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

state: generation 21439 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-06 13:54:39 +00:00
parent c9bb9401c9
commit e123480aea
8 changed files with 4719 additions and 4640 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2796,7 +2796,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-06T12:33:26.861683+00:00", "generatedAt": "2026-10-06T13:52:10.355245+00:00",
"summary": { "summary": {
"activeBlockCount": 141, "activeBlockCount": 141,
"byGpuFramework": { "byGpuFramework": {

296
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-10-06T12:41:15.753345+00:00", "communityAttemptedAt": "2026-10-06T13:52:10.375897+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-10-06T12:41:15.753345+00:00", "communityUpdatedAt": "2026-10-06T13:52:10.375897+00:00",
"frameworkAttemptedAt": "2026-10-06T08:46:32.962057+00:00", "frameworkAttemptedAt": "2026-10-06T08:46:32.962057+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -434,121 +434,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-06T12:41:15.753345+00:00", "generatedAt": "2026-10-06T13:52:10.375897+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 989.25, "backlogHours": 970.638036809816,
"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": 1.5916516918808188, "qualityFactor": 1.4800817782418774,
"queueFactor": 0.9914855147015481, "queueFactor": 0.992826178698954,
"queueWeight": 0.9914855147015481, "queueWeight": 0.992826178698954,
"recentSuccess": 47, "recentSuccess": 48,
"recentSuccessRate": 0.29375, "recentSuccessRate": 0.294478527607362,
"recentTerminal": 160, "recentTerminal": 163,
"recentWilsonLowerBound": 0.22867364459504114, "recentWilsonLowerBound": 0.22988413694625084,
"running": 8, "running": 9,
"selectionWeight": 1.5780995969500435, "selectionWeight": 1.4694639360538357,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.666666666666668, "throughputPerHour": 27.166666666666668,
"waiting": 26380 "waiting": 26369
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1201.6666666666667, "backlogHours": 1145.0860927152316,
"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": 0.9629742636471292, "queueFactor": 0.9685144283629833,
"queueWeight": 0.9629742636471292, "queueWeight": 0.9685144283629833,
"recentSuccess": 51, "recentSuccess": 55,
"recentSuccessRate": 0.3541666666666667, "recentSuccessRate": 0.36423841059602646,
"recentTerminal": 144, "recentTerminal": 151,
"recentWilsonLowerBound": 0.2807687889835203, "recentWilsonLowerBound": 0.29173479472925495,
"running": 8, "running": 8,
"selectionWeight": 2.407435659117823, "selectionWeight": 2.4212860709074584,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.0, "throughputPerHour": 25.166666666666668,
"waiting": 28840 "waiting": 28818
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 114.73684210526316, "backlogHours": 105.21081081081081,
"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": 0.6388359728403867, "qualityFactor": 0.42180384984060826,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 35, "recentSuccess": 33,
"recentSuccessRate": 0.2046783625730994, "recentSuccessRate": 0.1783783783783784,
"recentTerminal": 171, "recentTerminal": 185,
"recentWilsonLowerBound": 0.15101066718447043, "recentWilsonLowerBound": 0.1299278067352906,
"running": 8, "running": 8,
"selectionWeight": 0.8304867646925028, "selectionWeight": 0.5483450047927908,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 28.5, "throughputPerHour": 30.833333333333332,
"waiting": 3270 "waiting": 3244
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1327.1666666666667, "backlogHours": 1137.2142857142858,
"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": 0.4635086060617766, "qualityFactor": 0.49762437750366295,
"queueFactor": 0.9487318109762511, "queueFactor": 0.969517092344306,
"queueWeight": 0.9487318109762511, "queueWeight": 0.969517092344306,
"recentSuccess": 15, "recentSuccess": 18,
"recentSuccessRate": 0.20833333333333334, "recentSuccessRate": 0.21428571428571427,
"recentTerminal": 72, "recentTerminal": 84,
"recentWilsonLowerBound": 0.1305194089904011, "recentWilsonLowerBound": 0.14006654921749653,
"running": 7, "running": 7,
"selectionWeight": 0.4397453592320671, "selectionWeight": 0.4824553395569966,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.0, "throughputPerHour": 14.0,
"waiting": 15926 "waiting": 15921
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 365.2992700729927, "backlogHours": 384.2307692307692,
"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": 0.9056141184812663, "qualityFactor": 0.7957538973393086,
"queueFactor": 1.1512906081797127, "queueFactor": 1.1408879546981925,
"queueWeight": 1.1512906081797127, "queueWeight": 1.1408879546981925,
"recentSuccess": 33, "recentSuccess": 31,
