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

state: generation 22904 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-10 07:40:54 +00:00
parent 03f9fbec96
commit 07c3d48ae8
11 changed files with 2966 additions and 2955 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2438,6 +2438,27 @@
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"metax_c-500|vllm_tokenizer_patch|text-generation|architectures:spark2_5forcausallm": {
"architectureSignature": "architectures:spark2_5forcausallm",
"architectures": [
"spark2_5forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-11-05T08:52:25.966686+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-10-06T08:52:25.966686+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": "spark2_5",
"sourceModelIds": [
"cyankiwi/Spark-X2.5-4B-AWQ-INT4"
],
"sourceTaskIds": [
"5319965"
],
"targetGpu": "MetaX_c-500",
"taskType": "text-generation"
},
"metax_c-500|vllm_tokenizer_patch|text-generation|model_type:mini_k3": { "metax_c-500|vllm_tokenizer_patch|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3", "architectureSignature": "model_type:mini_k3",
"architectures": [], "architectures": [],
@@ -2923,9 +2944,9 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-10T07:23:45.357665+00:00", "generatedAt": "2026-10-10T07:37:44.558136+00:00",
"summary": { "summary": {
"activeBlockCount": 146, "activeBlockCount": 147,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 10, "Ascend_910-b3|vllm": 10,
"Ascend_910-b3|vllm_tokenizer_patch": 10, "Ascend_910-b3|vllm_tokenizer_patch": 10,
@@ -2946,7 +2967,7 @@
"Kunlunxin_p-800|vllm": 10, "Kunlunxin_p-800|vllm": 10,
"Kunlunxin_p-800|vllm_tokenizer_patch": 9, "Kunlunxin_p-800|vllm_tokenizer_patch": 9,
"MetaX_c-500|vllm": 1, "MetaX_c-500|vllm": 1,
"MetaX_c-500|vllm_tokenizer_patch": 3, "MetaX_c-500|vllm_tokenizer_patch": 4,
"Mthreads_s4000|vllm": 6, "Mthreads_s4000|vllm": 6,
"Sunrise_pt-200-x1|vllm": 2, "Sunrise_pt-200-x1|vllm": 2,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4, "Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,

292
.modelhub_state/market_intelligence.json
View File

@@ -443,55 +443,55 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-10T07:36:04.895826+00:00", "generatedAt": "2026-10-10T07:39:51.233394+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1152.1241379310345, "backlogHours": 1136.4489795918366,
"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": 0.8171973546449243, "qualityFactor": 0.7896418318443348,
"queueFactor": 0.9576187895875821, "queueFactor": 0.9636433608488492,
"queueWeight": 0.9576187895875821, "queueWeight": 0.9636433608488492,
"recentSuccess": 47, "recentSuccess": 47,
"recentSuccessRate": 0.32413793103448274, "recentSuccessRate": 0.3197278911564626,
"recentTerminal": 145, "recentTerminal": 147,
"recentWilsonLowerBound": 0.2533452486065094, "recentWilsonLowerBound": 0.2497511340637152,
"running": 8, "running": 8,
"selectionWeight": 0.7825635416092465, "selectionWeight": 0.7609331087053166,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.166666666666668, "throughputPerHour": 24.5,
"waiting": 27843 "waiting": 27843
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1478.8548387096773, "backlogHours": 1455.4761904761904,
"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": 0.9224200156554346, "queueFactor": 0.9285345310806952,
"queueWeight": 0.9224200156554346, "queueWeight": 0.9285345310806952,
"recentSuccess": 63, "recentSuccess": 64,
"recentSuccessRate": 0.5080645161290323, "recentSuccessRate": 0.5079365079365079,
"recentTerminal": 124, "recentTerminal": 126,
"recentWilsonLowerBound": 0.42115888884621255, "recentWilsonLowerBound": 0.4217081082666577,
"running": 9, "running": 10,
"selectionWeight": 2.3060500391385865, "selectionWeight": 2.321336327701738,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.666666666666668, "throughputPerHour": 21.0,
"waiting": 30563 "waiting": 30565
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 136.3783783783784, "backlogHours": 137.1195652173913,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
@@ -500,64 +500,64 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 19, "recentSuccess": 17,
"recentSuccessRate": 0.10270270270270271, "recentSuccessRate": 0.09239130434782608,
"recentTerminal": 185, "recentTerminal": 184,
"recentWilsonLowerBound": 0.06673918450520243, "recentWilsonLowerBound": 0.05848484207545414,
"running": 8, "running": 9,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 30.833333333333332, "throughputPerHour": 30.666666666666668,
"waiting": 4205 "waiting": 4205
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1387.4366197183099, "backlogHours": 1387.6056338028168,
"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": 0.5660235121648329, "qualityFactor": 0.6373256295666673,
"queueFactor": 0.9312913672717502, "queueFactor": 0.9352095152910791,
"queueWeight": 0.9312913672717502, "queueWeight": 0.9352095152910791,
"recentSuccess": 22, "recentSuccess": 23,
"recentSuccessRate": 0.30985915492957744, "recentSuccessRate": 0.323943661971831,
"recentTerminal": 71, "recentTerminal": 71,
"recentWilsonLowerBound": 0.2143957547902181, "recentWilsonLowerBound": 0.22657056384385282,
"running": 8, "running": 7,
"selectionWeight": 0.5271328105519454, "selectionWeight": 0.5960329931096248,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.833333333333334, "throughputPerHour": 11.833333333333334,
"waiting": 16418 "waiting": 16420
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 390.44117647058823, "backlogHours": 402.1818181818182,
"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": 0.2937009853466837, "qualityFactor": 0.31340113400613057,
"queueFactor": 1.1263781267352055, "queueFactor": 1.126122044441985,
"queueWeight": 1.1263781267352055, "queueWeight": 1.126122044441985,
"recentSuccess": 30, "recentSuccess": 30,
"recentSuccessRate": 0.22058823529411764, "recentSuccessRate": 0.22727272727272727,
"recentTerminal": 136, "recentTerminal": 132,
"recentWilsonLowerBound": 0.15911201250331414, "recentWilsonLowerBound": 0.1640910639205752,
"running": 8, "running": 8,
"selectionWeight": 0.33081836569508166, "selectionWeight": 0.35292792575742027,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.666666666666668, "throughputPerHour": 22.0,
"waiting": 8850 "waiting": 8848
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 49.969465648854964, "backlogHours": 49.07575757575758,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -567,196 +567,196 @@
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 1, "recentSuccess": 1,
"recentSuccessRate": 0.002544529262086514, "recentSuccessRate": 0.0025252525252525255,
"recentTerminal": 393, "recentTerminal": 396,
"recentWilsonLowerBound": 0.0004493016390765759, "recentWilsonLowerBound": 0.0004458967757809532,
"running": 25, "running": 26,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 65.5, "throughputPerHour": 66.0,
"waiting": 3273 "waiting": 3239
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 154.67175572519085, "backlogHours": 157.09727626459144,
"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": 0.20222118295358976, "qualityFactor": 0.22241033063277482,
"queueFactor": 1.2942134171933946, "queueFactor": 1.296652276233569,
"queueWeight": 1.2942134171933946, "queueWeight": 1.296652276233569,
"recentSuccess": 46, "recentSuccess": 47,
"recentSuccessRate": 0.17557251908396945, "recentSuccessRate": 0.1828793774319066,
"recentTerminal": 262, "recentTerminal": 257,
"recentWilsonLowerBound": 0.13428602133853898, "recentWilsonLowerBound": 0.14040493792492742,
"running": 6, "running": 7,
"selectionWeight": 0.261717368219256, "selectionWeight": 0.28838886147284815,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 43.666666666666664, "throughputPerHour": 42.833333333333336,
"waiting": 6754 "waiting": 6729
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2261.268292682927, "backlogHours": 2107.227272727273,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_mrv-100", "gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.6984661649677302, "qualityFactor": 0.7091102084541998,
"queueFactor": 0.8654953446092563, "queueFactor": 0.8783995776687181,
"queueWeight": 0.8654953446092563, "queueWeight": 0.8783995776687181,
"recentSuccess": 15, "recentSuccess": 16,
"recentSuccessRate": 0.36585365853658536, "recentSuccessRate": 0.36363636363636365,
"recentTerminal": 41, "recentTerminal": 44,
"recentWilsonLowerBound": 0.23589630416936813, "recentWilsonLowerBound": 0.23783334127491426,
"running": 2, "running": 2,
"selectionWeight": 0.6045192141466512, "selectionWeight": 0.6228821076267458,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.833333333333333, "throughputPerHour": 7.333333333333333,
"waiting": 15452 "waiting": 15453
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 453.59999999999997, "backlogHours": 449.3793103448276,
"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": 0.4692848712157325, "qualityFactor": 0.4587670941817401,
"queueFactor": 1.1013277780766761, "queueFactor": 1.107533481368473,
"queueWeight": 1.1013277780766761, "queueWeight": 1.107533481368473,
"recentSuccess": 31, "recentSuccess": 31,
"recentSuccessRate": 0.26956521739130435, "recentSuccessRate": 0.2672413793103448,
