 1.1688161554943766, "queueWeight": 1.1699234734828168,
"recentSuccess": 24, "recentSuccess": 24,
"recentSuccessRate": 0.15, "recentSuccessRate": 0.15,
"recentTerminal": 160, "recentTerminal": 160,
"recentWilsonLowerBound": 0.10291773698744075, "recentWilsonLowerBound": 0.10291773698744075,
"running": 6, "running": 8,
"selectionWeight": 0.2259470211189384, "selectionWeight": 0.22288331997224317,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.666666666666668, "throughputPerHour": 26.666666666666668,
"waiting": 9374 "waiting": 9369
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 669.2727272727273, "backlogHours": 683.0721649484535,
"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": 0.3994092211479776, "qualityFactor": 0.4123243205049007,
"queueFactor": 1.0612047107508835, "queueFactor": 1.0588785299746502,
"queueWeight": 1.0612047107508835, "queueWeight": 1.0588785299746502,
"recentSuccess": 21, "recentSuccess": 21,
"recentSuccessRate": 0.21212121212121213, "recentSuccessRate": 0.21649484536082475,
"recentTerminal": 99, "recentTerminal": 97,
"recentWilsonLowerBound": 0.14313429916193274, "recentWilsonLowerBound": 0.14618670657065766,
"running": 4, "running": 4,
"selectionWeight": 0.42385494699957527, "selectionWeight": 0.43660137036902574,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.5, "throughputPerHour": 16.166666666666668,
"waiting": 11043 "waiting": 11043
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1521.767441860465, "backlogHours": 1504.4137931034484,
"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": 1.1984040883238989, "qualityFactor": 1.149868851369287,
"queueFactor": 0.9381826455776731, "queueFactor": 0.9406131257832155,
"queueWeight": 0.9381826455776731, "queueWeight": 0.9406131257832155,
"recentSuccess": 28, "recentSuccess": 28,
"recentSuccessRate": 0.32558139534883723, "recentSuccessRate": 0.3218390804597701,
"recentTerminal": 86, "recentTerminal": 87,
"recentWilsonLowerBound": 0.23585553745183332, "recentWilsonLowerBound": 0.23300577279734025,
"running": 4, "running": 4,
"selectionWeight": 1.1243219180548147, "selectionWeight": 1.0815817345272207,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.333333333333334, "throughputPerHour": 14.5,
"waiting": 21812 "waiting": 21814
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 2086.65306122449, "backlogHours": 2044.9199999999998,
"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": 0.3245495550726005, "qualityFactor": 0.30538500215517983,
"queueFactor": 0.8947920180655805, "queueFactor": 0.8982861060506538,
"queueWeight": 0.8947920180655805, "queueWeight": 0.8982861060506538,
"recentSuccess": 11, "recentSuccess": 11,
"recentSuccessRate": 0.22448979591836735, "recentSuccessRate": 0.22,
"recentTerminal": 49, "recentTerminal": 50,
"recentWilsonLowerBound": 0.1302483771472861, "recentWilsonLowerBound": 0.1275378622430229,
"running": 1, "running": 2,
"selectionWeight": 0.2904043513456985, "selectionWeight": 0.274323104432247,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.166666666666666, "throughputPerHour": 8.333333333333334,
"waiting": 17041 "waiting": 17041
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1277.925, "backlogHours": 1231.734939759036,
"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": 0.9630832583584571, "queueFactor": 0.9692560971994898,
"queueWeight": 0.9630832583584571, "queueWeight": 0.9692560971994898,
"recentSuccess": 3, "recentSuccess": 3,
"recentSuccessRate": 0.0375, "recentSuccessRate": 0.03614457831325301,
"recentTerminal": 80, "recentTerminal": 83,
"recentWilsonLowerBound": 0.012834336300788755, "recentWilsonLowerBound": 0.012367579124893054,
"running": 16, "running": 16,
"selectionWeight": 0.048154162917922856, "selectionWeight": 0.04846280485997449,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 13.333333333333334, "throughputPerHour": 13.833333333333334,
"waiting": 17039 "waiting": 17039
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 1011.4285714285714, "backlogHours": 1011.2857142857143,
"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": 0.7109315395317777, "qualityFactor": 0.6444029282445073,
"queueFactor": 0.9974688815728332, "queueFactor": 0.9983551209736672,
"queueWeight": 0.9974688815728332, "queueWeight": 0.9983551209736672,
"recentSuccess": 32, "recentSuccess": 31,
"recentSuccessRate": 0.25396825396825395, "recentSuccessRate": 0.24603174603174602,
"recentTerminal": 126, "recentTerminal": 126,
"recentWilsonLowerBound": 0.1860228544733811, "recentWilsonLowerBound": 0.17908230637931405,
"running": 4, "running": 6,
"selectionWeight": 0.7091320876116147, "selectionWeight": 0.6433429633833304,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 21.0, "throughputPerHour": 21.0,
"waiting": 21240 "waiting": 21237
} }
}, },
"queueAttemptedAt": "2026-10-07T01:46:24.177524+00:00", "queueAttemptedAt": "2026-10-07T01:56:47.591304+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-07T01:46:24.177524+00:00", "queueUpdatedAt": "2026-10-07T01:56:47.591304+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{ {
"catalogUpdatedAt": "2026-10-07T01:54:14.751477+00:00", "catalogUpdatedAt": "2026-10-07T01:56:47.591304+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-10-07T01:54:14.751477+00:00", "generatedAt": "2026-10-07T01:56:47.591304+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6548,6 +6548,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-10-07T01:54:14.751477+00:00", "taskTreeUpdatedAt": "2026-10-07T01:56:47.591304+00:00",
"version": 1 "version": 1
} }

84
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-07T01:11:29.278446+00:00", "generatedAt": "2026-10-07T01:55:18.403270+00:00",
