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

state: generation 17768 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-28 06:19:55 +00:00
parent c03c0faac9
commit 2f3dc9a8e1
8 changed files with 1623 additions and 1624 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -3280,7 +3280,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-28T06:05:44.466115+00:00", "generatedAt": "2026-09-28T06:15:43.831808+00:00",
"summary": { "summary": {
"activeBlockCount": 165, "activeBlockCount": 165,
"byGpuFramework": { "byGpuFramework": {

252
.modelhub_state/market_intelligence.json
View File

@@ -396,99 +396,99 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-28T06:14:40.868987+00:00", "generatedAt": "2026-09-28T06:17:46.768768+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1710.2376237623764, "backlogHours": 1629.3396226415093,
"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": 2.2928906994568936, "qualityFactor": 2.3252615515336874,
"queueFactor": 0.904405179810237, "queueFactor": 0.9123912979109076,
"queueWeight": 0.904405179810237, "queueWeight": 0.9123912979109076,
"recentSuccess": 48, "recentSuccess": 49,
"recentSuccessRate": 0.4752475247524752, "recentSuccessRate": 0.46226415094339623,
"recentTerminal": 101, "recentTerminal": 106,
"recentWilsonLowerBound": 0.3805571262165129, "recentWilsonLowerBound": 0.37033458798877916,
"running": 8, "running": 8,
"selectionWeight": 2.073702225327532, "selectionWeight": 2.121548404986152,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.833333333333332, "throughputPerHour": 17.666666666666668,
"waiting": 28789 "waiting": 28785
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 144.66315789473683, "backlogHours": 143.81151832460733,
"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": 0.13202049554810352, "qualityFactor": 0.12764415610320898,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 28, "recentSuccess": 27,
"recentSuccessRate": 0.14736842105263157, "recentSuccessRate": 0.14136125654450263,
"recentTerminal": 190, "recentTerminal": 191,
"recentWilsonLowerBound": 0.1039682587715899, "recentWilsonLowerBound": 0.09900405189480148,
"running": 9, "running": 9,
"selectionWeight": 0.1716266442125346, "selectionWeight": 0.16593740293417167,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 31.666666666666668, "throughputPerHour": 31.833333333333332,
"waiting": 4581 "waiting": 4578
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1430.2153846153844, "backlogHours": 1408.5454545454545,
"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": 0.3903565733696901, "qualityFactor": 0.40581047337041104,
"queueFactor": 0.9289905423686096, "queueFactor": 0.9325395233025158,
"queueWeight": 0.9289905423686096, "queueWeight": 0.9325395233025158,
"recentSuccess": 17, "recentSuccess": 17,
"recentSuccessRate": 0.26153846153846155, "recentSuccessRate": 0.25757575757575757,
"recentTerminal": 65, "recentTerminal": 66,
"recentWilsonLowerBound": 0.17018055060319134, "recentWilsonLowerBound": 0.1674870734589668,
"running": 7, "running": 7,
"selectionWeight": 0.3626375648118603, "selectionWeight": 0.37843430538801137,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.833333333333334, "throughputPerHour": 11.0,
"waiting": 15494 "waiting": 15494
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 499.44444444444446, "backlogHours": 513.6,
"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": 0.4302532996117326, "qualityFactor": 0.44665065124378656,
"queueFactor": 1.0877984395232363, "queueFactor": 1.0848985407374252,
"queueWeight": 1.0877984395232363, "queueWeight": 1.0848985407374252,
"recentSuccess": 27, "recentSuccess": 26,
"recentSuccessRate": 0.25, "recentSuccessRate": 0.24761904761904763,
"recentTerminal": 108, "recentTerminal": 105,
"recentWilsonLowerBound": 0.17787718518702555, "recentWilsonLowerBound": 0.17494869705401506,
"running": 7, "running": 7,
"selectionWeight": 0.46802886791736614, "selectionWeight": 0.48457063975380466,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.0, "throughputPerHour": 17.5,
"waiting": 8990 "waiting": 8988
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 34.16230366492147, "backlogHours": 33.65552699228792,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -497,169 +497,169 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 22, "recentSuccess": 23,
"recentSuccessRate": 0.05759162303664921, "recentSuccessRate": 0.05912596401028278,
