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

state: generation 5230 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-09-10 15:29:43 +00:00
parent 35f5d18664
commit 4eaabbbd50
9 changed files with 1144 additions and 1145 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1311,7 +1311,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-10T15:23:51.438109+00:00", "generatedAt": "2026-09-10T15:27:10.037984+00:00",
"summary": { "summary": {
"activeBlockCount": 66, "activeBlockCount": 66,
"byGpuFramework": { "byGpuFramework": {

536
.modelhub_state/market_intelligence.json
View File

@@ -3,106 +3,106 @@
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-09-10T15:16:33.850208+00:00", "communityUpdatedAt": "2026-09-10T15:16:33.850208+00:00",
"frameworkAttemptedAt": "2026-09-10T12:35:14.692612+00:00", "frameworkAttemptedAt": "2026-09-10T15:27:32.924657+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
"text-generation": { "text-generation": {
"Ascend_910-b3": { "Ascend_910-b3": {
"llamacpp": { "llamacpp": {
"framework": "llamacpp", "framework": "llamacpp",
"modelCount": 38318, "modelCount": 38338,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 18283, "successCount": 18295,
"successRate": 0.47713868155958034, "successRate": 0.47720277531430955,
"wilsonLowerBound": 0.47214006949864223 "wilsonLowerBound": 0.47220543078048205
}, },
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 50542, "modelCount": 50568,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 14324, "successCount": 14328,
"successRate": 0.28340785881049424, "successRate": 0.28334124347413386,
"wilsonLowerBound": 0.27949552744451256 "wilsonLowerBound": 0.27943019786424367
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"modelCount": 1770, "modelCount": 1789,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 445, "successCount": 449,
"successRate": 0.2514124293785311, "successRate": 0.2509782001117943,
"wilsonLowerBound": 0.2317546860465486 "wilsonLowerBound": 0.23143456102944407
} }
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"llamacpp": { "llamacpp": {
"framework": "llamacpp", "framework": "llamacpp",
"modelCount": 31396, "modelCount": 31416,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 13506, "successCount": 13521,
"successRate": 0.43018218881386167, "successRate": 0.43038579067990834,
"wilsonLowerBound": 0.42471443238148554 "wilsonLowerBound": 0.42491943017841394
}, },
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 36514, "modelCount": 36525,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 10437, "successCount": 10442,
"successRate": 0.2858355699183875, "successRate": 0.285886379192334,
"wilsonLowerBound": 0.2812239942679824 "wilsonLowerBound": 0.28127524230104706
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"modelCount": 6942, "modelCount": 6968,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 3194, "successCount": 3199,
"successRate": 0.460097954479977, "successRate": 0.4590987370838117,
"wilsonLowerBound": 0.4483986894698718 "wilsonLowerBound": 0.4474237173995597
} }
}, },
"Biren_166m": { "Biren_166m": {
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 63790, "modelCount": 63793,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 12060, "successCount": 12060,
"successRate": 0.18905784605737577, "successRate": 0.18904895521452197,
"wilsonLowerBound": 0.1860380147747332 "wilsonLowerBound": 0.18602924981833124
}, },
"vllm_fix_tokenizer": { "vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelCount": 13800, "modelCount": 13844,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 2726, "successCount": 2735,
"successRate": 0.19753623188405797, "successRate": 0.19755850910141579,
"wilsonLowerBound": 0.19097797620808124 "wilsonLowerBound": 0.1910102609114936
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"modelCount": 5147, "modelCount": 5151,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 36, "successCount": 37,
"successRate": 0.006994365649893142, "successRate": 0.007183071248301301,
"wilsonLowerBound": 0.005056576682829683 "wilsonLowerBound": 0.005215910778690411
} }
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 25953, "modelCount": 25961,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 3186, "successCount": 3187,
"successRate": 0.12276037452317651, "successRate": 0.12276106467393398,
"wilsonLowerBound": 0.1188235595334533 "wilsonLowerBound": 0.11882483798483397
}, },
"vllm-customized": { "vllm-customized": {
"framework": "vllm-customized", "framework": "vllm-customized",
@@ -115,23 +115,23 @@
}, },
"vllm-mlu": { "vllm-mlu": {
"framework": "vllm-mlu", "framework": "vllm-mlu",
"modelCount": 9391, "modelCount": 9407,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 4077, "successCount": 4084,
"successRate": 0.434139069321691, "successRate": 0.43414478579781013,
"wilsonLowerBound": 0.424143358656614 "wilsonLowerBound": 0.4241575354389301
} }
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 24027, "modelCount": 24030,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 3770, "successCount": 3770,
"successRate": 0.15690681316851876, "successRate": 0.15688722430295465,
"wilsonLowerBound": 0.1523626843060331 "wilsonLowerBound": 0.1523436123834872
}, },
"vllm-customized": { "vllm-customized": {
"framework": "vllm-customized", "framework": "vllm-customized",
@@ -144,50 +144,50 @@
}, },
"vllm-mlu": { "vllm-mlu": {
"framework": "vllm-mlu", "framework": "vllm-mlu",
"modelCount": 39385, "modelCount": 39427,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 9934, "successCount": 9945,
"successRate": 0.25222800558588293, "successRate": 0.25223831384584167,
"wilsonLowerBound": 0.2479631553725973 "wilsonLowerBound": 0.24797566376420394
} }
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"transformers": { "transformers": {
"framework": "transformers", "framework": "transformers",