"recentTerminal": 115, "recentTerminal": 116,
"recentWilsonLowerBound": 0.1968870391761085, "recentWilsonLowerBound": 0.19512298408590828,
"running": 8, "running": 10,
"selectionWeight": 0.5168364645010217, "selectionWeight": 0.5080999169564008,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 19.166666666666668, "throughputPerHour": 19.333333333333332,
"waiting": 8694 "waiting": 8688
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 513.483870967742, "backlogHours": 505.0,
"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": 0.3018343563822727, "qualityFactor": 0.34837202708360293,
"queueFactor": 1.0810319485963815, "queueFactor": 1.0883162613882846,
"queueWeight": 1.0810319485963815, "queueWeight": 1.0883162613882846,
"recentSuccess": 28, "recentSuccess": 30,
"recentSuccessRate": 0.22580645161290322, "recentSuccessRate": 0.23809523809523808,
"recentTerminal": 124, "recentTerminal": 126,
"recentWilsonLowerBound": 0.16109993441103604, "recentWilsonLowerBound": 0.17217416354451306,
"running": 4, "running": 6,
"selectionWeight": 0.3262925824332629, "selectionWeight": 0.37913894208788496,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.666666666666668, "throughputPerHour": 21.0,
"waiting": 10612 "waiting": 10605
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2552.6037735849054, "backlogHours": 2553.056603773585,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Mthreads_s4000", "gpu": "Mthreads_s4000",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 1.4286224580053941, "qualityFactor": 1.778546916783681,
"queueFactor": 0.8499043246987983, "queueFactor": 0.8534729448932877,
"queueWeight": 0.8499043246987983, "queueWeight": 0.8534729448932877,
"recentSuccess": 24, "recentSuccess": 26,
"recentSuccessRate": 0.4528301886792453, "recentSuccessRate": 0.49056603773584906,
"recentTerminal": 53, "recentTerminal": 53,
"recentWilsonLowerBound": 0.32657368160147465, "recentWilsonLowerBound": 0.36124029356039444,
"running": 5, "running": 4,
"selectionWeight": 1.2141924054206117, "selectionWeight": 1.5179416746982453,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.833333333333334, "throughputPerHour": 8.833333333333334,
"waiting": 22548 "waiting": 22552
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 2430.8372093023254, "backlogHours": 2613.0,
"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": 0.1416611195078842, "qualityFactor": 0.1667029885931764,
"queueFactor": 0.8561584923066802, "queueFactor": 0.8505070415964059,
"queueWeight": 0.8561584923066802, "queueWeight": 0.8505070415964059,
"recentSuccess": 9, "recentSuccess": 9,
"recentSuccessRate": 0.20930232558139536, "recentSuccessRate": 0.225,
"recentTerminal": 43, "recentTerminal": 40,
"recentWilsonLowerBound": 0.11422705997811458, "recentWilsonLowerBound": 0.12315953254678531,
"running": 2, "running": 2,
"selectionWeight": 0.12128437049634658, "selectionWeight": 0.14178206565366186,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 7.166666666666667, "throughputPerHour": 6.666666666666667,
"waiting": 17421 "waiting": 17420
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 727.21875, "backlogHours": 749.9032258064516,
"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": 0.25499278049769103, "qualityFactor": 0.273259043640234,
"queueFactor": 1.0260482641938642, "queueFactor": 1.0256473016931755,
"queueWeight": 1.0260482641938642, "queueWeight": 1.0256473016931755,
"recentSuccess": 27, "recentSuccess": 27,
"recentSuccessRate": 0.2109375, "recentSuccessRate": 0.21774193548387097,
"recentTerminal": 128, "recentTerminal": 124,
"recentWilsonLowerBound": 0.1492121185502459, "recentWilsonLowerBound": 0.15417986080833496,
"running": 16, "running": 17,
"selectionWeight": 0.2616348998116229, "selectionWeight": 0.2802674007728637,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": true,
"throughputPerHour": 21.333333333333332, "throughputPerHour": 20.666666666666668,
"waiting": 15514 "waiting": 15498
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 999.2033898305084, "backlogHours": 1025.7391304347825,
"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": 0.37086740507236393, "qualityFactor": 0.42905329448153173,
"queueFactor": 0.9782941698746422, "queueFactor": 0.9785731299218279,
"queueWeight": 0.9782941698746422, "queueWeight": 0.9785731299218279,
"recentSuccess": 29, "recentSuccess": 30,
"recentSuccessRate": 0.2457627118644068, "recentSuccessRate": 0.2608695652173913,
"recentTerminal": 118, "recentTerminal": 115,
"recentWilsonLowerBound": 0.17691084285864664, "recentWilsonLowerBound": 0.18927348744454853,
"running": 6, "running": 6,
"selectionWeight": 0.36281742017883095, "selectionWeight": 0.41986002528406424,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 19.666666666666668, "throughputPerHour": 19.166666666666668,
"waiting": 19651 "waiting": 19660
} }
}, },
"queueAttemptedAt": "2026-10-10T07:29:46.991502+00:00", "queueAttemptedAt": "2026-10-10T07:39:51.233394+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-10T07:29:46.991502+00:00", "queueUpdatedAt": "2026-10-10T07:39:51.233394+00:00",
"supportedGpus": [ "supportedGpus": [
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",
"Vastai_va16", "Vastai_va16",

2388
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

195
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-10T05:05:29.610717+00:00", "generatedAt": "2026-10-10T07:39:51.137069+00:00",
"lastSyncTime": "2026-10-10T05:05:29.556490+00:00", "lastSyncTime": "2026-10-10T07:39:51.086832+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2442,6 +2442,27 @@
"targetGpu": "Kunlunxin_p-800", "targetGpu": "Kunlunxin_p-800",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"metax_c-500|vllm_tokenizer_patch|text-generation|architectures:spark2_5forcausallm": {
"architectureSignature": "architectures:spark2_5forcausallm",
"architectures": [
"spark2_5forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-11-05T08:52:25.966686+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-10-06T08:52:25.966686+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": "spark2_5",
"sourceModelIds": [
"cyankiwi/Spark-X2.5-4B-AWQ-INT4"
],
"sourceTaskIds": [
"5319965"
],
"targetGpu": "MetaX_c-500",
"taskType": "text-generation"
},
"metax_c-500|vllm_tokenizer_patch|text-generation|model_type:mini_k3": { "metax_c-500|vllm_tokenizer_patch|text-generation|model_type:mini_k3": {
"architectureSignature": "model_type:mini_k3", "architectureSignature": "model_type:mini_k3",
"architectures": [], "architectures": [],
@@ -2928,7 +2949,7 @@
} }
}, },
"architectureCompatibilitySummary": { "architectureCompatibilitySummary": {
"activeBlockCount": 146, "activeBlockCount": 147,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 10, "Ascend_910-b3|vllm": 10,
"Ascend_910-b3|vllm_tokenizer_patch": 10, "Ascend_910-b3|vllm_tokenizer_patch": 10,
@@ -2949,7 +2970,7 @@
"Kunlunxin_p-800|vllm": 10, "Kunlunxin_p-800|vllm": 10,
"Kunlunxin_p-800|vllm_tokenizer_patch": 9, "Kunlunxin_p-800|vllm_tokenizer_patch": 9,
"MetaX_c-500|vllm": 1, "MetaX_c-500|vllm": 1,
"MetaX_c-500|vllm_tokenizer_patch": 3, "MetaX_c-500|vllm_tokenizer_patch": 4,
"Mthreads_s4000|vllm": 6, "Mthreads_s4000|vllm": 6,
"Sunrise_pt-200-x1|vllm": 2, "Sunrise_pt-200-x1|vllm": 2,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4, "Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
@@ -4788,17 +4809,17 @@
"unresolvedFailureCount": 66 "unresolvedFailureCount": 66
}, },
"MetaX_c-500|vllm_tokenizer_patch|text-generation": { "MetaX_c-500|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 6, "attributableFailureCount": 7,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 6, "decisionTotal": 7,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1, "ambiguous_runtime": 1,
"framework_architecture_unsupported": 5, "framework_architecture_unsupported": 6,
"model_load": 1, "model_load": 1,
"参数/模板问题": 20 "参数/模板问题": 20
}, },
"failureCount": 27, "failureCount": 28,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"pendingCount": 0, "pendingCount": 0,
@@ -4808,7 +4829,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 27, "total": 28,
"unresolvedFailureCount": 21 "unresolvedFailureCount": 21
}, },
"MetaX_c-500|vllm|feature_emb": { "MetaX_c-500|vllm|feature_emb": {
@@ -5804,15 +5825,15 @@
"unresolvedFailureCount": 427 "unresolvedFailureCount": 427
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"attributableFailureCount": 168, "attributableFailureCount": 169,
"decisionFailureRate": 0.9438, "decisionFailureRate": 0.9441,
"decisionSuccessRate": 0.0562, "decisionSuccessRate": 0.0559,
"decisionTotal": 178, "decisionTotal": 179,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 211, "ambiguous_runtime": 211,
"backend_operator": 15, "backend_operator": 15,
"context_length": 9, "context_length": 9,
"framework_architecture_unsupported": 110, "framework_architecture_unsupported": 111,
"memory_capacity": 2, "memory_capacity": 2,
"model_load": 24, "model_load": 24,
"platform_infrastructure": 3, "platform_infrastructure": 3,
@@ -5821,18 +5842,18 @@
"tokenizer_compatibility": 2, "tokenizer_compatibility": 2,
"参数/模板问题": 96 "参数/模板问题": 96
}, },
"failureCount": 478, "failureCount": 479,
"failureRate": 0.9795, "failureRate": 0.9796,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 3, "platformFailureCount": 3,