"recentSuccessRate": 0.24087591240875914, "recentSuccessRate": 0.23846153846153847,
"recentTerminal": 137, "recentTerminal": 130,
"recentWilsonLowerBound": 0.17696840103106276, "recentWilsonLowerBound": 0.17338273546709032,
"running": 8, "running": 7,
"selectionWeight": 1.0426250292424315, "selectionWeight": 0.9078660363785592,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.833333333333332, "throughputPerHour": 21.666666666666668,
"waiting": 8341 "waiting": 8325
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 43.61290322580645, "backlogHours": 42.20295983086681,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -557,197 +557,197 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 10, "recentSuccess": 14,
"recentSuccessRate": 0.021505376344086023, "recentSuccessRate": 0.02959830866807611,
"recentTerminal": 465, "recentTerminal": 473,
"recentWilsonLowerBound": 0.011722298946194337, "recentWilsonLowerBound": 0.01771134703499595,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 77.5, "throughputPerHour": 78.83333333333333,
"waiting": 3380 "waiting": 3327
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 122.3076923076923, "backlogHours": 116.45121951219512,
"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": 0.23355179511932275, "qualityFactor": 0.32174137152316806,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 40, "recentSuccess": 49,
"recentSuccessRate": 0.1282051282051282, "recentSuccessRate": 0.14939024390243902,
"recentTerminal": 312, "recentTerminal": 328,
"recentWilsonLowerBound": 0.09558031679393873, "recentWilsonLowerBound": 0.11488039275559753,
"running": 5, "running": 1,
"selectionWeight": 0.3036173336551196, "selectionWeight": 0.4182637829801185,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 52.0, "throughputPerHour": 54.666666666666664,
"waiting": 6360 "waiting": 6366
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2127.6818181818185, "backlogHours": 1910.326530612245,
"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": 1.1852146462918114, "qualityFactor": 0.8482810043894893,
"queueFactor": 0.8838860510051985, "queueFactor": 0.8969447142854403,
"queueWeight": 0.8838860510051985, "queueWeight": 0.8969447142854403,
"recentSuccess": 14, "recentSuccess": 14,
"recentSuccessRate": 0.3181818181818182, "recentSuccessRate": 0.2857142857142857,
"recentTerminal": 44, "recentTerminal": 49,
"recentWilsonLowerBound": 0.19999129931673565, "recentWilsonLowerBound": 0.1784943493972417,
"running": 2, "running": 2,
"selectionWeight": 1.0475946933043923, "selectionWeight": 0.7608611631158968,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 7.333333333333333, "throughputPerHour": 8.166666666666666,
"waiting": 15603 "waiting": 15601
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 307.5652173913044, "backlogHours": 300.1090909090909,
"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": 0.3705219133712646, "qualityFactor": 0.3547514558070931,
"queueFactor": 1.1813856726174559, "queueFactor": 1.1839679420813185,
"queueWeight": 1.1813856726174559, "queueWeight": 1.1839679420813185,
"recentSuccess": 27, "recentSuccess": 28,
"recentSuccessRate": 0.16770186335403728, "recentSuccessRate": 0.1696969696969697,
"recentTerminal": 161, "recentTerminal": 165,
"recentWilsonLowerBound": 0.11788901090974872, "recentWilsonLowerBound": 0.1200954330165454,
"running": 8, "running": 8,
"selectionWeight": 0.43772927984761817, "selectionWeight": 0.42001435108227586,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.833333333333332, "throughputPerHour": 27.5,
"waiting": 8253 "waiting": 8253
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 697.6235294117647, "backlogHours": 592.8,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "MetaX_c-500", "gpu": "MetaX_c-500",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 1.4341082323703036, "qualityFactor": 0.731878825182921,
"queueFactor": 1.0448143156600227, "queueFactor": 1.0690440156430236,
"queueWeight": 1.0448143156600227, "queueWeight": 1.0690440156430236,
"recentSuccess": 26, "recentSuccess": 24,
"recentSuccessRate": 0.3058823529411765, "recentSuccessRate": 0.24,
"recentTerminal": 85, "recentTerminal": 100,
"recentWilsonLowerBound": 0.21809243965848635, "recentWilsonLowerBound": 0.16691211265459965,
"running": 4, "running": 4,
"selectionWeight": 1.4983768113863836, "selectionWeight": 0.7824106782376484,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.166666666666666, "throughputPerHour": 16.666666666666668,
"waiting": 9883 "waiting": 9880
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1746.4, "backlogHours": 1438.6153846153848,
"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": 2.122711763790171, "qualityFactor": 1.9630585223493522,