"recentTerminal": 382, "recentTerminal": 389,
"recentWilsonLowerBound": 0.038336646873171426, "recentWilsonLowerBound": 0.03971820376292673,
"running": 27, "running": 25,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 63.666666666666664, "throughputPerHour": 64.83333333333333,
"waiting": 2175 "waiting": 2182
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 91.87261146496814, "backlogHours": 89.83125,
"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": 0.17208108983569842, "qualityFactor": 0.1969265815875907,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 48, "recentSuccess": 50,
"recentSuccessRate": 0.15286624203821655, "recentSuccessRate": 0.15625,
"recentTerminal": 314, "recentTerminal": 320,
"recentWilsonLowerBound": 0.11727764062037702, "recentWilsonLowerBound": 0.12057171165892638,
"running": 4, "running": 14,
"selectionWeight": 0.22370541678640796, "selectionWeight": 0.2560045560638679,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 52.333333333333336, "throughputPerHour": 53.333333333333336,
"waiting": 4808 "waiting": 4791
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2214.9545454545455, "backlogHours": 2215.090909090909,
"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": 1.1389085783355763, "qualityFactor": 0.8777370410069757,
"queueFactor": 0.8699950602365154, "queueFactor": 0.8713129003566186,
"queueWeight": 0.8699950602365154, "queueWeight": 0.8713129003566186,
"recentSuccess": 18, "recentSuccess": 16,
"recentSuccessRate": 0.4090909090909091, "recentSuccessRate": 0.36363636363636365,
"recentTerminal": 44, "recentTerminal": 44,
"recentWilsonLowerBound": 0.27687643879006824, "recentWilsonLowerBound": 0.23783334127491426,
"running": 2, "running": 2,
"selectionWeight": 0.9908448372129439, "selectionWeight": 0.7647836069502243,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 7.333333333333333, "throughputPerHour": 7.333333333333333,
"waiting": 16243 "waiting": 16244
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 532.0, "backlogHours": 517.4594594594595,
"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": 0.4302532996117326, "qualityFactor": 0.4351869250225999,
"queueFactor": 1.0775433837372372, "queueFactor": 1.0836809219102932,
"queueWeight": 1.0775433837372372, "queueWeight": 1.0836809219102932,
"recentSuccess": 27, "recentSuccess": 27,
"recentSuccessRate": 0.25, "recentSuccessRate": 0.24324324324324326,
"recentTerminal": 108, "recentTerminal": 111,
"recentWilsonLowerBound": 0.17787718518702555, "recentWilsonLowerBound": 0.17289320485810214,
"running": 8, "running": 9,
"selectionWeight": 0.46361659632773766, "selectionWeight": 0.4716037681117967,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.0, "throughputPerHour": 18.5,
"waiting": 9576 "waiting": 9573
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 642.1836734693878, "backlogHours": 617.0,
"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": 0.6504003964762635, "qualityFactor": 0.762713644476857,
"queueFactor": 1.0475448363935884, "queueFactor": 1.0554559261357035,
"queueWeight": 1.0475448363935884, "queueWeight": 1.0554559261357035,
"recentSuccess": 29, "recentSuccess": 31,
"recentSuccessRate": 0.29591836734693877, "recentSuccessRate": 0.30392156862745096,
"recentTerminal": 98, "recentTerminal": 102,
"recentWilsonLowerBound": 0.21463049371609197, "recentWilsonLowerBound": 0.223122897734759,
"running": 4, "running": 4,
"selectionWeight": 0.6813235769170525, "selectionWeight": 0.8050106360076588,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.333333333333332, "throughputPerHour": 17.0,
"waiting": 10489 "waiting": 10489
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2047.59375, "backlogHours": 1985.5454545454545,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Mthreads_s4000", "gpu": "Mthreads_s4000",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.8803085909752258, "queueFactor": 0.8857290773601232,
"queueWeight": 0.8803085909752258, "queueWeight": 0.8857290773601232,
"recentSuccess": 33, "recentSuccess": 33,
"recentSuccessRate": 0.515625, "recentSuccessRate": 0.5,
"recentTerminal": 64, "recentTerminal": 66,
"recentWilsonLowerBound": 0.39581392243999036, "recentWilsonLowerBound": 0.38273484399489194,
"running": 4, "running": 4,
"selectionWeight": 2.2007714774380647, "selectionWeight": 2.214322693400308,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.666666666666666, "throughputPerHour": 11.0,