"successCount": 10, "successCount": 10,
"successRate": 0.0205, "successRate": 0.0204,
"total": 488, "total": 489,
"unresolvedFailureCount": 307 "unresolvedFailureCount": 307
} }
}, },
"generatedAt": "2026-10-10T05:05:29.598113+00:00", "generatedAt": "2026-10-10T07:39:51.123588+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 130, "attributableFailureCount": 130,
@@ -6107,16 +6128,16 @@
"unresolvedFailureCount": 170 "unresolvedFailureCount": 170
}, },
"MetaX_c-500": { "MetaX_c-500": {
"attributableFailureCount": 681, "attributableFailureCount": 682,
"decisionFailureRate": 0.8225, "decisionFailureRate": 0.8227,
"decisionSuccessRate": 0.1775, "decisionSuccessRate": 0.1773,
"decisionTotal": 828, "decisionTotal": 829,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 308, "ambiguous_runtime": 308,
"architecture_compatibility": 21, "architecture_compatibility": 21,
"backend_operator": 43, "backend_operator": 43,
"context_length": 59, "context_length": 59,
"framework_architecture_unsupported": 212, "framework_architecture_unsupported": 213,
"memory_capacity": 85, "memory_capacity": 85,
"model_load": 66, "model_load": 66,
"platform_infrastructure": 5, "platform_infrastructure": 5,
@@ -6127,14 +6148,14 @@
"日志缺失": 15, "日志缺失": 15,
"验证失败": 48 "验证失败": 48
}, },
"failureCount": 1485, "failureCount": 1486,
"failureRate": 0.9099, "failureRate": 0.91,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 5, "platformFailureCount": 5,
"successCount": 147, "successCount": 147,
"successRate": 0.0901, "successRate": 0.09,
"total": 1632, "total": 1633,
"unresolvedFailureCount": 799 "unresolvedFailureCount": 799
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
@@ -6273,7 +6294,7 @@
"hygon_k100-ai": 64.0 "hygon_k100-ai": 64.0
}, },
"pendingRecords": 0, "pendingRecords": 0,
"policyCancelledRecords": 510, "policyCancelledRecords": 514,
"profileCombinationStats": { "profileCombinationStats": {
"Ascend_910-b3|llamacpp|text-generation|smollm3|none": { "Ascend_910-b3|llamacpp|text-generation|smollm3|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -21431,6 +21452,29 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|aquila3|none": { "MetaX_c-500|vllm|text-generation|aquila3|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -26341,9 +26385,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 7 "ambiguous_runtime": 6
}, },
"failureCount": 7, "failureCount": 6,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -26355,8 +26399,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 7, "total": 6,
"unresolvedFailureCount": 7 "unresolvedFailureCount": 6
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -26590,17 +26634,17 @@
"unresolvedFailureCount": 9 "unresolvedFailureCount": 9
}, },
"MetaX_c-500|vllm_tokenizer_patch|text-generation": { "MetaX_c-500|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 5, "attributableFailureCount": 6,
"consecutiveFailures": 5, "consecutiveFailures": 6,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 5, "decisionTotal": 6,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1, "ambiguous_runtime": 1,
"framework_architecture_unsupported": 4, "framework_architecture_unsupported": 5,
"model_load": 1, "model_load": 1,
"参数/模板问题": 14 "参数/模板问题": 13
}, },
"failureCount": 20, "failureCount": 20,
"failureRate": 1.0, "failureRate": 1.0,
@@ -26615,7 +26659,7 @@
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 20, "total": 20,
"unresolvedFailureCount": 15 "unresolvedFailureCount": 14
}, },
"Mthreads_s4000|unknown|text-generation": { "Mthreads_s4000|unknown|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -27082,9 +27126,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 3 "ambiguous_runtime": 2
}, },
"failureCount": 3, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-10T00:08:25.360789+00:00", "lastTerminalAt": "2026-10-10T00:08:25.360789+00:00",
@@ -27097,8 +27141,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 3, "total": 2,
"unresolvedFailureCount": 3 "unresolvedFailureCount": 2
}, },
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": { "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -27700,6 +27744,31 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-10-10T07:37:42.662674+00:00",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Mthreads_s4000|vllm|text-generation|lfm2|none": { "Mthreads_s4000|vllm|text-generation|lfm2|none": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"consecutiveFailures": 1, "consecutiveFailures": 1,
@@ -51103,6 +51172,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"MetaX_c-500|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"loadSizeLog2Bucket": 31,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "MetaX_c-500",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"MetaX_c-500|vllm|text-generation|aquila3|none|12": { "MetaX_c-500|vllm|text-generation|aquila3|none|12": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -58427,20 +58520,20 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17774, "terminalRecords": 17775,
"totalRecords": 18284, "totalRecords": 18289,
"totals": { "totals": {
"attributableFailureCount": 6314, "attributableFailureCount": 6315,
"decisionFailureRate": 0.8655, "decisionFailureRate": 0.8655,
"decisionSuccessRate": 0.1345, "decisionSuccessRate": 0.1345,
"decisionTotal": 7295, "decisionTotal": 7296,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4623, "ambiguous_runtime": 4623,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 131, "backend_operator": 131,
"context_length": 327, "context_length": 327,
"framework_architecture_unsupported": 2329, "framework_architecture_unsupported": 2330,
"memory_capacity": 1206, "memory_capacity": 1206,
"model_load": 571, "model_load": 571,
"platform_infrastructure": 956, "platform_infrastructure": 956,
@@ -58451,14 +58544,14 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16793, "failureCount": 16794,
"failureRate": 0.9448, "failureRate": 0.9448,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 956, "platformFailureCount": 956,
"successCount": 981, "successCount": 981,
"successRate": 0.0552, "successRate": 0.0552,
"total": 17774, "total": 17775,
"unresolvedFailureCount": 9523 "unresolvedFailureCount": 9523
}, },
"warnings": [ "warnings": [
@@ -58521,6 +58614,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 18284, "summarizedRecords": 18289,
"version": 1 "version": 1
} }

183
.modelhub_state/queue_cleanup_latest.json
View File

@@ -14,13 +14,13 @@
100 100
], ],
"accounts": 12, "accounts": 12,
"activeScanned": 966, "activeScanned": 961,
"ageCleanupMode": "admission_only", "ageCleanupMode": "admission_only",
"agePolicySkipped": { "agePolicySkipped": {
"cleanupDisabled": true, "cleanupDisabled": true,
"reason": "admission_only" "reason": "admission_only"
}, },
"architectureBlockCount": 146, "architectureBlockCount": 147,
"architectureFrameworkCatalog": { "architectureFrameworkCatalog": {
"ascend_910-b3|text-generation": [ "ascend_910-b3|text-generation": [
"llamacpp", "llamacpp",
@@ -59,12 +59,12 @@
] ]
}, },
"architectureFrameworkCatalogErrors": {}, "architectureFrameworkCatalogErrors": {},
"architectureIncompatibleCount": 3, "architectureIncompatibleCount": 4,
"architectureIncompatibleTasks": [ "architectureIncompatibleTasks": [
{ {
"accountIndex": 5, "accountIndex": 2,
"architectureBlockEvidenceCount": 1, "architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-02T16:15:49.651187+00:00", "architectureBlockExpiresAt": "2026-11-05T08:52:25.966686+00:00",
"architectureMatchScope": "exact_framework", "architectureMatchScope": "exact_framework",
"architectureMatchType": "architectures", "architectureMatchType": "architectures",
"architectureSignature": "architectures:spark2_5forcausallm", "architectureSignature": "architectures:spark2_5forcausallm",
@@ -75,38 +75,59 @@
"vllm_tokenizer_patch" "vllm_tokenizer_patch"
], ],
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b3", "gpuType": "MetaX_c-500",
"modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5260100,
"taskType": "text-generation"
},
{
"accountIndex": 5,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-02T16:15:49.651187+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "architectures",
"architectureSignature": "architectures:spark2_5forcausallm",
"architectureSignatures": [
"architectures:spark2_5forcausallm"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b3",
"modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base",
"reason": "known_framework_architecture_incompatible", "reason": "known_framework_architecture_incompatible",
"status": "waiting", "status": "waiting",
"taskId": 5368938, "taskId": 5367428,
"taskType": "text-generation"
},
{
"accountIndex": 3,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-05T08:52:25.966686+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "architectures",
"architectureSignature": "architectures:spark2_5forcausallm",
"architectureSignatures": [
"architectures:spark2_5forcausallm"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "MetaX_c-500",
"modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5208880,
"taskType": "text-generation"
},
{
"accountIndex": 3,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-05T08:52:25.966686+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "architectures",