"modelCount": 22914, "modelCount": 22915,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 3026, "successCount": 3026,
"successRate": 0.1320590032294667, "successRate": 0.1320532402356535,
"wilsonLowerBound": 0.1277369743815997 "wilsonLowerBound": 0.12773138638590842
}, },
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 86481, "modelCount": 86485,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 9762, "successCount": 9762,
"successRate": 0.11288028584313317, "successRate": 0.11287506504018038,
"wilsonLowerBound": 0.11078836443747443 "wilsonLowerBound": 0.11078323440993057
}, },
"vllm-patch-tokenizer": { "vllm-patch-tokenizer": {
"framework": "vllm-patch-tokenizer", "framework": "vllm-patch-tokenizer",
"modelCount": 38609, "modelCount": 38614,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 4738, "successCount": 4738,
"successRate": 0.12271750110077961, "successRate": 0.12270161081473041,
"wilsonLowerBound": 0.11948206919093914 "wilsonLowerBound": 0.11946656975844437
}, },
"vllm_fix_tokenizer": { "vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelCount": 26113, "modelCount": 26133,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 3210, "successCount": 3213,
"successRate": 0.1229272776011948, "successRate": 0.12294799678567328,
"wilsonLowerBound": 0.11900002209957782 "wilsonLowerBound": 0.11902193180839078
} }
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
@@ -202,30 +202,30 @@
}, },
"transformers": { "transformers": {
"framework": "transformers", "framework": "transformers",
"modelCount": 5051, "modelCount": 5054,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 562, "successCount": 562,
"successRate": 0.11126509602058998, "successRate": 0.111199050257222,
"wilsonLowerBound": 0.10288651808446177 "wilsonLowerBound": 0.10282517065480763
}, },
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 112422, "modelCount": 112425,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 16502, "successCount": 16502,
"successRate": 0.14678621622102436, "successRate": 0.14678229931065154,
"wilsonLowerBound": 0.1447295643963279 "wilsonLowerBound": 0.14472569775049507
}, },
"vllm_0_17_0_corex_4_4_0": { "vllm_0_17_0_corex_4_4_0": {
"framework": "vllm_0_17_0_corex_4_4_0", "framework": "vllm_0_17_0_corex_4_4_0",
"modelCount": 15606, "modelCount": 15613,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 3187, "successCount": 3188,
"successRate": 0.2042163270536973, "successRate": 0.2041888170114648,
"wilsonLowerBound": 0.19796458864174885 "wilsonLowerBound": 0.19793878702309592
}, },
"vllm_fix_tokenizer": { "vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
@@ -238,12 +238,12 @@
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"modelCount": 6020, "modelCount": 6025,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 469, "successCount": 469,
"successRate": 0.07790697674418605, "successRate": 0.07784232365145229,
"wilsonLowerBound": 0.07140227111708827 "wilsonLowerBound": 0.07134281712711635
} }
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
@@ -258,81 +258,81 @@
}, },
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 29851, "modelCount": 29865,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 5085, "successCount": 5092,
"successRate": 0.1703460520585575, "successRate": 0.17050058597019924,
"wilsonLowerBound": 0.16612380778830965 "wilsonLowerBound": 0.16627776573653213
} }
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 60731, "modelCount": 60733,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 12375, "successCount": 12376,
"successRate": 0.20376743343597176, "successRate": 0.20377718867831326,
"wilsonLowerBound": 0.2005826178036079 "wilsonLowerBound": 0.20059236750741152
}, },
"vllm_fix_tokenizer": { "vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelCount": 5963, "modelCount": 5978,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 1765, "successCount": 1768,
"successRate": 0.29599195036055675, "successRate": 0.29575108732017397,
"wilsonLowerBound": 0.2845397771768032 "wilsonLowerBound": 0.28431600169064586
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"modelCount": 11689, "modelCount": 11706,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 3070, "successCount": 3073,
"successRate": 0.26264008897253827, "successRate": 0.26251494959849647,
"wilsonLowerBound": 0.2547411183645426 "wilsonLowerBound": 0.2546229223317426
} }
}, },
"MetaX_c-500": { "MetaX_c-500": {
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 58107, "modelCount": 58155,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 15820, "successCount": 15830,
"successRate": 0.2722563546560655, "successRate": 0.2722035938440375,
"wilsonLowerBound": 0.26865223630882573 "wilsonLowerBound": 0.26860117980036025
} }
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"llamacpp": { "llamacpp": {
"framework": "llamacpp", "framework": "llamacpp",
"modelCount": 45825, "modelCount": 45831,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 19871, "successCount": 19877,
"successRate": 0.4336279323513366, "successRate": 0.43370207937858657,
"wilsonLowerBound": 0.42909620642371943 "wilsonLowerBound": 0.42917055264073056
}, },
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 34986, "modelCount": 35052,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 2968, "successCount": 2968,
"successRate": 0.08483393357342937, "successRate": 0.08467419833390391,
"wilsonLowerBound": 0.08195958326032747 "wilsonLowerBound": 0.08180502284967742
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"framework": "vllm_tokenizer_patch", "framework": "vllm_tokenizer_patch",
"modelCount": 203, "modelCount": 211,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"wilsonLowerBound": 1.702505035850099e-18 "wilsonLowerBound": 0.0
} }
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
@@ -356,12 +356,12 @@
}, },
"vllm_fix_tokenizer": { "vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelCount": 5360, "modelCount": 5367,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 2244, "successCount": 2248,