"lastSyncTime": "2026-10-07T01:11:29.042626+00:00", "lastSyncTime": "2026-10-07T01:55:18.170081+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -3219,10 +3219,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 1,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 126, "ambiguous_runtime": 127,
"memory_capacity": 1 "memory_capacity": 1
}, },
"failureCount": 127, "failureCount": 128,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -3232,8 +3232,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 127, "total": 128,
"unresolvedFailureCount": 126 "unresolvedFailureCount": 127
}, },
"Biren_166m|vllm|text-generation": { "Biren_166m|vllm|text-generation": {
"attributableFailureCount": 50, "attributableFailureCount": 50,
@@ -5610,7 +5610,7 @@
"decisionSuccessRate": 0.0281, "decisionSuccessRate": 0.0281,
"decisionTotal": 178, "decisionTotal": 178,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 362, "ambiguous_runtime": 363,
"backend_operator": 9, "backend_operator": 9,
"framework_architecture_unsupported": 47, "framework_architecture_unsupported": 47,
"memory_capacity": 10, "memory_capacity": 10,
@@ -5619,15 +5619,15 @@
"tokenizer_compatibility": 95, "tokenizer_compatibility": 95,
"参数/模板问题": 13 "参数/模板问题": 13
}, },
"failureCount": 573, "failureCount": 574,
"failureRate": 0.9913, "failureRate": 0.9914,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 25, "platformFailureCount": 25,
"successCount": 5, "successCount": 5,
"successRate": 0.0087, "successRate": 0.0086,
"total": 578, "total": 579,
"unresolvedFailureCount": 375 "unresolvedFailureCount": 376
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"attributableFailureCount": 150, "attributableFailureCount": 150,
@@ -5658,7 +5658,7 @@
"unresolvedFailureCount": 236 "unresolvedFailureCount": 236
} }
}, },
"generatedAt": "2026-10-07T01:11:29.260425+00:00", "generatedAt": "2026-10-07T01:55:18.386532+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 119, "attributableFailureCount": 119,
@@ -5721,7 +5721,7 @@
"decisionSuccessRate": 0.1147, "decisionSuccessRate": 0.1147,
"decisionTotal": 218, "decisionTotal": 218,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 270, "ambiguous_runtime": 271,
"backend_operator": 4, "backend_operator": 4,
"context_length": 10, "context_length": 10,
"framework_architecture_unsupported": 125, "framework_architecture_unsupported": 125,
@@ -5735,15 +5735,15 @@
"日志缺失": 62, "日志缺失": 62,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 768, "failureCount": 769,
"failureRate": 0.9685, "failureRate": 0.9685,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 25, "successCount": 25,
"successRate": 0.0315, "successRate": 0.0315,
"total": 793, "total": 794,
"unresolvedFailureCount": 573 "unresolvedFailureCount": 574
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"attributableFailureCount": 759, "attributableFailureCount": 759,
@@ -8887,9 +8887,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 6 "ambiguous_runtime": 7
}, },
"failureCount": 6, "failureCount": 7,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelType": "gemma2", "modelType": "gemma2",
@@ -8901,8 +8901,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 6, "total": 7,
"unresolvedFailureCount": 6 "unresolvedFailureCount": 7
}, },
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma3|compressed-tensors": { "Biren_166m|vllm_fix_tokenizer|text-generation|gemma3|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -33730,6 +33730,30 @@
"total": 2, "total": 2,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 2
}, },
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|34": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm_fix_tokenizer|text-generation|gemma3|compressed-tensors|34": { "Biren_166m|vllm_fix_tokenizer|text-generation|gemma3|compressed-tensors|34": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -57856,15 +57880,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17352, "terminalRecords": 17353,
"totalRecords": 17576, "totalRecords": 17577,
"totals": { "totals": {
"attributableFailureCount": 6238, "attributableFailureCount": 6238,
"decisionFailureRate": 0.8645, "decisionFailureRate": 0.8645,
"decisionSuccessRate": 0.1355, "decisionSuccessRate": 0.1355,
"decisionTotal": 7216, "decisionTotal": 7216,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4556, "ambiguous_runtime": 4557,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 129, "backend_operator": 129,
@@ -57880,15 +57904,15 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16374, "failureCount": 16375,
"failureRate": 0.9436, "failureRate": 0.9436,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 952, "platformFailureCount": 952,
"successCount": 978, "successCount": 978,
"successRate": 0.0564, "successRate": 0.0564,
"total": 17352, "total": 17353,
"unresolvedFailureCount": 9184 "unresolvedFailureCount": 9185
}, },
"warnings": [ "warnings": [
"GPU MetaX_c-500 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。",
@@ -57897,14 +57921,14 @@
"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 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 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 Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 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 Cambricon_mlu-370-x8 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-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 Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 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。",
"组合 Vastai_va16|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|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b3|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 Ascend_910-b3|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 Iluvatar_mrv-100|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 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -57948,6 +57972,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17576, "summarizedRecords": 17577,