"architectureSignature": "architectures:spark2_5forcausallm",
"architectureSignatures": [
"architectures:spark2_5forcausallm"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "MetaX_c-500",
"modelId": "hcnote/SparkMuse-4B-INT4",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5319963,
"taskType": "text-generation" "taskType": "text-generation"
}, },
{ {
"accountIndex": 10, "accountIndex": 10,
"architectureBlockEvidenceCount": 1, "architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-02T16:15:49.651187+00:00", "architectureBlockExpiresAt": "2026-11-05T08:52:25.966686+00:00",
"architectureMatchScope": "exact_framework", "architectureMatchScope": "exact_framework",
"architectureMatchType": "architectures", "architectureMatchType": "architectures",
"architectureSignature": "architectures:spark2_5forcausallm", "architectureSignature": "architectures:spark2_5forcausallm",
@@ -117,11 +138,11 @@
"vllm_tokenizer_patch" "vllm_tokenizer_patch"
], ],
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b3", "gpuType": "MetaX_c-500",
"modelId": "hcnote/SparkMuse-4B-INT4", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M",
"reason": "known_framework_architecture_incompatible", "reason": "known_framework_architecture_incompatible",
"status": "waiting", "status": "waiting",
"taskId": 5260112, "taskId": 5319940,
"taskType": "text-generation" "taskType": "text-generation"
} }
], ],
@@ -151,18 +172,18 @@
"frameworkCatalogUnknown": 0, "frameworkCatalogUnknown": 0,
"frameworkContextUnknown": 44, "frameworkContextUnknown": 44,
"modelArchitectureUnknown": 166, "modelArchitectureUnknown": 166,
"noMatchingBlock": 781, "noMatchingBlock": 775,
"partiallyBlockedFrameworkSet": 16, "partiallyBlockedFrameworkSet": 16,
"runningMatchedProtected": 0, "runningMatchedProtected": 0,
"submissionContextMismatch": 0, "submissionContextMismatch": 0,
"submissionContextUnknown": 0 "submissionContextUnknown": 0
}, },
"cancelledCount": 3, "cancelledCount": 4,
"cancelledTasks": [ "cancelledTasks": [
{ {
"accountIndex": 5, "accountIndex": 2,
"architectureBlockEvidenceCount": 1, "architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-02T16:15:49.651187+00:00", "architectureBlockExpiresAt": "2026-11-05T08:52:25.966686+00:00",
"architectureMatchScope": "exact_framework", "architectureMatchScope": "exact_framework",
"architectureMatchType": "architectures", "architectureMatchType": "architectures",
"architectureSignature": "architectures:spark2_5forcausallm", "architectureSignature": "architectures:spark2_5forcausallm",
@@ -176,41 +197,65 @@
"vllm_tokenizer_patch" "vllm_tokenizer_patch"
], ],
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b3", "gpuType": "MetaX_c-500",
"modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5260100,
"taskType": "text-generation"
},
{
"accountIndex": 5,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-02T16:15:49.651187+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "architectures",
"architectureSignature": "architectures:spark2_5forcausallm",
"architectureSignatures": [
"architectures:spark2_5forcausallm"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b3",
"modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base",
"reason": "known_framework_architecture_incompatible", "reason": "known_framework_architecture_incompatible",
"status": "waiting", "status": "waiting",
"taskId": 5368938, "taskId": 5367428,
"taskType": "text-generation"
},
{
"accountIndex": 3,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-05T08:52:25.966686+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "architectures",
"architectureSignature": "architectures:spark2_5forcausallm",
"architectureSignatures": [
"architectures:spark2_5forcausallm"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "MetaX_c-500",
"modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5208880,
"taskType": "text-generation"
},
{
"accountIndex": 3,
"architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-05T08:52:25.966686+00:00",
"architectureMatchScope": "exact_framework",
"architectureMatchType": "architectures",
"architectureSignature": "architectures:spark2_5forcausallm",
"architectureSignatures": [
"architectures:spark2_5forcausallm"
],
"cleanupReasons": [
"known_framework_architecture_incompatible"
],
"evaluatedFrameworks": [
"vllm_tokenizer_patch"
],
"framework": "vllm_tokenizer_patch",
"gpuType": "MetaX_c-500",
"modelId": "hcnote/SparkMuse-4B-INT4",
"reason": "known_framework_architecture_incompatible",
"status": "waiting",
"taskId": 5319963,
"taskType": "text-generation" "taskType": "text-generation"
}, },
{ {
"accountIndex": 10, "accountIndex": 10,
"architectureBlockEvidenceCount": 1, "architectureBlockEvidenceCount": 1,
"architectureBlockExpiresAt": "2026-11-02T16:15:49.651187+00:00", "architectureBlockExpiresAt": "2026-11-05T08:52:25.966686+00:00",
"architectureMatchScope": "exact_framework", "architectureMatchScope": "exact_framework",
"architectureMatchType": "architectures", "architectureMatchType": "architectures",
"architectureSignature": "architectures:spark2_5forcausallm", "architectureSignature": "architectures:spark2_5forcausallm",
@@ -224,17 +269,17 @@
"vllm_tokenizer_patch" "vllm_tokenizer_patch"
], ],
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"gpuType": "Ascend_910-b3", "gpuType": "MetaX_c-500",
"modelId": "hcnote/SparkMuse-4B-INT4", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M",
"reason": "known_framework_architecture_incompatible", "reason": "known_framework_architecture_incompatible",
"status": "waiting", "status": "waiting",
"taskId": 5260112, "taskId": 5319940,
"taskType": "text-generation" "taskType": "text-generation"
} }
], ],
"certainOomCount": 0, "certainOomCount": 0,
"certainOomTasks": [], "certainOomTasks": [],
"cleanupCandidateCount": 3, "cleanupCandidateCount": 4,
"dryRun": false, "dryRun": false,
"listingErrors": {}, "listingErrors": {},
"modelAgeErrors": {}, "modelAgeErrors": {},
@@ -259,7 +304,7 @@
], ],
"oldOverflowCount": 0, "oldOverflowCount": 0,
"oldOverflowTasks": [], "oldOverflowTasks": [],
"policyCancelledRecorded": 3, "policyCancelledRecorded": 4,
"policyNoLongerAppliesCount": 0, "policyNoLongerAppliesCount": 0,
"policyNoLongerAppliesTasks": [], "policyNoLongerAppliesTasks": [],
"recentModelDays": 7, "recentModelDays": 7,
@@ -272,5 +317,5 @@
"repositorySizeUnknown": 0 "repositorySizeUnknown": 0
}, },
"stopErrors": [], "stopErrors": [],
"uniqueModels": 309 "uniqueModels": 308
} }

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -205,6 +205,7 @@
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:09:53.041479+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Balance", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:26.360775+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319981", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:09:53.041479+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Balance", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:26.360775+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319981", "taskType": "text-generation", "verifyResult": null}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T06:27:34.062607+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:26.243503+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319978", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T06:27:34.062607+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:26.243503+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319978", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:09:53.041452+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:26.051111+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319972", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:09:53.041452+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:26.051111+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319972", "taskType": "text-generation", "verifyResult": null}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T07:37:42.662674+00:00", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:25.966686+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319965", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T06:05:03.160740+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529500, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529500}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:25.882518+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319960", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T06:05:03.160740+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529500, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529500}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:25.882518+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319960", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T04:16:40.361082+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:25.845437+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319959", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["mini_k3"], "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T04:16:40.361082+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelProfile": {"architectures": [], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033585336, "estimatedRequiredGiB": 2.457, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2198654500, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2198654500}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:25.845437+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319959", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:31:58.345474+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:25.762465+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319956", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:31:58.345474+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:25.762465+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319956", "taskType": "text-generation", "verifyResult": null}