"successRate": 0.41865671641791047, "successRate": 0.4188559716787777,
"wilsonLowerBound": 0.40551212475467374 "wilsonLowerBound": 0.4057188914791776
} }
}, },
"Vastai_va16": { "Vastai_va16": {
@@ -376,161 +376,161 @@
}, },
"vllm_fix_tokenizer": { "vllm_fix_tokenizer": {
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelCount": 9834, "modelCount": 9857,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 3381, "successCount": 3390,
"successRate": 0.3438071995118975, "successRate": 0.3439180277975043,
"wilsonLowerBound": 0.33448201885340845 "wilsonLowerBound": 0.3346028962130698
} }
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"llamacpp": { "llamacpp": {
"framework": "llamacpp", "framework": "llamacpp",
"modelCount": 25567, "modelCount": 25585,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 12857, "successCount": 12865,
"successRate": 0.5028747995462901, "successRate": 0.5028336916161814,
"wilsonLowerBound": 0.49674597776775475 "wilsonLowerBound": 0.4967070292687963
}, },
"vllm": { "vllm": {
"framework": "vllm", "framework": "vllm",
"modelCount": 60420, "modelCount": 60431,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 5862, "successCount": 5864,
"successRate": 0.09702085402184707, "successRate": 0.09703628932170574,
"wilsonLowerBound": 0.0946862739354135 "wilsonLowerBound": 0.0947017509028485
}, },
"vllm-patch-tokenizer": { "vllm-patch-tokenizer": {
"framework": "vllm-patch-tokenizer", "framework": "vllm-patch-tokenizer",
"modelCount": 11994, "modelCount": 12006,
"officialConfigError": null, "officialConfigError": null,
"officialConfigValid": true, "officialConfigValid": true,
"successCount": 1622, "successCount": 1628,
"successRate": 0.13523428380857094, "successRate": 0.13559886723305015,
"wilsonLowerBound": 0.1292307288142234 "wilsonLowerBound": 0.1295911942318147
} }
} }
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-10T15:22:18.248614+00:00", "generatedAt": "2026-09-10T15:27:32.924657+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1077.1384615384616, "backlogHours": 1077.0923076923077,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b3", "gpu": "Ascend_910-b3",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 1.3023494599865717, "qualityFactor": 1.504632795098374,
"queueFactor": 0.9508142077470051, "queueFactor": 0.9512896617649836,
"queueWeight": 0.9508142077470051, "queueWeight": 0.9512896617649836,
"recentSuccess": 51, "recentSuccess": 54,
"recentSuccessRate": 0.3923076923076923, "recentSuccessRate": 0.4153846153846154,
"recentTerminal": 130, "recentTerminal": 130,
"recentWilsonLowerBound": 0.3126200051001405, "recentWilsonLowerBound": 0.3342905969843901,
"running": 8, "running": 7,
"selectionWeight": 1.238292370006872, "selectionWeight": 1.431341622729634,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 21.666666666666668, "throughputPerHour": 21.666666666666668,
"waiting": 23338 "waiting": 23337
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 973.3136094674555, "backlogHours": 996.8363636363637,
"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": 0.9886513030818428, "qualityFactor": 1.087693595098827,
"queueFactor": 0.965380391416169, "queueFactor": 0.9624033694620674,
"queueWeight": 0.965380391416169, "queueWeight": 0.9624033694620674,
"recentSuccess": 58, "recentSuccess": 59,
"recentSuccessRate": 0.3431952662721893, "recentSuccessRate": 0.3575757575757576,
"recentTerminal": 169, "recentTerminal": 165,
"recentWilsonLowerBound": 0.27581302397641744, "recentWilsonLowerBound": 0.2884481904837394,
"running": 8, "running": 7,
"selectionWeight": 0.954424581943255, "selectionWeight": 1.0467999808654207,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 28.166666666666668, "throughputPerHour": 27.5,
"waiting": 27415 "waiting": 27413
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 128.98536585365855, "backlogHours": 132.8140703517588,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.24647406477127937, "qualityFactor": 0.24614996127901195,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 40, "recentSuccess": 39,
"recentSuccessRate": 0.1951219512195122, "recentSuccessRate": 0.19597989949748743,
"recentTerminal": 205, "recentTerminal": 199,
"recentWilsonLowerBound": 0.14668991695050224, "recentWilsonLowerBound": 0.14680692645920698,
"running": 8, "running": 8,
"selectionWeight": 0.32041628420266316, "selectionWeight": 0.3199949496627155,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 34.166666666666664, "throughputPerHour": 33.166666666666664,
"waiting": 4407 "waiting": 4405
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1021.7349397590361, "backlogHours": 1046.5185185185185,
"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": 0.13799428842124495, "qualityFactor": 0.11984357842622166,
"queueFactor": 0.9583753964830888, "queueFactor": 0.9554075700017707,
"queueWeight": 0.9583753964830888, "queueWeight": 0.9554075700017707,
"recentSuccess": 15, "recentSuccess": 14,
"recentSuccessRate": 0.18072289156626506, "recentSuccessRate": 0.1728395061728395,
"recentTerminal": 83, "recentTerminal": 81,
"recentWilsonLowerBound": 0.1126926689223679, "recentWilsonLowerBound": 0.10584307626279289,
"running": 7, "running": 6,
"selectionWeight": 0.13225033087811233, "selectionWeight": 0.11449946204451307,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 13.833333333333334, "throughputPerHour": 13.5,
"waiting": 14134 "waiting": 14128
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 432.59016393442624, "backlogHours": 418.85714285714283,
"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": 0.3773376449381269, "qualityFactor": 0.4493221962021021,
"queueFactor": 1.0902469907359134, "queueFactor": 1.0960763996917333,
"queueWeight": 1.0902469907359134, "queueWeight": 1.0960763996917333,
"recentSuccess": 30, "recentSuccess": 33,
"recentSuccessRate": 0.2459016393442623, "recentSuccessRate": 0.2619047619047619,