"waiting": 21841 "waiting": 21841
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 4018.7999999999997, "backlogHours": 3588.2142857142853,
"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": 0.7867910104423531, "qualityFactor": 0.8601438739462683,
"queueFactor": 0.7956224891291596, "queueFactor": 0.8104964587707507,
"queueWeight": 0.7956224891291596, "queueWeight": 0.8104964587707507,
"recentSuccess": 10, "recentSuccess": 11,
"recentSuccessRate": 0.4, "recentSuccessRate": 0.39285714285714285,
"recentTerminal": 25, "recentTerminal": 28,
"recentWilsonLowerBound": 0.23403057664190918, "recentWilsonLowerBound": 0.23565451827580033,
"running": 2, "running": 2,
"selectionWeight": 0.6259886221525915, "selectionWeight": 0.6971435638668055,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 4.166666666666667, "throughputPerHour": 4.666666666666667,
"waiting": 16745 "waiting": 16745
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 875.2727272727273, "backlogHours": 884.2040816326531,
"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": 0.38273319227006164, "qualityFactor": 0.3760283799943317,
"queueFactor": 1.0, "queueFactor": 1.0,
"queueWeight": 1.0, "queueWeight": 1.0,
"recentSuccess": 24, "recentSuccess": 23,
"recentSuccessRate": 0.24242424242424243, "recentSuccessRate": 0.23469387755102042,
"recentTerminal": 99, "recentTerminal": 98,
"recentWilsonLowerBound": 0.16866173936129494, "recentWilsonLowerBound": 0.16178365590883514,
"running": 17, "running": 16,
"selectionWeight": 0.38273319227006164, "selectionWeight": 0.3760283799943317,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.5, "throughputPerHour": 16.333333333333332,
"waiting": 14442 "waiting": 14442
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
@@ -670,24 +670,24 @@
"gpu": "hygon_k100-ai", "gpu": "hygon_k100-ai",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 6, "maxConcurrentTasks": 6,
"qualityFactor": 0.23337522418597198, "qualityFactor": 0.32134505422744797,
"queueFactor": 0.9760739494321284, "queueFactor": 0.9775615016049631,
"queueWeight": 0.9760739494321284, "queueWeight": 0.9775615016049631,
"recentSuccess": 21, "recentSuccess": 23,
"recentSuccessRate": 0.2, "recentSuccessRate": 0.21904761904761905,
"recentTerminal": 105, "recentTerminal": 105,
"recentWilsonLowerBound": 0.13469807905069028, "recentWilsonLowerBound": 0.15063031032976165,
"running": 6, "running": 6,
"selectionWeight": 0.22779147677081005, "selectionWeight": 0.31413455374391236,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": true,
"throughputPerHour": 17.5, "throughputPerHour": 17.5,
"waiting": 18001 "waiting": 18001
} }
}, },
"queueAttemptedAt": "2026-09-28T06:07:38.164498+00:00", "queueAttemptedAt": "2026-09-28T06:17:46.768768+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-28T06:07:38.164498+00:00", "queueUpdatedAt": "2026-09-28T06:17:46.768768+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": "2026-09-28T06:14:40.868987+00:00", "catalogUpdatedAt": "2026-09-28T06:17:46.768768+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-09-28T06:14:40.868987+00:00", "generatedAt": "2026-09-28T06:17:46.768768+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6541,6 +6541,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-09-28T06:14:40.868987+00:00", "taskTreeUpdatedAt": "2026-09-28T06:17:46.768768+00:00",
"version": 1 "version": 1
} }

96
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-28T05:20:23.829117+00:00", "generatedAt": "2026-09-28T06:15:43.739437+00:00",
"lastSyncTime": "2026-09-28T05:20:23.558009+00:00", "lastSyncTime": "2026-09-28T06:15:43.444013+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -5422,18 +5422,18 @@
"unresolvedFailureCount": 296 "unresolvedFailureCount": 296
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 113, "attributableFailureCount": 114,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 113, "decisionTotal": 114,
"failureBreakdown": { "failureBreakdown": {
"backend_operator": 9, "backend_operator": 9,
"framework_architecture_unsupported": 14, "framework_architecture_unsupported": 14,
"platform_infrastructure": 20, "platform_infrastructure": 20,
"tokenizer_compatibility": 90, "tokenizer_compatibility": 91,
"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_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -5443,7 +5443,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 139, "total": 140,