"queueFactor": 0.9104596934768452, "queueFactor": 0.9359229803494772,
"queueWeight": 0.9104596934768452, "queueWeight": 0.9359229803494772,
"recentSuccess": 27, "recentSuccess": 32,
"recentSuccessRate": 0.36, "recentSuccessRate": 0.3516483516483517,
"recentTerminal": 75, "recentTerminal": 91,
"recentWilsonLowerBound": 0.26064766399338823, "recentWilsonLowerBound": 0.2613712913278969,
"running": 4, "running": 4,
"selectionWeight": 1.9326435018000925, "selectionWeight": 1.8372715828376465,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.5, "throughputPerHour": 15.166666666666666,
"waiting": 21830 "waiting": 21819
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 2088.2448979591836, "backlogHours": 1894.4444444444443,
"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": 0.25662482784256896, "qualityFactor": 0.2575354550194465,
"queueFactor": 0.8863700400604634, "queueFactor": 0.8980686473260635,
"queueWeight": 0.8863700400604634, "queueWeight": 0.8980686473260635,
"recentSuccess": 9, "recentSuccess": 10,
"recentSuccessRate": 0.1836734693877551, "recentSuccessRate": 0.18518518518518517,
"recentTerminal": 49, "recentTerminal": 54,
"recentWilsonLowerBound": 0.09976228838458356, "recentWilsonLowerBound": 0.10382574505942958,
"running": 2, "running": 2,
"selectionWeight": 0.22746455893532735, "selectionWeight": 0.2312845177278166,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.166666666666666, "throughputPerHour": 9.0,
"waiting": 17054 "waiting": 17050
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 997.2631578947368, "backlogHours": 1088.6206896551723,
"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": 0.9902864034279355, "queueFactor": 0.9758887879379217,
"queueWeight": 0.9902864034279355, "queueWeight": 0.9758887879379217,
"recentSuccess": 5, "recentSuccess": 3,
"recentSuccessRate": 0.05263157894736842, "recentSuccessRate": 0.034482758620689655,
"recentTerminal": 95, "recentTerminal": 87,
"recentWilsonLowerBound": 0.022687778480124217, "recentWilsonLowerBound": 0.011795606761416898,
"running": 16, "running": 16,
"selectionWeight": 0.04951432017139678, "selectionWeight": 0.04879443939689609,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 15.833333333333334, "throughputPerHour": 14.5,
"waiting": 15790 "waiting": 15785
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 879.6176470588235, "backlogHours": 879.6617647058823,
"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": 0.542355812211674, "qualityFactor": 0.325049734639516,
"queueFactor": 1.0091092623516837, "queueFactor": 1.0075914153826016,
"queueWeight": 1.0091092623516837, "queueWeight": 1.0075914153826016,
"recentSuccess": 27, "recentSuccess": 23,
"recentSuccessRate": 0.19852941176470587, "recentSuccessRate": 0.16911764705882354,
"recentTerminal": 136, "recentTerminal": 136,
"recentWilsonLowerBound": 0.14018035078929256, "recentWilsonLowerBound": 0.11541583950698799,
"running": 6, "running": 6,
"selectionWeight": 0.5472962735930706, "selectionWeight": 0.32751732219516894,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.666666666666668, "throughputPerHour": 22.666666666666668,
"waiting": 19938 "waiting": 19939
} }
}, },
"queueAttemptedAt": "2026-10-06T12:41:15.753345+00:00", "queueAttemptedAt": "2026-10-06T13:52:10.375897+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-06T12:41:15.753345+00:00", "queueUpdatedAt": "2026-10-06T13:52:10.375897+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",

5433
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

191
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-06T10:54:57.000923+00:00", "generatedAt": "2026-10-06T13:52:10.257937+00:00",
"lastSyncTime": "2026-10-06T10:54:56.760703+00:00", "lastSyncTime": "2026-10-06T13:52:09.946220+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2924,25 +2924,25 @@
"decisionSuccessRate": 0.0784, "decisionSuccessRate": 0.0784,
"decisionTotal": 51, "decisionTotal": 51,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 90, "ambiguous_runtime": 91,
"context_length": 9, "context_length": 9,
"framework_architecture_unsupported": 37, "framework_architecture_unsupported": 37,
"memory_capacity": 1, "memory_capacity": 1,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"参数/模板问题": 8 "参数/模板问题": 8
}, },
"failureCount": 146, "failureCount": 147,
"failureRate": 0.9733, "failureRate": 0.9735,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 4, "successCount": 4,
"successRate": 0.0267, "successRate": 0.0265,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 150, "total": 151,
"unresolvedFailureCount": 98 "unresolvedFailureCount": 99
}, },
"Ascend_910-b3|vllm|text-generation": { "Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 71, "attributableFailureCount": 71,