"recentTerminal": 122, "recentTerminal": 126,
"recentWilsonLowerBound": 0.17802151523932291, "recentWilsonLowerBound": 0.19299483361516778,
"running": 7, "running": 7,
"selectionWeight": 0.4113912318851694, "selectionWeight": 0.4924914551147827,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.333333333333332, "throughputPerHour": 21.0,
"waiting": 8796 "waiting": 8796
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 66.90140845070422, "backlogHours": 67.85714285714286,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -539,197 +539,197 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 17, "recentSuccess": 16,
"recentSuccessRate": 0.07981220657276995, "recentSuccessRate": 0.0761904761904762,
"recentTerminal": 213, "recentTerminal": 210,
"recentWilsonLowerBound": 0.05042523581880395, "recentWilsonLowerBound": 0.047438977513945844,
"running": 1, "running": 1,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": false,
"throughputPerHour": 35.5, "throughputPerHour": 35.0,
"waiting": 2375 "waiting": 2375
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 117.6923076923077, "backlogHours": 120.15706806282724,
"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": 0.0647465175359186, "qualityFactor": 0.0676123502754561,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 23, "recentSuccess": 23,
"recentSuccessRate": 0.11794871794871795, "recentSuccessRate": 0.12041884816753927,
"recentTerminal": 195, "recentTerminal": 191,
"recentWilsonLowerBound": 0.07989354857234383, "recentWilsonLowerBound": 0.08159575665748214,
"running": 1, "running": 1,
"selectionWeight": 0.08417047279669419, "selectionWeight": 0.08789605535809294,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 32.5, "throughputPerHour": 31.833333333333332,
"waiting": 3825 "waiting": 3825
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 1855.4399999999998, "backlogHours": 1932.375,
"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": 0.18117436275647994, "qualityFactor": 0.25508215803483625,
"queueFactor": 0.8763333818567766, "queueFactor": 0.8714390238547999,
"queueWeight": 0.8763333818567766, "queueWeight": 0.8714390238547999,
"recentSuccess": 11, "recentSuccess": 12,
"recentSuccessRate": 0.22, "recentSuccessRate": 0.25,
"recentTerminal": 50, "recentTerminal": 48,
"recentWilsonLowerBound": 0.1275378622430229, "recentWilsonLowerBound": 0.1492048880971003,
"running": 2, "running": 2,
"selectionWeight": 0.15876914202013248, "selectionWeight": 0.2222885468006535,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.333333333333334, "throughputPerHour": 8.0,
"waiting": 15462 "waiting": 15459
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 692.1063829787234, "backlogHours": 684.8210526315789,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.4210453294615219, "qualityFactor": 0.45523063755852883,
"queueFactor": 1.0160392014722135, "queueFactor": 1.0181555905320407,
"queueWeight": 1.0160392014722135, "queueWeight": 1.0181555905320407,
"recentSuccess": 25, "recentSuccess": 26,
"recentSuccessRate": 0.26595744680851063, "recentSuccessRate": 0.2736842105263158,
"recentTerminal": 94, "recentTerminal": 95,
"recentWilsonLowerBound": 0.1871148582279006, "recentWilsonLowerBound": 0.19414427878715157,
"running": 7, "running": 7,
"selectionWeight": 0.42779856032968977, "selectionWeight": 0.4634956186116813,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.666666666666666, "throughputPerHour": 15.833333333333334,
"waiting": 10843 "waiting": 10843
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 599.7894736842105, "backlogHours": 584.3076923076923,
"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": 0.3668089035745469, "qualityFactor": 0.3783077320646403,
"queueFactor": 1.0380937271106694, "queueFactor": 1.0426882394039771,
"queueWeight": 1.0380937271106694, "queueWeight": 1.0426882394039771,
"recentSuccess": 28, "recentSuccess": 29,
"recentSuccessRate": 0.24561403508771928, "recentSuccessRate": 0.24786324786324787,
"recentTerminal": 114, "recentTerminal": 117,
"recentWilsonLowerBound": 0.17574622644308974, "recentWilsonLowerBound": 0.1784782855379003,
"running": 4, "running": 4,
"selectionWeight": 0.3807820218490795, "selectionWeight": 0.3944570230993913,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 19.0, "throughputPerHour": 19.5,
"waiting": 11396 "waiting": 11394
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1907.2835820895523, "backlogHours": 1879.0588235294117,
"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": 1.025898745090207, "qualityFactor": 0.9878212979600234,
"queueFactor": 0.8727183388955203, "queueFactor": 0.8751039805539271,
"queueWeight": 0.8727183388955203, "queueWeight": 0.8751039805539271,
"recentSuccess": 26, "recentSuccess": 26,
"recentSuccessRate": 0.3880597014925373, "recentSuccessRate": 0.38235294117647056,
"recentTerminal": 67, "recentTerminal": 68,
"recentWilsonLowerBound": 0.2804887105692933, "recentWilsonLowerBound": 0.2760927529710457,
"running": 4, "running": 4,
"selectionWeight": 0.8953206486901243, "selectionWeight": 0.8644463499207634,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.166666666666666, "throughputPerHour": 11.333333333333334,
"waiting": 21298 "waiting": 21296
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 3852.2727272727275, "backlogHours": 3684.782608695652,
"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": 1.2533531071700206, "qualityFactor": 1.120483029902168,
"queueFactor": 0.7853781937174696, "queueFactor": 0.7910226788918543,
"queueWeight": 0.7853781937174696, "queueWeight": 0.7910226788918543,
"recentSuccess": 11, "recentSuccess": 11,
"recentSuccessRate": 0.5, "recentSuccessRate": 0.4782608695652174,
"recentTerminal": 22, "recentTerminal": 23,
"recentWilsonLowerBound": 0.3072180469247956, "recentWilsonLowerBound": 0.29236869539945726,
"running": 2, "running": 2,