@@ -297,4 +298,3 @@
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557020+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T05:54:51.550868+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5013339", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557020+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T05:54:51.550868+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5013339", "taskType": "text-generation", "verifyResult": null}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-09T17:58:01.576792+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:52:13.652441+00:00", "targetGpu": "Biren_166m", "taskId": "5013306", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-09T17:58:01.576792+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:52:13.652441+00:00", "targetGpu": "Biren_166m", "taskId": "5013306", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["SSESWAMoBAForCausalLM"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T14:08:43.365639+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:48:17.265295+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5013248", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["SSESWAMoBAForCausalLM"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-08T14:08:43.365639+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:48:17.265295+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5013248", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-09T18:48:59.559996+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g32-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031556216, "estimatedRequiredGiB": 2.28, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039918195}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:45:37.003989+00:00", "targetGpu": "Biren_166m", "taskId": "5013207", "taskType": "text-generation", "verifyResult": -1}

1092
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1708
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

5
ledger/submissions.jsonl
View File

@@ -338,7 +338,6 @@
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/bench-labs/pulvis-v1", "modelId": "bench-labs/pulvis-v1", "submitTime": "2026-09-30T19:00:30.054397+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200517", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/bench-labs/pulvis-v1", "modelId": "bench-labs/pulvis-v1", "submitTime": "2026-09-30T19:00:30.054397+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200517", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-G1k-2.9B-20260930", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "submitTime": "2026-09-30T19:00:30.056861+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200519", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/RWKV/RWKV7-G1k-2.9B-20260930", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "submitTime": "2026-09-30T19:00:30.056861+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200519", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/K2-Horizon-3.7B-8bit", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "submitTime": "2026-09-30T19:16:58.857252+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200707", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/K2-Horizon-3.7B-8bit", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "submitTime": "2026-09-30T19:16:58.857252+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200707", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "submitTime": "2026-10-01T05:41:58.050597+00:00", "targetGpu": "MetaX_c-500", "taskId": "5208880", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-1-FP8-dynamic", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "submitTime": "2026-10-01T05:59:45.051636+00:00", "targetGpu": "MetaX_c-500", "taskId": "5209080", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-1-FP8-dynamic", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "submitTime": "2026-10-01T05:59:45.051636+00:00", "targetGpu": "MetaX_c-500", "taskId": "5209080", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "submitTime": "2026-10-01T06:01:55.960786+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209103", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "submitTime": "2026-10-01T06:01:55.960786+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209103", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-1-FP8-dynamic", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "submitTime": "2026-10-01T06:17:59.744659+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209313", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b4"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/shisa-ai/shisa-de-1-FP8-dynamic", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "submitTime": "2026-10-01T06:17:59.744659+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209313", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-ascend-910-b4"}
@@ -422,12 +421,10 @@
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/groxaxo/Hemmingway-1-AutoRound-W4G128", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "submitTime": "2026-10-06T08:50:49.256812+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319929", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/groxaxo/Hemmingway-1-AutoRound-W4G128", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "submitTime": "2026-10-06T08:50:49.256812+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319929", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/NovelAI/clio-v1-legacy", "modelId": "NovelAI/clio-v1-legacy", "submitTime": "2026-10-06T08:50:49.254703+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319935", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/NovelAI/clio-v1-legacy", "modelId": "NovelAI/clio-v1-legacy", "submitTime": "2026-10-06T08:50:49.254703+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319935", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-4.2-3b", "modelId": "ibm-granite/granite-4.2-3b", "submitTime": "2026-10-06T08:52:25.554613+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319948", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/ibm-granite/granite-4.2-3b", "modelId": "ibm-granite/granite-4.2-3b", "submitTime": "2026-10-06T08:52:25.554613+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319948", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "submitTime": "2026-10-06T08:52:25.557635+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319940", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "submitTime": "2026-10-06T08:52:25.676818+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319951", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "submitTime": "2026-10-06T08:52:25.676818+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319951", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/Hemmingway-1-OptiQ-4bit", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "submitTime": "2026-10-06T08:52:25.748983+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319954", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/Hemmingway-1-OptiQ-4bit", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "submitTime": "2026-10-06T08:52:25.748983+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319954", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-610m-fin-instruct", "modelId": "pfnet/plamo-3-610m-fin-instruct", "submitTime": "2026-10-06T08:52:25.756975+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319955", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/pfnet/plamo-3-610m-fin-instruct", "modelId": "pfnet/plamo-3-610m-fin-instruct", "submitTime": "2026-10-06T08:52:25.756975+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319955", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/juspay/xor-lite", "modelId": "juspay/xor-lite", "submitTime": "2026-10-06T08:52:25.752033+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319957", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/juspay/xor-lite", "modelId": "juspay/xor-lite", "submitTime": "2026-10-06T08:52:25.752033+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319957", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B-INT4", "modelId": "hcnote/SparkMuse-4B-INT4", "submitTime": "2026-10-06T08:52:25.860251+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319963", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/burtenshaw/nanochat", "modelId": "burtenshaw/nanochat", "submitTime": "2026-10-06T08:52:25.847783+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319961", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/burtenshaw/nanochat", "modelId": "burtenshaw/nanochat", "submitTime": "2026-10-06T08:52:25.847783+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319961", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-32B-NVFP4", "modelId": "IFM/K2-Horizon-32B-NVFP4", "submitTime": "2026-10-06T08:52:25.964919+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319967", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/IFM/K2-Horizon-32B-NVFP4", "modelId": "IFM/K2-Horizon-32B-NVFP4", "submitTime": "2026-10-06T08:52:25.964919+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319967", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/FINAL-Bench/Darwin-27B-RSI", "modelId": "FINAL-Bench/Darwin-27B-RSI", "submitTime": "2026-10-06T08:52:25.963552+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319966", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/FINAL-Bench/Darwin-27B-RSI", "modelId": "FINAL-Bench/Darwin-27B-RSI", "submitTime": "2026-10-06T08:52:25.963552+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319966", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