@@ -3109,13 +3109,13 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 32, "decisionTotal": 32,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 100, "ambiguous_runtime": 101,
"framework_architecture_unsupported": 31, "framework_architecture_unsupported": 31,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"repository_structure": 1, "repository_structure": 1,
"参数/模板问题": 6 "参数/模板问题": 6
}, },
"failureCount": 139, "failureCount": 140,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"pendingCount": 0, "pendingCount": 0,
@@ -3125,8 +3125,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b4", "targetGpu": "Ascend_910-b4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 139, "total": 140,
"unresolvedFailureCount": 106 "unresolvedFailureCount": 107
}, },
"Ascend_910-b4|vllm|text-generation": { "Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 205, "attributableFailureCount": 205,
@@ -3258,23 +3258,23 @@
"decisionSuccessRate": 0.2308, "decisionSuccessRate": 0.2308,
"decisionTotal": 65, "decisionTotal": 65,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 13, "ambiguous_runtime": 14,
"framework_architecture_unsupported": 36, "framework_architecture_unsupported": 36,
"model_load": 12, "model_load": 12,
"tokenizer_compatibility": 2 "tokenizer_compatibility": 2
}, },
"failureCount": 63, "failureCount": 64,
"failureRate": 0.8077, "failureRate": 0.8101,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 15, "successCount": 15,
"successRate": 0.1923, "successRate": 0.1899,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 78, "total": 79,
"unresolvedFailureCount": 13 "unresolvedFailureCount": 14
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 695, "attributableFailureCount": 695,
@@ -5503,7 +5503,7 @@
"decisionSuccessRate": 0.0279, "decisionSuccessRate": 0.0279,
"decisionTotal": 3769, "decisionTotal": 3769,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1599, "ambiguous_runtime": 1600,
"architecture_compatibility": 112, "architecture_compatibility": 112,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 94, "backend_operator": 94,
@@ -5517,15 +5517,15 @@
"tokenizer_compatibility": 420, "tokenizer_compatibility": 420,
"参数/模板问题": 50 "参数/模板问题": 50
}, },
"failureCount": 6191, "failureCount": 6192,
"failureRate": 0.9833, "failureRate": 0.9833,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 878, "platformFailureCount": 878,
"successCount": 105, "successCount": 105,
"successRate": 0.0167, "successRate": 0.0167,
"total": 6296, "total": 6297,
"unresolvedFailureCount": 1649 "unresolvedFailureCount": 1650
}, },
"vllm-customized": { "vllm-customized": {
"attributableFailureCount": 15, "attributableFailureCount": 15,
@@ -5652,7 +5652,7 @@
"decisionSuccessRate": 0.0625, "decisionSuccessRate": 0.0625,
"decisionTotal": 160, "decisionTotal": 160,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 204, "ambiguous_runtime": 206,
"backend_operator": 15, "backend_operator": 15,
"context_length": 9, "context_length": 9,
"framework_architecture_unsupported": 93, "framework_architecture_unsupported": 93,
@@ -5664,18 +5664,18 @@
"tokenizer_compatibility": 2, "tokenizer_compatibility": 2,
"参数/模板问题": 29 "参数/模板问题": 29
}, },
"failureCount": 386, "failureCount": 388,
"failureRate": 0.9747, "failureRate": 0.9749,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 3, "platformFailureCount": 3,
"successCount": 10, "successCount": 10,
"successRate": 0.0253, "successRate": 0.0251,
"total": 396, "total": 398,
"unresolvedFailureCount": 233 "unresolvedFailureCount": 235
} }
}, },
"generatedAt": "2026-10-06T10:54:56.983561+00:00", "generatedAt": "2026-10-06T13:52:10.241667+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 119, "attributableFailureCount": 119,
@@ -5683,7 +5683,7 @@
"decisionSuccessRate": 0.156, "decisionSuccessRate": 0.156,
"decisionTotal": 141, "decisionTotal": 141,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 159, "ambiguous_runtime": 160,
"context_length": 9, "context_length": 9,
"framework_architecture_unsupported": 104, "framework_architecture_unsupported": 104,
"memory_capacity": 2, "memory_capacity": 2,
@@ -5694,15 +5694,15 @@
"日志缺失": 3, "日志缺失": 3,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 349, "failureCount": 350,
"failureRate": 0.9407, "failureRate": 0.9409,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 22, "successCount": 22,
"successRate": 0.0593, "successRate": 0.0591,
"total": 371, "total": 372,
"unresolvedFailureCount": 229 "unresolvedFailureCount": 230
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"attributableFailureCount": 331, "attributableFailureCount": 331,
@@ -5710,7 +5710,7 @@
"decisionSuccessRate": 0.162, "decisionSuccessRate": 0.162,
"decisionTotal": 395, "decisionTotal": 395,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 250, "ambiguous_runtime": 251,