"selectionWeight": 0.9843561993993689, "selectionWeight": 0.8863274879660746,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 3.6666666666666665, "throughputPerHour": 3.8333333333333335,
"waiting": 14125 "waiting": 14125
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 847.0140845070422, "backlogHours": 859.3714285714286,
"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": 0.6414138264514839, "qualityFactor": 0.660853348951212,
"queueFactor": 0.9857182512242489, "queueFactor": 0.9840645319666167,
"queueWeight": 0.9857182512242489, "queueWeight": 0.9840645319666167,
"recentSuccess": 23, "recentSuccess": 23,
"recentSuccessRate": 0.323943661971831, "recentSuccessRate": 0.32857142857142857,
"recentTerminal": 71, "recentTerminal": 70,
"recentWilsonLowerBound": 0.22657056384385282, "recentWilsonLowerBound": 0.2299871182671781,
"running": 16, "running": 16,
"selectionWeight": 0.6322533153208106, "selectionWeight": 0.6503223415342456,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.833333333333334, "throughputPerHour": 11.666666666666666,
"waiting": 10023 "waiting": 10026
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 485.3831775700935, "backlogHours": 476.31192660550454,
"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": 2.5, "qualityFactor": 2.5,
"queueFactor": 1.0715777430310858, "queueFactor": 1.0751448952718026,
"queueWeight": 1.0715777430310858, "queueWeight": 1.0751448952718026,
"recentSuccess": 55, "recentSuccess": 56,
"recentSuccessRate": 0.514018691588785, "recentSuccessRate": 0.5137614678899083,
"recentTerminal": 107, "recentTerminal": 109,
"recentWilsonLowerBound": 0.42048422635928223, "recentWilsonLowerBound": 0.4210714006745304,
"running": 6, "running": 5,
"selectionWeight": 2.6789443575777145, "selectionWeight": 2.6878622381795063,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.833333333333332, "throughputPerHour": 18.166666666666668,
"waiting": 8656 "waiting": 8653
} }
}, },
"queueAttemptedAt": "2026-09-10T15:16:33.850208+00:00", "queueAttemptedAt": "2026-09-10T15:27:32.924657+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-10T15:16:33.850208+00:00", "queueUpdatedAt": "2026-09-10T15:27:32.924657+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Iluvatar_mrv-100", "Iluvatar_mrv-100",

1506
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

204
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-10T15:19:40.193833+00:00", "generatedAt": "2026-09-10T15:27:10.017950+00:00",
"lastSyncTime": "2026-09-10T15:19:40.009069+00:00", "lastSyncTime": "2026-09-10T15:27:09.820580+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1596,11 +1596,11 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 7, "decisionTotal": 7,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 18, "ambiguous_runtime": 19,
"framework_architecture_unsupported": 7, "framework_architecture_unsupported": 7,
"参数/模板问题": 3 "参数/模板问题": 3
}, },
"failureCount": 28, "failureCount": 29,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"pendingCount": 0, "pendingCount": 0,
@@ -1610,8 +1610,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 28, "total": 29,
"unresolvedFailureCount": 21 "unresolvedFailureCount": 22
}, },
"Cambricon_mlu-370-x8|vllm|text-generation": { "Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3, "attributableFailureCount": 3,
@@ -1906,9 +1906,9 @@
}, },
"MetaX_c-500|vllm|text-generation": { "MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 45, "attributableFailureCount": 45,
"decisionFailureRate": 0.9783, "decisionFailureRate": 0.9574,
"decisionSuccessRate": 0.0217, "decisionSuccessRate": 0.0426,
"decisionTotal": 46, "decisionTotal": 47,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 7, "ambiguous_runtime": 7,
"backend_operator": 26, "backend_operator": 26,
@@ -1918,16 +1918,16 @@
"参数/模板问题": 9 "参数/模板问题": 9
}, },
"failureCount": 61, "failureCount": 61,
"failureRate": 0.9839, "failureRate": 0.9683,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 2,
"successRate": 0.0161, "successRate": 0.0317,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 62, "total": 63,
"unresolvedFailureCount": 16 "unresolvedFailureCount": 16
}, },
"Mthreads_s4000|llamacpp|text-generation": { "Mthreads_s4000|llamacpp|text-generation": {
@@ -2317,9 +2317,9 @@
}, },
"vllm": { "vllm": {
"attributableFailureCount": 239, "attributableFailureCount": 239,
"decisionFailureRate": 0.9958, "decisionFailureRate": 0.9917,
"decisionSuccessRate": 0.0042, "decisionSuccessRate": 0.0083,
"decisionTotal": 240, "decisionTotal": 241,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 172, "ambiguous_runtime": 172,
"backend_operator": 32, "backend_operator": 32,
@@ -2333,13 +2333,13 @@
"参数/模板问题": 24 "参数/模板问题": 24
}, },
"failureCount": 436, "failureCount": 436,
"failureRate": 0.9977, "failureRate": 0.9954,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 1, "successCount": 2,
"successRate": 0.0023, "successRate": 0.0046,
"total": 437, "total": 438,
"unresolvedFailureCount": 196 "unresolvedFailureCount": 196
}, },
"vllm-mlu": { "vllm-mlu": {
@@ -2348,19 +2348,19 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 7, "decisionTotal": 7,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 18, "ambiguous_runtime": 19,
"framework_architecture_unsupported": 7, "framework_architecture_unsupported": 7,
"参数/模板问题": 3 "参数/模板问题": 3
}, },
"failureCount": 28, "failureCount": 29,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 28, "total": 29,
"unresolvedFailureCount": 21 "unresolvedFailureCount": 22
}, },
"vllm-patch-tokenizer": { "vllm-patch-tokenizer": {
"attributableFailureCount": 3, "attributableFailureCount": 3,
@@ -2443,7 +2443,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-10T15:19:40.187828+00:00", "generatedAt": "2026-09-10T15:27:10.014184+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 26, "attributableFailureCount": 26,
@@ -2545,22 +2545,22 @@
"decisionSuccessRate": 0.1053, "decisionSuccessRate": 0.1053,