"unresolvedFailureCount": 6 "unresolvedFailureCount": 6
}, },
"Sunrise_pt-200-x1|vllm|text-generation": { "Sunrise_pt-200-x1|vllm|text-generation": {
@@ -6100,10 +6100,10 @@
"unresolvedFailureCount": 25 "unresolvedFailureCount": 25
}, },
"vllm_fix_tokenizer": { "vllm_fix_tokenizer": {
"attributableFailureCount": 150, "attributableFailureCount": 151,
"decisionFailureRate": 0.9677, "decisionFailureRate": 0.9679,
"decisionSuccessRate": 0.0323, "decisionSuccessRate": 0.0321,
"decisionTotal": 155, "decisionTotal": 156,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 320, "ambiguous_runtime": 320,
"backend_operator": 9, "backend_operator": 9,
@@ -6111,17 +6111,17 @@
"memory_capacity": 10, "memory_capacity": 10,
"model_load": 9, "model_load": 9,
"platform_infrastructure": 20, "platform_infrastructure": 20,
"tokenizer_compatibility": 90, "tokenizer_compatibility": 91,
"参数/模板问题": 13 "参数/模板问题": 13
}, },
"failureCount": 503, "failureCount": 504,
"failureRate": 0.9902, "failureRate": 0.9902,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 20, "platformFailureCount": 20,
"successCount": 5, "successCount": 5,
"successRate": 0.0098, "successRate": 0.0098,
"total": 508, "total": 509,
"unresolvedFailureCount": 333 "unresolvedFailureCount": 333
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
@@ -6153,7 +6153,7 @@
"unresolvedFailureCount": 197 "unresolvedFailureCount": 197
} }
}, },
"generatedAt": "2026-09-28T05:20:23.816680+00:00", "generatedAt": "2026-09-28T06:15:43.725831+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 102, "attributableFailureCount": 102,
@@ -6488,10 +6488,10 @@
"unresolvedFailureCount": 299 "unresolvedFailureCount": 299
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"attributableFailureCount": 747, "attributableFailureCount": 748,
"decisionFailureRate": 0.8893, "decisionFailureRate": 0.8894,
"decisionSuccessRate": 0.1107, "decisionSuccessRate": 0.1106,
"decisionTotal": 840, "decisionTotal": 841,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 162, "ambiguous_runtime": 162,
"architecture_compatibility": 44, "architecture_compatibility": 44,
@@ -6502,18 +6502,18 @@
"platform_infrastructure": 227, "platform_infrastructure": 227,
"repository_structure": 83, "repository_structure": 83,
"runtime_memory": 1, "runtime_memory": 1,
"tokenizer_compatibility": 272, "tokenizer_compatibility": 273,
"参数/模板问题": 228, "参数/模板问题": 228,
"验证失败": 32 "验证失败": 32
}, },
"failureCount": 1396, "failureCount": 1397,
"failureRate": 0.9375, "failureRate": 0.9376,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 227, "platformFailureCount": 227,
"successCount": 93, "successCount": 93,
"successRate": 0.0625, "successRate": 0.0624,
"total": 1489, "total": 1490,
"unresolvedFailureCount": 422 "unresolvedFailureCount": 422
}, },
"Vastai_va16": { "Vastai_va16": {
@@ -20655,14 +20655,14 @@
"unresolvedFailureCount": 3 "unresolvedFailureCount": 3
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 2, "attributableFailureCount": 3,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"tokenizer_compatibility": 2 "tokenizer_compatibility": 3
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelType": "gemma2", "modelType": "gemma2",
@@ -20674,7 +20674,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors": {
@@ -48297,14 +48297,14 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|33": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gemma2|compressed-tensors|33": {
"attributableFailureCount": 1, "attributableFailureCount": 2,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 2,
"failureBreakdown": { "failureBreakdown": {
"tokenizer_compatibility": 1 "tokenizer_compatibility": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 33, "loadSizeLog2Bucket": 33,
@@ -48317,7 +48317,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors|35": { "Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|gpt_oss|compressed-tensors|35": {
@@ -51639,13 +51639,13 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17071, "terminalRecords": 17072,
"totalRecords": 17292, "totalRecords": 17293,
"totals": { "totals": {
"attributableFailureCount": 6118, "attributableFailureCount": 6119,
"decisionFailureRate": 0.8636, "decisionFailureRate": 0.8637,
"decisionSuccessRate": 0.1364, "decisionSuccessRate": 0.1363,