"context_length": 1, "context_length": 1,
"framework_architecture_unsupported": 187, "framework_architecture_unsupported": 187,
"memory_capacity": 19, "memory_capacity": 19,
@@ -5722,15 +5722,15 @@
"日志缺失": 14, "日志缺失": 14,
"验证失败": 175 "验证失败": 175
}, },
"failureCount": 1042, "failureCount": 1043,
"failureRate": 0.9421, "failureRate": 0.9422,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 3, "platformFailureCount": 3,
"successCount": 64, "successCount": 64,
"successRate": 0.0579, "successRate": 0.0578,
"total": 1106, "total": 1107,
"unresolvedFailureCount": 708 "unresolvedFailureCount": 709
}, },
"Biren_166m": { "Biren_166m": {
"attributableFailureCount": 193, "attributableFailureCount": 193,
@@ -5738,7 +5738,7 @@
"decisionSuccessRate": 0.1147, "decisionSuccessRate": 0.1147,
"decisionTotal": 218, "decisionTotal": 218,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 266, "ambiguous_runtime": 267,
"backend_operator": 4, "backend_operator": 4,
"context_length": 10, "context_length": 10,
"framework_architecture_unsupported": 125, "framework_architecture_unsupported": 125,
@@ -5752,15 +5752,15 @@
"日志缺失": 62, "日志缺失": 62,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 764, "failureCount": 765,
"failureRate": 0.9683, "failureRate": 0.9684,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 2, "platformFailureCount": 2,
"successCount": 25, "successCount": 25,
"successRate": 0.0317, "successRate": 0.0316,
"total": 789, "total": 790,
"unresolvedFailureCount": 569 "unresolvedFailureCount": 570
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"attributableFailureCount": 759, "attributableFailureCount": 759,
@@ -6397,9 +6397,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4 "ambiguous_runtime": 5
}, },
"failureCount": 4, "failureCount": 5,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"modelType": "lfm2", "modelType": "lfm2",
@@ -6411,8 +6411,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 4, "total": 5,
"unresolvedFailureCount": 4 "unresolvedFailureCount": 5
}, },
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|awq": { "Ascend_910-b3|vllm_tokenizer_patch|text-generation|llama|awq": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -7799,9 +7799,9 @@
"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_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"modelType": "lfm2", "modelType": "lfm2",
@@ -7813,8 +7813,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b4", "targetGpu": "Ascend_910-b4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 6, "total": 7,
"unresolvedFailureCount": 6 "unresolvedFailureCount": 7
}, },
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq": { "Ascend_910-b4|vllm_tokenizer_patch|text-generation|llama|awq": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -9864,6 +9864,29 @@
"total": 2, "total": 2,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 2
}, },
"Biren_166m|vllm|text-generation|gemma3|none": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|gemma4_unified|compressed-tensors": { "Biren_166m|vllm|text-generation|gemma4_unified|compressed-tensors": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -29253,9 +29276,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1 "ambiguous_runtime": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 30, "loadSizeLog2Bucket": 30,
@@ -29268,8 +29291,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 2
}, },
"Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none|31": { "Ascend_910-b3|vllm_tokenizer_patch|text-generation|lfm2|none|31": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -31576,9 +31599,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1 "ambiguous_runtime": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 30, "loadSizeLog2Bucket": 30,
@@ -31591,8 +31614,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b4", "targetGpu": "Ascend_910-b4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 2
}, },
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|31": { "Ascend_910-b4|vllm_tokenizer_patch|text-generation|lfm2|none|31": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -35072,6 +35095,30 @@
"total": 2, "total": 2,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 2
}, },
"Biren_166m|vllm|text-generation|gemma3|none|35": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 35,
"modelType": "gemma3",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Biren_166m|vllm|text-generation|gemma4_unified|compressed-tensors|33": { "Biren_166m|vllm|text-generation|gemma4_unified|compressed-tensors|33": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -57374,15 +57421,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17334, "terminalRecords": 17337,
"totalRecords": 17558, "totalRecords": 17561,
"totals": { "totals": {