"decisionTotal": 19, "decisionTotal": 19,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 37, "ambiguous_runtime": 38,
"framework_architecture_unsupported": 15, "framework_architecture_unsupported": 15,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 18, "参数/模板问题": 18,
"验证失败": 22 "验证失败": 22
}, },
"failureCount": 94, "failureCount": 95,
"failureRate": 0.9792, "failureRate": 0.9794,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 2,
"successRate": 0.0208, "successRate": 0.0206,
"total": 96, "total": 97,
"unresolvedFailureCount": 77 "unresolvedFailureCount": 78
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -2651,9 +2651,9 @@
}, },
"MetaX_c-500": { "MetaX_c-500": {
"attributableFailureCount": 45, "attributableFailureCount": 45,
"decisionFailureRate": 0.8182, "decisionFailureRate": 0.8036,
"decisionSuccessRate": 0.1818, "decisionSuccessRate": 0.1964,
"decisionTotal": 55, "decisionTotal": 56,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 7, "ambiguous_runtime": 7,
"backend_operator": 26, "backend_operator": 26,
@@ -2664,13 +2664,13 @@
"验证失败": 48 "验证失败": 48
}, },
"failureCount": 117, "failureCount": 117,
"failureRate": 0.9213, "failureRate": 0.9141,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 10, "successCount": 11,
"successRate": 0.0787, "successRate": 0.0859,
"total": 127, "total": 128,
"unresolvedFailureCount": 72 "unresolvedFailureCount": 72
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
@@ -2931,9 +2931,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 2 "ambiguous_runtime": 3
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"modelType": "phi3", "modelType": "phi3",
@@ -2945,8 +2945,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 3
}, },
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|compressed-tensors": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -3730,25 +3730,25 @@
}, },
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": { "MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 7, "attributableFailureCount": 7,
"decisionFailureRate": 1.0, "decisionFailureRate": 0.875,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.125,
"decisionTotal": 7, "decisionTotal": 8,
"failureBreakdown": { "failureBreakdown": {
"backend_operator": 7 "backend_operator": 7
}, },
"failureCount": 7, "failureCount": 7,
"failureRate": 1.0, "failureRate": 0.875,
"framework": "vllm", "framework": "vllm",
"modelType": "starcoder2", "modelType": "starcoder2",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"quantizationMethod": "compressed-tensors", "quantizationMethod": "compressed-tensors",
"successCount": 0, "successCount": 1,
"successRate": 0.0, "successRate": 0.125,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 7, "total": 8,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": { "Mthreads_s4000|vllm|text-generation|glm_ocr|fp8": {
@@ -4147,11 +4147,11 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 4, "decisionTotal": 4,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 14, "ambiguous_runtime": 15,
"framework_architecture_unsupported": 4, "framework_architecture_unsupported": 4,
"参数/模板问题": 1 "参数/模板问题": 1
}, },
"failureCount": 19, "failureCount": 20,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -4163,8 +4163,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 19, "total": 20,
"unresolvedFailureCount": 15 "unresolvedFailureCount": 16
}, },
"Cambricon_mlu-370-x8|vllm|text-generation": { "Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3, "attributableFailureCount": 3,
@@ -4713,9 +4713,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1 "ambiguous_runtime": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"lastTerminalAt": "2026-09-08T20:25:19.301781+00:00", "lastTerminalAt": "2026-09-08T20:25:19.301781+00:00",
@@ -4728,8 +4728,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 2
}, },
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|compressed-tensors": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -5404,9 +5404,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1 "ambiguous_runtime": 2
}, },
"failureCount": 1, "failureCount": 2,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"loadSizeLog2Bucket": 33, "loadSizeLog2Bucket": 33,
@@ -5419,8 +5419,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 1, "total": 2,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 2
}, },
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|compressed-tensors|30": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen2|compressed-tensors|30": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -6810,14 +6810,14 @@
}, },
"MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|34": { "MetaX_c-500|vllm|text-generation|starcoder2|compressed-tensors|34": {
"attributableFailureCount": 2, "attributableFailureCount": 2,
"decisionFailureRate": 1.0, "decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.3333,
"decisionTotal": 2, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"backend_operator": 2 "backend_operator": 2
}, },
"failureCount": 2, "failureCount": 2,
"failureRate": 1.0, "failureRate": 0.6667,
"framework": "vllm", "framework": "vllm",
"loadSizeLog2Bucket": 34, "loadSizeLog2Bucket": 34,
"modelType": "starcoder2", "modelType": "starcoder2",
@@ -6825,11 +6825,11 @@
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"quantizationMethod": "compressed-tensors", "quantizationMethod": "compressed-tensors",
"successCount": 0, "successCount": 1,
"successRate": 0.0, "successRate": 0.3333,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Mthreads_s4000|vllm|text-generation|glm_ocr|fp8|30": { "Mthreads_s4000|vllm|text-generation|glm_ocr|fp8|30": {
@@ -7121,15 +7121,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1598, "terminalRecords": 1600,
"totalRecords": 1685, "totalRecords": 1687,
"totals": { "totals": {
"attributableFailureCount": 419, "attributableFailureCount": 419,
"decisionFailureRate": 0.8915, "decisionFailureRate": 0.8896,