"decisionTotal": 7084, "decisionTotal": 7085,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4426, "ambiguous_runtime": 4426,
"architecture_compatibility": 212, "architecture_compatibility": 212,
@@ -51658,19 +51658,19 @@
"platform_infrastructure": 938, "platform_infrastructure": 938,
"repository_structure": 742, "repository_structure": 742,
"runtime_memory": 100, "runtime_memory": 100,
"tokenizer_compatibility": 680, "tokenizer_compatibility": 681,
"参数/模板问题": 3228, "参数/模板问题": 3228,
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16105, "failureCount": 16106,
"failureRate": 0.9434, "failureRate": 0.9434,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 938, "platformFailureCount": 938,
"successCount": 966, "successCount": 966,
"successRate": 0.0566, "successRate": 0.0566,
"total": 17071, "total": 17072,
"unresolvedFailureCount": 9049 "unresolvedFailureCount": 9049
}, },
"warnings": [ "warnings": [
@@ -51679,15 +51679,15 @@
"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 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。",
"GPU Mthreads_s4000 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 Iluvatar_bi-150 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 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 Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU 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 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 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 Iluvatar_bi-150 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。",
"组合 Ascend_910-b3|vllm_tokenizer_patch|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_tokenizer_patch|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 Ascend_910-b4|llamacpp|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-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51711,7 +51711,6 @@
"组合 Cambricon_mlu-370-x4|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 Cambricon_mlu-370-x4|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_bi-150|transformers|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_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_mrv-100|unknown|visual-multi-modal 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|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Mthreads_s4000|llamacpp|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_bi-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_bi-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -51725,10 +51724,11 @@
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|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 Mthreads_s4000|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 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Kunlunxin_p-800|vllm_tokenizer_patch|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_bi-150|llamacpp|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_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17292, "summarizedRecords": 17293,
"version": 1 "version": 1
} }

1236
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1636
.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": "2026.09.22.1", "agentVersion": "2026.09.22.1",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "6fe65a4d5ecc276313647c41c21dc9259e820be6786da39b833778c23d1e0172", ".modelhub_state/architecture_compatibility_blacklist.json": "4e3a7da3cea5d5beeafa851d0f033342a8eeecd51f179768dd08b229e1fd78bd",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "f759fcf34bf357ceb8aedea804aed87d3101b2a1764367d800eecf5c25d923be", ".modelhub_state/market_intelligence.json": "3e93737dc68fb623983646a0c3e93f51ddc661ec4d3b13a6192fcdcd81862b34",
".modelhub_state/official_capabilities.json": "27a932e2a8f02f0c21ee4ea29dc87fee21738f3322d3fc82d57f9b94b77b9062", ".modelhub_state/official_capabilities.json": "741e409ffad12dad573b439155bfe0de9d108f61d1e6a083abf71072095746fb",
".modelhub_state/outcome_checkpoint.json": "d579a7c225adf26412d1e7e1539fe6fdb2b310bb8ff192f18f74d98e88e0c357", ".modelhub_state/outcome_checkpoint.json": "91d45d51ecc70d26a73de31e52f1cdc7ed26675d06af360f45bd96491a935723",
".modelhub_state/queue_cleanup_latest.json": "e557ed3dc713e441b689ce8cc7bdc2b4e6f41ed1f75f2750fab491d148312d32", ".modelhub_state/queue_cleanup_latest.json": "e557ed3dc713e441b689ce8cc7bdc2b4e6f41ed1f75f2750fab491d148312d32",
".modelhub_state/recent_outcomes.jsonl": "1dbde9c4996b0dbc395b2b06ede89ee01d228323012054151eb598a3995b826e", ".modelhub_state/recent_outcomes.jsonl": "1dbde9c4996b0dbc395b2b06ede89ee01d228323012054151eb598a3995b826e",