"attributableFailureCount": 6232, "attributableFailureCount": 6232,
"decisionFailureRate": 0.8644, "decisionFailureRate": 0.8644,
"decisionSuccessRate": 0.1356, "decisionSuccessRate": 0.1356,
"decisionTotal": 7210, "decisionTotal": 7210,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4545, "ambiguous_runtime": 4548,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 129, "backend_operator": 129,
@@ -57398,15 +57445,15 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16356, "failureCount": 16359,
"failureRate": 0.9436, "failureRate": 0.9436,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 951, "platformFailureCount": 951,
"successCount": 978, "successCount": 978,
"successRate": 0.0564, "successRate": 0.0564,
"total": 17334, "total": 17337,
"unresolvedFailureCount": 9173 "unresolvedFailureCount": 9176
}, },
"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。",
@@ -57415,14 +57462,14 @@
"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。",
@@ -57466,6 +57513,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17558, "summarizedRecords": 17561,
"version": 1 "version": 1
} }

1334
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2082
.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": "72945895db81c2fac451a18bde4412834b992b8e2814b679cabbe63d612504b6", ".modelhub_state/architecture_compatibility_blacklist.json": "8387025c00126983a079b521a7b475cf87acd026f593710d45142742bcf74301",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "32a96c8d510e146bfd44b06e753c9c79e767da65265b9aad1599d44106f8d0b4", ".modelhub_state/market_intelligence.json": "0e0009dbca721d561af041aff4b1090567c1c3de97bca84ddad6c6bc891e5be2",
".modelhub_state/official_capabilities.json": "077aad052850fe32331a10f8ce96b5896bf15fcdca4ebd123812223cafa0817c", ".modelhub_state/official_capabilities.json": "d281872be654c2b28473e51a0de46ea6950fd312621d0c0c6e443a2e9c81a40c",
".modelhub_state/outcome_checkpoint.json": "72eb5187ead42e54cf74e34002fb118c15804cc7114eaed2fd5414fa44e97a11", ".modelhub_state/outcome_checkpoint.json": "3219ee23fc6332b68e0909472b775cec84675017a62f01162788052dcdb8437c",
".modelhub_state/queue_cleanup_latest.json": "5a0303e8316fcab30a4e922547230f80795528b823c5599adce914d800fab218", ".modelhub_state/queue_cleanup_latest.json": "5a0303e8316fcab30a4e922547230f80795528b823c5599adce914d800fab218",
".modelhub_state/recent_outcomes.jsonl": "66f65405defcf850f044e43e54c3dc291f18521f309cb9962d861b493cb049ac", ".modelhub_state/recent_outcomes.jsonl": "66f65405defcf850f044e43e54c3dc291f18521f309cb9962d861b493cb049ac",
".modelhub_state/recovery_active_tasks.jsonl": "ee0dad4fb66f1f6c9291930ddb3ad20ba131a8d338916918fd96694f000cc627", ".modelhub_state/recovery_active_tasks.jsonl": "1dcf39696e698e272d7820db7d2cadf64d972a5d30c3d1f9216f5f8e1821a5cb",
".modelhub_state/recovery_intents.jsonl": "d35271f4935da912fe8ad9bb1d88a1f5cf40bcb9038b7f5581f6034368a98754", ".modelhub_state/recovery_intents.jsonl": "cc6657b9d5cc2dc2ac33f9c623043dc328854a3dc4875150c65b24410dd128d5",
".modelhub_state/routing_intelligence.json": "a648a147d02925142f95b55d31b14142867452cec76d320d33c1e0a1c1c7aec5", ".modelhub_state/routing_intelligence.json": "a648a147d02925142f95b55d31b14142867452cec76d320d33c1e0a1c1c7aec5",
".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": "4b2bb9ff22e275717fa8280c85f062d253324648902ce0c82c1ee6b7c5eef2e2", "ledger/submissions.jsonl": "4b2bb9ff22e275717fa8280c85f062d253324648902ce0c82c1ee6b7c5eef2e2",
"outcomes/submissions.jsonl": "282b55897a432254686eb59e14f5ec67f0f080b88a8562de69e09b6989da71a7" "outcomes/submissions.jsonl": "de0866bea5cc339fe2e4df3778ad25fd4f88212b48e74d1dcaa3f92192ca1bfa"
}, },
"generation": 21438, "generation": 21439,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-06T13:52:04.772079+00:00", "updatedAt": "2026-10-06T13:54:39.804373+00:00",
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2" "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
} }

3
outcomes/submissions.jsonl
View File

@@ -138,7 +138,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063090+00:00", "modelId": "rengensheng/Ternary-Bonsai-2-27B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "87e2d06ee2cbb5d6c759a240df54c78746d706859f9a364e78515c8f28fcc1fd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629246976, "estimatedRequiredGiB": 8.757, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7835440764, "modelscopeLicense": "apache-2.0", "modelscopeParams": 460730096, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7835440764}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.174402+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947147", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063090+00:00", "modelId": "rengensheng/Ternary-Bonsai-2-27B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "87e2d06ee2cbb5d6c759a240df54c78746d706859f9a364e78515c8f28fcc1fd", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 