"decisionSuccessRate": 0.1085, "decisionSuccessRate": 0.1104,
"decisionTotal": 470, "decisionTotal": 471,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 354, "ambiguous_runtime": 355,
"backend_operator": 39, "backend_operator": 39,
"framework_architecture_unsupported": 272, "framework_architecture_unsupported": 272,
"memory_capacity": 11, "memory_capacity": 11,
@@ -7141,49 +7141,49 @@
"参数/模板问题": 98, "参数/模板问题": 98,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1547, "failureCount": 1548,
"failureRate": 0.9681, "failureRate": 0.9675,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 3, "platformFailureCount": 3,
"successCount": 51, "successCount": 52,
"successRate": 0.0319, "successRate": 0.0325,
"total": 1598, "total": 1600,
"unresolvedFailureCount": 1125 "unresolvedFailureCount": 1126
}, },
"warnings": [ "warnings": [
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Biren_166m|unknown|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 MetaX_c-500|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。"
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1685, "summarizedRecords": 1687,
"version": 1 "version": 1
} }

12
.modelhub_state/queue_cleanup_latest.json
View File

@@ -116,13 +116,13 @@
"unsloth/LFM2-2.6B-Exp-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/unsloth/LFM2-2.6B-Exp-GGUF/resolve/master/config.json (status=404)", "unsloth/LFM2-2.6B-Exp-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/unsloth/LFM2-2.6B-Exp-GGUF/resolve/master/config.json (status=404)",
"z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)" "z-lab/Qwen3.8-27B-DFlash2-GGUF": "HttpJsonError: HTTP request failed for https://modelscope.cn/models/z-lab/Qwen3.8-27B-DFlash2-GGUF/resolve/master/config.json (status=404)"
}, },
"architectureModelConfigsComplete": 125, "architectureModelConfigsComplete": 123,
"architectureOnly": false, "architectureOnly": false,
"architecturePolicySkipped": { "architecturePolicySkipped": {
"frameworkCatalogUnknown": 2, "frameworkCatalogUnknown": 2,
"frameworkContextUnknown": 382, "frameworkContextUnknown": 377,
"modelArchitectureUnknown": 166, "modelArchitectureUnknown": 168,
"noMatchingBlock": 812, "noMatchingBlock": 810,
"partiallyBlockedFrameworkSet": 102, "partiallyBlockedFrameworkSet": 102,
"runningMatchedProtected": 0, "runningMatchedProtected": 0,
"submissionContextMismatch": 0, "submissionContextMismatch": 0,
@@ -165,12 +165,12 @@
"repositorySizeErrors": { "repositorySizeErrors": {
"empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete" "empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete"
}, },
"repositorySizesComplete": 266, "repositorySizesComplete": 267,
"skipped": { "skipped": {
"fitsKnownCapacity": 1080, "fitsKnownCapacity": 1080,
"gpuCapacityUnknown": 0, "gpuCapacityUnknown": 0,
"repositorySizeUnknown": 2 "repositorySizeUnknown": 2
}, },
"stopErrors": [], "stopErrors": [],
"uniqueModels": 267 "uniqueModels": 268
} }

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -280,6 +280,7 @@
{"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-mlu", "lastSyncTime": "2026-09-08T15:41:33.598990+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096479058, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096479058}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.888683+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712801", "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-mlu", "lastSyncTime": "2026-09-08T15:41:33.598990+00:00", "modelId": "RedHatAI/starcoder2-3b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4093180600, "estimatedRequiredGiB": 4.578, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 4096479058, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 3181366272, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4096479058}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.888683+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712801", "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-mlu", "lastSyncTime": "2026-09-08T20:25:19.301781+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.887685+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712810", "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-mlu", "lastSyncTime": "2026-09-08T20:25:19.301781+00:00", "modelId": "RedHatAI/Phi-3-mini-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4020365960, "estimatedRequiredGiB": 4.496, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 4022810352, "modelscopeLicense": "mit", "modelscopeParams": 3821079552, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4022810352}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.887685+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712810", "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-mlu", "lastSyncTime": "2026-09-08T18:40:55.416614+00:00", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3SmallForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8630134648, "estimatedRequiredGiB": 9.647, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3small", "modelscopeFileSize": 8632060880, "modelscopeLicense": "mit", "modelscopeParams": 7803314176, "modelscopeTags": ["license:mit", "model_type:phi3small", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8632060880}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.886454+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712804", "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-mlu", "lastSyncTime": "2026-09-08T18:40:55.416614+00:00", "modelId": "RedHatAI/Phi-3-small-128k-instruct-quantized.w8a16", "modelProfile": {"architectures": ["Phi3SmallForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8630134648, "estimatedRequiredGiB": 9.647, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3small", "modelscopeFileSize": 8632060880, "modelscopeLicense": "mit", "modelscopeParams": 