"version": 1 "version": 1
} }

1558
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2130
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "ee5342653e8453090d13782c1c4638168cbf4d1d85c422cbe6f0ca024ba5d219", ".modelhub_state/architecture_compatibility_blacklist.json": "f8ecf4da84be5335c72841cde6317322c1233b5eb952f25383341d0a0d89c6f6",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "cd5f629a6e4d89cc78a495b46559d646c0aa49ce61bf22d80666989c64fd1be0", ".modelhub_state/market_intelligence.json": "655db90bc1d12a9784fd9c5f42207d8ab9a86d4344f5b68d14d3ba08aef1834a",
".modelhub_state/official_capabilities.json": "2fcbd6deef44117604e3f284d2d6226af90b25f74d1cf32bf01a754c977445a5", ".modelhub_state/official_capabilities.json": "63ac5254c799c0924ced880012e43b6b903939f7b3fa5e67679ad12ecac7841d",
".modelhub_state/outcome_checkpoint.json": "9354f147d20ec54cab0fb80ae5def88bb0bacdb8bf5b7486cbfc681f204d3619", ".modelhub_state/outcome_checkpoint.json": "825cba37de4c460deed7936d1d91190dfa53bd2f02849a73e450c9c341bc91fc",
".modelhub_state/queue_cleanup_latest.json": "ac7dfc049da9da5930d3d9f4962bd3c2a0fa628a03049f8e5fa8eca7c87d8fe1", ".modelhub_state/queue_cleanup_latest.json": "ac7dfc049da9da5930d3d9f4962bd3c2a0fa628a03049f8e5fa8eca7c87d8fe1",
".modelhub_state/recent_outcomes.jsonl": "a431175c907bbd6eee4fecc9c3aeb926cd1c2b0218bbb9db9c0593e063c02b66", ".modelhub_state/recent_outcomes.jsonl": "a431175c907bbd6eee4fecc9c3aeb926cd1c2b0218bbb9db9c0593e063c02b66",
".modelhub_state/recovery_active_tasks.jsonl": "834b1e25fef02b054eee0d8f0d61b88339294383ed7f7996a7ae59605b676067", ".modelhub_state/recovery_active_tasks.jsonl": "bc9e8c4d10392f7f329a8e307c296c8b2e291958ddffb2f60350c2d7ff06a917",
".modelhub_state/recovery_intents.jsonl": "c772c23cd2fb3fcfc4a6b058c95b848835a967547b436f429542231cb2b16c1a", ".modelhub_state/recovery_intents.jsonl": "1d8372cde3ff4f606dc8d408235618127d9803547b7232eed531ea6ddb294bc5",
".modelhub_state/routing_intelligence.json": "186e379f649ae2f31a690f5030563073799829887e59540698e98641a9ce3b2c", ".modelhub_state/routing_intelligence.json": "186e379f649ae2f31a690f5030563073799829887e59540698e98641a9ce3b2c",
".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5", ".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f", ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "6340b8ce5b5a629529628fe5050c7b040b61d49405a657d4f23c1b7ab496a56c", "ledger/submissions.jsonl": "6340b8ce5b5a629529628fe5050c7b040b61d49405a657d4f23c1b7ab496a56c",
"outcomes/submissions.jsonl": "bd09198b367f0794030e18a1863aef1d40e3dc3c0dd9f11c057e65ffcb686b6c" "outcomes/submissions.jsonl": "09780620b354e80f44f5eebe883243a93bea6b9baddb9d992454f7cbd2e5acbc"
}, },
"generation": 21647, "generation": 21648,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-07T01:54:15.826632+00:00", "updatedAt": "2026-10-07T01:57:00.439385+00:00",
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2" "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
} }

3
outcomes/submissions.jsonl
View File

@@ -193,7 +193,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T08:25:31.485626+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3-8B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556376, "estimatedRequiredGiB": 17.964, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16073634582, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16073634582}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:22:06.134784+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4990307", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T08:25:31.485626+00:00", "modelId": "aisingapore/Llama-SEA-LION-v3-8B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16060556376, "estimatedRequiredGiB": 17.964, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 16073634582, "modelscopeLicense": "llama3.1", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16073634582}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:22:06.134784+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4990307", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295624+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:19:31.687350+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991029", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T09:32:45.295624+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "382ef635ba042d77a729681df1994f5ac5e7beaf5980ac5d2e7045645d11c732", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T01:19:31.687350+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991029", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998391+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:04:12.536952+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991720", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998391+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Thinking-MLX-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248516007, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx", "custom_tag:reasoning"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248516007}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:04:12.536952+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4991720", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:09:08.998195+00:00", "modelId": "RedHatAI/gemma-2-27b-it-quantized.w8a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30775446656, "estimatedRequiredGiB": 34.419, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 30797371689, "modelscopeLicense": "gemma", "modelscopeParams": 