629246976, "estimatedRequiredGiB": 8.757, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 7835440764, "modelscopeLicense": "apache-2.0", "modelscopeParams": 460730096, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:ternary", "custom_tag:2-bit", "custom_tag:gguf", "custom_tag:llama-cpp", "custom_tag:cuda", "custom_tag:metal", "custom_tag:on-device", "custom_tag:hybrid-attention", "custom_tag:prismml", "custom_tag:bonsai", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7835440764}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.174402+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947147", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063052+00:00", "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "a0e7803b6725f735d0804da4c3b2af6ac5c0db91adef3494b64f29a43c4cded8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.177348+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947146", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063052+00:00", "modelId": "ProCreations/Ternary-Bonsai-2-27B-MTP", "modelProfile": {"architectures": [], "configFingerprint": "a0e7803b6725f735d0804da4c3b2af6ac5c0db91adef3494b64f29a43c4cded8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7657489728, "estimatedRequiredGiB": 9.567, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8560440422, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:qwen3_5", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:bonsai", "custom_tag:ternary", "custom_tag:blackwell", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8560440422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.177348+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947146", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063105+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "ed217196ebf72901791ffd67a7627878fd8f0fd29fa1291cafd8f6b32c01507f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.175900+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947142", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-19T13:02:10.063105+00:00", "modelId": "soyaakinohara/Spark-X2.5-4B-Heretic-jp-gguf", "modelProfile": {"architectures": [], "configFingerprint": "ed217196ebf72901791ffd67a7627878fd8f0fd29fa1291cafd8f6b32c01507f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021184, "estimatedRequiredGiB": 24.098, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 21562254019, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark2_5", "custom_tag:uncensored", "custom_tag:refusal-removed", "custom_tag:quantized", "custom_tag:bf16", "custom_tag:q8_0", "custom_tag:q6_k", "custom_tag:q5_k_m", "custom_tag:q4_k_m", "custom_tag:tool-calling", "custom_tag:japanese", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21562254019}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-19T04:58:16.175900+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4947142", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647557+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409935, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.040710+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969021", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647466+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T02:52:51.140009+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969028", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647466+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "2026-09-20T02:52:51.140009+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4969028", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647505+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60671749474, "estimatedRequiredGiB": 67.825, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60688949222, "modelscopeLicense": "other", "modelscopeParams": 15303312058, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:jangtq-prestack", "custom_tag:minimax", "custom_tag:minimax-m2", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:2bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60688949222}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.187054+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969030", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:00:25.647505+00:00", "modelId": "JANGQ-AI/MiniMax-M2.7-JANGTQ", "modelProfile": {"architectures": ["MiniMaxM2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 60671749474, "estimatedRequiredGiB": 67.825, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "minimax_m2", "modelscopeFileSize": 60688949222, "modelscopeLicense": "other", "modelscopeParams": 