".modelhub_state/recovery_active_tasks.jsonl": "5cf2a3669d99f5d197456a7a737bcd69de0c6a8bfe051b579efdef4552726f4e", ".modelhub_state/recovery_active_tasks.jsonl": "68a72588a5644951d8732a0879f8924a0e1a012dfd18b11d1678b40c1726d2df",
".modelhub_state/recovery_intents.jsonl": "81881a32a678745ec62e188a47ea3282335dca0adc69404630b36d6238cdee20", ".modelhub_state/recovery_intents.jsonl": "d1f5e167034b373feb0ece150ab066f5c04d36c9d887e239f4c35afdd3d38f7c",
".modelhub_state/routing_intelligence.json": "4864d455a863d4f5712f620109cc96b5b2ab91f24bce5ef4e7a9f6191c4ecead", ".modelhub_state/routing_intelligence.json": "4864d455a863d4f5712f620109cc96b5b2ab91f24bce5ef4e7a9f6191c4ecead",
".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799", ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799",
".modelhub_state/worker_crashes.jsonl": "8f862697b8c8286a6ac8130827f91487a3eb07ecaf4af7ee3de2915d925deb10", ".modelhub_state/worker_crashes.jsonl": "8f862697b8c8286a6ac8130827f91487a3eb07ecaf4af7ee3de2915d925deb10",
"ledger/submissions.jsonl": "f09bda07620cca6c4a2f0e4611838e87a337095187103729be65c5afe631f197", "ledger/submissions.jsonl": "f09bda07620cca6c4a2f0e4611838e87a337095187103729be65c5afe631f197",
"outcomes/submissions.jsonl": "a64f940b7eb45f5287b1a5e748c8a0d56a517fb4615ca43b236339e73b1d69ab" "outcomes/submissions.jsonl": "e93f50de3bded2079152107536c8db15adcd55c7bf5aa9f827e7253af3c65524"
}, },
"generation": 17767, "generation": 17768,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-28T06:14:41.748332+00:00", "updatedAt": "2026-09-28T06:19:55.114867+00:00",
"writerId": "6e8ddfbd92ca45ccaf79298516f8a6ea" "writerId": "6e8ddfbd92ca45ccaf79298516f8a6ea"
} }

1
outcomes/submissions.jsonl
View File

@@ -2,7 +2,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:29:56.904005+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {"architectures": ["Param2MoEForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34302758832, "estimatedRequiredGiB": 38.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "param2moe", "modelscopeFileSize": 34317809830, "modelscopeLicense": null, "modelscopeParams": 17151125376, "modelscopeTags": ["model_type:param2moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:multilingual", "custom_tag:indian-languages"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 34317809830}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:29:16.672536+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611191", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-04T12:29:56.904005+00:00", "modelId": "bharatgenai/Param2-17B-A2.4B-Thinking", "modelProfile": {"architectures": ["Param2MoEForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 34302758832, "estimatedRequiredGiB": 38.353, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "param2moe", "modelscopeFileSize": 34317809830, "modelscopeLicense": null, "modelscopeParams": 17151125376, "modelscopeTags": ["model_type:param2moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:mixture-of-experts", "custom_tag:multilingual", "custom_tag:indian-languages"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 34317809830}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:29:16.672536+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4611191", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T12:43:05.302313+00:00", "modelId": "b77968543/Spark-X2.5-4B-Q8_0", "modelProfile": {"architectures": [], "configFingerprint": "054a7592edf89d789e18b12765c567c3c34b2ebb58661fdd49255aad03c66d40", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 4.889, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4375025003, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "library:", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4375025003}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:40:16.372199+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611339", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T12:43:05.302313+00:00", "modelId": "b77968543/Spark-X2.5-4B-Q8_0", "modelProfile": {"architectures": [], "configFingerprint": "054a7592edf89d789e18b12765c567c3c34b2ebb58661fdd49255aad03c66d40", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 