@@ -784,7 +781,6 @@
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "submitTime": "2026-10-07T20:33:02.759018+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361261", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "submitTime": "2026-10-07T20:33:02.759018+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361261", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "submitTime": "2026-10-07T21:42:18.062092+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5362155", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "submitTime": "2026-10-07T21:42:18.062092+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5362155", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-hygon-k100-ai"}
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "submitTime": "2026-10-07T22:49:57.464476+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5363028", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"} {"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "submitTime": "2026-10-07T22:49:57.464476+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5363028", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T03:55:00.884003+00:00", "targetGpu": "MetaX_c-500", "taskId": "5367428", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T04:19:38.748920+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5368612", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T04:19:38.748920+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5368612", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T04:54:20.845170+00:00", "targetGpu": "Biren_166m", "taskId": "5369290", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T04:54:20.845170+00:00", "targetGpu": "Biren_166m", "taskId": "5369290", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-biren-166m"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T05:37:38.062655+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5370970", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T05:37:38.062655+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5370970", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
@@ -871,6 +867,7 @@
{"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B-INT4", "modelId": "hcnote/SparkMuse-4B-INT4", "submitTime": "2026-10-07T19:29:02.288614+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360290", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"} {"framework": "vllm_0_17_0_corex_4_4_0", "modelAddress": "https://modelscope.cn/models/hcnote/SparkMuse-4B-INT4", "modelId": "hcnote/SparkMuse-4B-INT4", "submitTime": "2026-10-07T19:29:02.288614+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5360290", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-0-17-0-corex-4-4-0-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "submitTime": "2026-10-07T20:21:22.460114+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5361078", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "submitTime": "2026-10-07T20:21:22.460114+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5361078", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "submitTime": "2026-10-07T20:31:42.847347+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361257", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"} {"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-kda-kernel-0-v2", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-0-v2", "submitTime": "2026-10-07T20:31:42.847347+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361257", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-kunlunxin-p-800"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T03:55:00.884003+00:00", "targetGpu": "MetaX_c-500", "taskId": "5367428", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T04:35:43.854342+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5368938", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T04:35:43.854342+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5368938", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T05:16:49.666742+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5370509", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-Base", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "submitTime": "2026-10-08T05:16:49.666742+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5370509", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "submitTime": "2026-10-08T08:23:33.447710+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5374800", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "submitTime": "2026-10-08T08:23:33.447710+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5374800", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x4"}

24
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": "f43fd20dd9d5af94eb51b7d59b020632f2149a31ce79c1b5d324e1c2c15c7eec", ".modelhub_state/architecture_compatibility_blacklist.json": "2b5225c1a0391fccd04c0cc469f7d591c60c636c85abe809a6fa9e2814785823",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "a20dd47d5f058cb47a5d7740927bb21b52c5b93d001f1bfd334bbc08abe5bd12", ".modelhub_state/market_intelligence.json": "e046de7a7185d80584ece754db11200a7a2c39a83f24d36d2429fe19c0108f63",
".modelhub_state/official_capabilities.json": "1d41e5def675032de3c446d6d6bf60e161706f050e60eb0571a34f116d881b57", ".modelhub_state/official_capabilities.json": "87827ad29550f8e41108217da7bcab9d5eb7431c0734f19295204af162d8711f",
".modelhub_state/outcome_checkpoint.json": "c98cfb24f6fd5532d8bab29e9c3100aa41ac6e0bd7adab67eb937bd1903a2b2f", ".modelhub_state/outcome_checkpoint.json": "aaab2326370cdbae90e8d5396fe880c3ee0b447fb6aa46f01b10dd397c42ca79",
".modelhub_state/queue_cleanup_latest.json": "b88c15e5c1fe87405b3970a14e0a6105c4b551cdbde5e2e981816a0b2a1869e2", ".modelhub_state/queue_cleanup_latest.json": "479eeff66efc0333efe15f88578ae4a41d1437eba223ca0c5098d4114c04e8cd",
".modelhub_state/recent_outcomes.jsonl": "088112a025e6d880d2f1cd1880421e9a9a8df2d8837d16c7475a53e6e6cdb1f7", ".modelhub_state/recent_outcomes.jsonl": "7cf4a4509fb4eb47900dc5c1719a6929b7ffdb3284bb67a5f6fac8d4b4fcb4d4",
".modelhub_state/recovery_active_tasks.jsonl": "b21bc03883fd5c09fc2f6f6347bcfb16fb0a2267db2f3d672be6765a16bda44a", ".modelhub_state/recovery_active_tasks.jsonl": "8e2c361ce859f9455f226663ab55099126371061cc4f5d2ec7570341d564128f",
".modelhub_state/recovery_intents.jsonl": "87cebf01bec23e5f6045a6351b7c961e5bf9f8eeae0b5d53e608b1cbdc795ace", ".modelhub_state/recovery_intents.jsonl": "40b1c68fc62bfa6af61b6daa6503d739edbebbfc98109adfdfbd3aa73504b0e2",
".modelhub_state/routing_intelligence.json": "94b2db56167982b1b727ce34457b1d37556f3ce037602c951db8a51a3e64b6a6", ".modelhub_state/routing_intelligence.json": "94b2db56167982b1b727ce34457b1d37556f3ce037602c951db8a51a3e64b6a6",
".modelhub_state/submission_exclusions.jsonl": "2269e9d4ab33cc7afbf93b4a49c7f3833d35511505655e324e5937b07a97bd31", ".modelhub_state/submission_exclusions.jsonl": "2269e9d4ab33cc7afbf93b4a49c7f3833d35511505655e324e5937b07a97bd31",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f", ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "81068c3c9e502da7e942d004386d61925a69171ad37d0992df05e3e05f88cb66", "ledger/submissions.jsonl": "b621189fc18eb354bde0bb1d863fe48248e09ed9b389c24be82760d731db201e",
"outcomes/submissions.jsonl": "6f157fe8369673c2f7889341bcde9ffeba24dce4401e7c67367f95a92de82993" "outcomes/submissions.jsonl": "359b3db206f1b80dc8fa55a894fb55cde31bc1f0942efbeea0e183237a443149"
}, },
"generation": 22903, "generation": 22904,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-10T07:36:41.484112+00:00", "updatedAt": "2026-10-10T07:40:54.283200+00:00",
"writerId": "43462b8a22de474db5c83d43b475a356" "writerId": "43462b8a22de474db5c83d43b475a356"
} }

5
outcomes/submissions.jsonl
View File