15303312058, "modelscopeTags": ["license:other", "model_type:minimax_m2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:jangtq", "custom_tag:jangtq-prestack", "custom_tag:minimax", "custom_tag:minimax-m2", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:2bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 60688949222}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.187054+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969030", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647403+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.852389+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969067", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:00:25.647403+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T02:52:51.852389+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969067", "taskType": "text-generation", "verifyResult": null}
@@ -146,10 +145,8 @@
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:10:38.766358+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-20T03:09:17.840209+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969321", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T11:10:38.766358+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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": "2026-09-20T03:09:17.840209+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969321", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766033+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.555119+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969364", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T11:10:38.766033+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:09:18.555119+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4969364", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600185+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-20T11:30:54.600185+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:24.241562+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4969620", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.599986+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": 1248409935, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.252209+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969648", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600049+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": "2026-09-20T03:25:32.237107+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969645", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T11:30:54.600049+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "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": "2026-09-20T03:25:32.237107+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969645", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599773+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.763321+00:00", "targetGpu": "MetaX_c-500", "taskId": "4969808", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599773+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.763321+00:00", "targetGpu": "MetaX_c-500", "taskId": "4969808", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671009+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.141735+00:00", "targetGpu": "Biren_166m", "taskId": "4970017", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671002+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": 1248409935, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.545556+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970035", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671002+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": 1248409935, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409935}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:41:49.545556+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970035", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671271+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-09-20T03:41:49.554113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-20T12:01:00.671271+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-09-20T03:41:49.554113+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4970036", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671248+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-09-20T03:53:59.224352+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970246", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671248+00:00", "modelId": "inceptionai/Jais-2-8B-Chat", "modelProfile": {"architectures": ["Jais2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16180861064, "estimatedRequiredGiB": 18.097, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": "2026-09-20T03:53:59.224352+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4970246", "taskType": "text-generation", "verifyResult": null}