4.889, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4375025003, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "library:", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4375025003}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:40:16.372199+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611339", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T02:32:00.692571+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T18:26:16.665549+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632117", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T02:32:00.692571+00:00", "modelId": "ornith-ai/Ornith-1.5-35B-A3B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23420419700, "estimatedRequiredGiB": 26.214, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 23455515266, "modelscopeLicense": "mit", "modelscopeParams": 19528501104, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 23455515266}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T18:26:16.665549+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632117", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:05:43.096396+00:00", "modelId": "neuralmagic/gemma-2-9b-it-quantized.w8a8", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11998609696, "estimatedRequiredGiB": 13.434, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 12020499228, "modelscopeLicense": "gemma", "modelscopeParams": 10159209984, "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": 12020499228}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:03:47.678567+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632579", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:32:15.596901+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:29:42.987166+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632974", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:32:15.596901+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:29:42.987166+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632974", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:40:37.707812+00:00", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8dbcfce641caa83ec7080451f0410ae2c4732d92c35c6ea116cea836d3424ea2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2076674432, "estimatedRequiredGiB": 11.564, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10347343046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1942653248, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "custom_tag:edge", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10347343046}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:38:07.789820+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641229", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:40:37.707812+00:00", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8dbcfce641caa83ec7080451f0410ae2c4732d92c35c6ea116cea836d3424ea2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2076674432, "estimatedRequiredGiB": 11.564, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10347343046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1942653248, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "custom_tag:edge", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10347343046}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:38:07.789820+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641229", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:57:50.112723+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "7fcefcc66e6b781d939ce31d9aa1c7a89bdfb773b9556e6dcde4e21754b1189f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4610579744, "estimatedRequiredGiB": 25.463, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 22784105135, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4326350848, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22784105135}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:56:19.745119+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:57:50.112723+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "7fcefcc66e6b781d939ce31d9aa1c7a89bdfb773b9556e6dcde4e21754b1189f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4610579744, "estimatedRequiredGiB": 25.463, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 22784105135, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4326350848, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22784105135}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:56:19.745119+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "verifyResult": null}