@@ -345,7 +345,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T03:00:54.465107+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T19:00:30.054397+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200517", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T03:00:54.465107+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T19:00:30.054397+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200517", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T03:00:54.465067+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T19:00:30.056861+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200519", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T03:00:54.465067+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T19:00:30.056861+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200519", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T03:19:50.448066+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T19:16:58.857252+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200707", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T03:19:50.448066+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-30T19:16:58.857252+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5200707", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T13:47:42.951714+00:00", "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T05:41:58.050597+00:00", "targetGpu": "MetaX_c-500", "taskId": "5208880", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T14:07:32.753918+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T05:59:45.051636+00:00", "targetGpu": "MetaX_c-500", "taskId": "5209080", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T14:07:32.753918+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T05:59:45.051636+00:00", "targetGpu": "MetaX_c-500", "taskId": "5209080", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T14:07:32.753944+00:00", "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T06:01:55.960786+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209103", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-01T14:07:32.753944+00:00", "modelId": "OsaurusAI/Raptor-0.6-4B-JANG_4M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2635323720, "estimatedRequiredGiB": 2.962, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2650224659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T06:01:55.960786+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209103", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-01T14:35:00.855901+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T06:17:59.744659+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209313", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-01T14:35:00.855901+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-01T06:17:59.744659+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5209313", "taskType": "text-generation", "verifyResult": null}
@@ -429,16 +428,13 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347930+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.256812+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319929", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347930+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.256812+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319929", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348141+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.254703+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319935", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348141+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:50:49.254703+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319935", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347746+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.554613+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319948", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347746+00:00", "modelId": "ibm-granite/granite-4.2-3b", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7319517120, "estimatedRequiredGiB": 8.191, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 7329313125, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3659737600, "modelscopeTags": ["license:apache-2.0", "model_type:granite", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:granite", "custom_tag:granite-4.2", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:tool-calling", "custom_tag:ibm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7329313125}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.554613+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319948", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347639+00:00", "modelId": "OsaurusAI/Raptor-0.6.1-preview-4B-JANG_6M", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3662928280, "estimatedRequiredGiB": 4.11, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3677830216, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:jang", "custom_tag:quantized", "custom_tag:apple-silicon", "custom_tag:reasoning", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:spark2_5", "custom_tag:imatrix", "custom_tag:awq", "custom_tag:gptq", "custom_tag:preview"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3677830216}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.557635+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319940", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348043+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.676818+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319951", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348043+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.676818+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319951", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347912+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.748983+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319954", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347912+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.748983+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319954", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347633+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.756975+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319955", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347633+00:00", "modelId": "pfnet/plamo-3-610m-fin-instruct", "modelProfile": {"architectures": ["Plamo3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1780709128, "estimatedRequiredGiB": 1.994, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "plamo3", "modelscopeFileSize": 1784320455, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:plamo3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:finance", "custom_tag:plamo", "custom_tag:japanese"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1784320455}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.756975+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319955", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347738+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.752033+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319957", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347738+00:00", "modelId": "juspay/xor-lite", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043603436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.752033+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319957", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348038+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.860251+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319963", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347792+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.847783+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319961", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347792+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "5f9f3c1607c4d592480a2bc6bf4bd3811708695139f6772f4b18a577c41a71ec", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": 8592610065, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.847783+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319961", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347964+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.964919+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319967", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347964+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 23275790433, "modelscopeLicense": "apache-2.0", "modelscopeParams": 34779305408, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvfp4", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790433}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.964919+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319967", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347732+00:00", "modelId": "FINAL-Bench/Darwin-27B-RSI", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53792110192, "estimatedRequiredGiB": 60.14, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 53812206708, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:darwin", "custom_tag:darwin-rsi", "custom_tag:recursive-self-improvement", "custom_tag:model-level-rsi", "custom_tag:rsi", "custom_tag:self-improvement", "custom_tag:self-improving-ai", "custom_tag:self-evolving", "custom_tag:no-human-labels", "custom_tag:label-free", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:chain-of-thought", "custom_tag:gpqa", "custom_tag:supergpqa", "custom_tag:decision-index", "custom_tag:typed-decisions", "custom_tag:jev", "custom_tag:system-2", "custom_tag:qwen3.5", "custom_tag:27b", "custom_tag:vidraft", "custom_tag:final-bench"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53812206708}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.963552+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319966", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347732+00:00", "modelId": "FINAL-Bench/Darwin-27B-RSI", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 