28406776320, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30797371689}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:08:13.509125+00:00", "targetGpu": "Biren_166m", "taskId": "4991811", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:33:30.477748+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:08.713395+00:00", "targetGpu": "Biren_166m", "taskId": "4991852", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T10:33:30.477748+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "jais2", "modelscopeFileSize": 16193187697, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8090401280, "modelscopeTags": ["license:apache-2.0", "model_type:jais2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16193187697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T02:09:08.713395+00:00", "targetGpu": "Biren_166m", "taskId": "4991852", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T12:58:50.741624+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T04:44:11.759434+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4994057", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T12:58:50.741624+00:00", "modelId": "BAAI/AquilaMed-RL", "modelProfile": {"architectures": ["AquilaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6968, "estimatedRequiredGiB": 18.386, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "aquila3", "modelscopeFileSize": 16451477782, "modelscopeLicense": "other", "modelscopeParams": 8223748096, "modelscopeTags": ["license:other", "model_type:aquila3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:arxiv:2406.12182"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16451477782}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T04:44:11.759434+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4994057", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T14:32:55.759836+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:25:35.855289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995260", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-21T14:32:55.759836+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231270112, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233120748, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-09-20T18:18:38.666111+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 1233120748}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T06:25:35.855289+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4995260", "taskType": "text-generation", "verifyResult": null}
@@ -1038,7 +1037,7 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T23:34:00.361444+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T15:28:01.845021+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5334000", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T23:34:00.361444+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T15:28:01.845021+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5334000", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T00:15:56.875069+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T15:49:30.159431+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5337783", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T00:15:56.875069+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T15:49:30.159431+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5337783", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T01:19:21.272519+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T17:10:22.746810+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5338817", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T01:19:21.272519+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T17:10:22.746810+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5338817", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17593027563}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T17:37:43.462174+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5339448", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T01:55:18.170055+00:00", "modelId": "ibm-granite/granite-4.2-8b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17583228032, "estimatedRequiredGiB": 19.662, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 17593027563, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8791592960, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 17593027563}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T17:37:43.462174+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5339448", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "2fa45b75e4d617f12bf51b750d20c9f095b0f2ca0d5d0d11b71927e24a75e3e5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T18:24:48.750563+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5339863", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "2fa45b75e4d617f12bf51b750d20c9f095b0f2ca0d5d0d11b71927e24a75e3e5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T18:24:48.750563+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5339863", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T18:24:48.847650+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5339864", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T18:24:48.847650+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5339864", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "b3ef6bcf57e6bb4fc9ede989e67a765b0e40b19fbd407f1f8452833c12bd5c38", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T18:24:48.659775+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5339858", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "b3ef6bcf57e6bb4fc9ede989e67a765b0e40b19fbd407f1f8452833c12bd5c38", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-06T18:24:48.659775+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5339858", "taskType": "text-generation", "verifyResult": null}