53792110192, "estimatedRequiredGiB": 60.14, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 53812206708, "modelscopeLicense": "apache-2.0", "modelscopeParams": 26895998464, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:darwin", "custom_tag:darwin-rsi", "custom_tag:recursive-self-improvement", "custom_tag:model-level-rsi", "custom_tag:rsi", "custom_tag:self-improvement", "custom_tag:self-improving-ai", "custom_tag:self-evolving", "custom_tag:no-human-labels", "custom_tag:label-free", "custom_tag:reasoning", "custom_tag:thinking", "custom_tag:chain-of-thought", "custom_tag:gpqa", "custom_tag:supergpqa", "custom_tag:decision-index", "custom_tag:typed-decisions", "custom_tag:jev", "custom_tag:system-2", "custom_tag:qwen3.5", "custom_tag:27b", "custom_tag:vidraft", "custom_tag:final-bench"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53812206708}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.963552+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319966", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347627+00:00", "modelId": "cyankiwi/Spark-X2.5-4B-AWQ-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2856860040, "estimatedRequiredGiB": 3.21, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2872281308, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2872281308}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.966686+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319965", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347906+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.946650+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319964", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347906+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6343991648, "estimatedRequiredGiB": 7.115, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 6366013051, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1716764160, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6366013051}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:25.946650+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319964", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347990+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.047758+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319968", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.347990+00:00", "modelId": "peculiar-ragdoll/Sharp-MiniCPM5-2B-MLX-oQ6e", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2092366914, "estimatedRequiredGiB": 2.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2103475788, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:apple-silicon", "custom_tag:oq", "custom_tag:llama", "custom_tag:minicpm", "custom_tag:imatrix", "custom_tag:long-context", "custom_tag:coding", "custom_tag:sharp-template", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2103475788}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.047758+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319968", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348121+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "0ff19870d6fc477c61af7cf46bc2f3e6dd4cc9e712cd976a53d87c17d2045bb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.071974+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319969", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-06T16:58:45.348121+00:00", "modelId": "BananaMind/BananaMind-2-assistant2user", "modelProfile": {"architectures": ["BananaMind2ProForCausalLM"], "configFingerprint": "0ff19870d6fc477c61af7cf46bc2f3e6dd4cc9e712cd976a53d87c17d2045bb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 277971120, "estimatedRequiredGiB": 0.315, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananamind2_pro", "modelscopeFileSize": 281591196, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananamind2_pro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:assistant-to-user", "custom_tag:reconstruction", "custom_tag:reverse-sft", "custom_tag:causal-lm", "custom_tag:bananamind"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 281591196}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T08:52:26.071974+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319969", "taskType": "text-generation", "verifyResult": null}
@@ -797,7 +793,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T04:46:03.168038+00:00", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120900461, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1915564544, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:qwen3.5", "custom_tag:reasoning", "custom_tag:long-context", "custom_tag:function-calling", "custom_tag:tool-use", "custom_tag:agentic", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-07T14:46:46.372736+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 7120900461}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T20:33:02.759018+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361261", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T04:46:03.168038+00:00", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120900461, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1915564544, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:qwen3.5", "custom_tag:reasoning", "custom_tag:long-context", "custom_tag:function-calling", "custom_tag:tool-use", "custom_tag:agentic", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-10-07T14:46:46.372736+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 7120900461}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T20:33:02.759018+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5361261", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T06:08:00.557064+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580753, "modelscopeLicense": "other", "modelscopeParams": 219544320, "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": 809580753}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T21:42:18.062092+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5362155", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T06:08:00.557064+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580753, "modelscopeLicense": "other", "modelscopeParams": 219544320, "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": 809580753}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T21:42:18.062092+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5362155", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T07:02:21.767768+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580753, "modelscopeLicense": "other", "modelscopeParams": 219544320, "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": 809580753}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T22:49:57.464476+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5363028", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T07:02:21.767768+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580753, "modelscopeLicense": "other", "modelscopeParams": 219544320, "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": 809580753}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T22:49:57.464476+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5363028", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T12:03:49.371279+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T03:55:00.884003+00:00", "targetGpu": "MetaX_c-500", "taskId": "5367428", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T12:22:18.279562+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T04:19:38.748920+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5368612", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-08T12:22:18.279562+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T04:19:38.748920+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5368612", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T12:56:53.956707+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T04:54:20.845170+00:00", "targetGpu": "Biren_166m", "taskId": "5369290", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T12:56:53.956707+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T04:54:20.845170+00:00", "targetGpu": "Biren_166m", "taskId": "5369290", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T13:40:06.048902+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T05:37:38.062655+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5370970", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-08T13:40:06.048902+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-Base", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3415340496, "estimatedRequiredGiB": 3.834, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3430794465, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3430794465}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-08T05:37:38.062655+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5370970", "taskType": "text-generation", "verifyResult": null}