7803314176, "modelscopeTags": ["license:mit", "model_type:phi3small", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8632060880}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.886454+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712804", "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-mlu", "lastSyncTime": "2026-09-10T15:27:09.820580+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293335560, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295942065, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295942065}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.810137+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712809", "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-mlu", "lastSyncTime": "2026-09-10T13:14:20.004644+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.808048+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712807", "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-mlu", "lastSyncTime": "2026-09-10T13:14:20.004644+00:00", "modelId": "RedHatAI/starcoder2-3b-FP8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3484485728, "estimatedRequiredGiB": 3.898, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 3487786133, "modelscopeLicense": "other", "modelscopeParams": 3181366272, "modelscopeTags": ["license:other", "model_type:starcoder2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 3487786133}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.808048+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712807", "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-mlu", "lastSyncTime": "2026-09-08T20:58:55.412656+00:00", "modelId": "RedHatAI/Qwen2.5-1.5B-quantized.w4a16", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1611497856, "estimatedRequiredGiB": 1.819, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 1627385309, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1781159424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:chat", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1627385309}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.804740+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712806", "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-mlu", "lastSyncTime": "2026-09-08T20:58:55.412656+00:00", "modelId": "RedHatAI/Qwen2.5-1.5B-quantized.w4a16", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1611497856, "estimatedRequiredGiB": 1.819, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 1627385309, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1781159424, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:chat", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1627385309}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.804740+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712806", "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-mlu", "lastSyncTime": "2026-09-08T15:41:33.599000+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2023929984, "estimatedRequiredGiB": 2.272, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033083373, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033083377}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.795745+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712800", "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-mlu", "lastSyncTime": "2026-09-08T15:41:33.599000+00:00", "modelId": "neuralmagic/Llama-3.2-1B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2023929984, "estimatedRequiredGiB": 2.272, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 2033083373, "modelscopeLicense": "llama3.2", "modelscopeParams": 1498482688, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2033083377}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T06:46:06.795745+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712800", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T03:17:11.503517+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:11:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4487542", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm", "lastSyncTime": "2026-09-08T03:17:11.503517+00:00", "modelId": "ysqlian/YZH_Model", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:11:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4487542", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T03:17:11.503505+00:00", "modelId": "nightmedia/Qwen3-4B-Element8-Eva-Heretic-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:05:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079944", "taskType": "text-generation", "verifyResult": -1} {"failReason": "model_load", "failureAction": "inspect_root_exception_then_llm_if_unknown", "failureCategory": "model_load", "failureClassificationReason": "broad_load_error", "failureCode": "MODEL_LOAD_FAILED", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T03:17:11.503505+00:00", "modelId": "nightmedia/Qwen3-4B-Element8-Eva-Heretic-mxfp4-mlx", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:05:21+00:00", "targetGpu": "Vastai_va16", "taskId": "4079944", "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", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-08T03:04:50.903963+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:01:23+00:00", "targetGpu": "Biren_166m", "taskId": "4610405", "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", "failureUnsupportedModelTypes": ["qwen3_5_moe"], "framework": "", "lastSyncTime": "2026-09-08T03:04:50.903963+00:00", "modelId": "mlx-community/Qwen3.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:01:23+00:00", "targetGpu": "Biren_166m", "taskId": "4610405", "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", "framework": "vllm", "lastSyncTime": "2026-09-08T03:04:50.903987+00:00", "modelId": "microsoft/Phi-3-small-128k-instruct", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T03:01:22+00:00", "targetGpu": "Vastai_va16", "taskId": "4079318", "taskType": "text-generation", "verifyResult": -1}

1
.modelhub_state/recovery_intents.jsonl
View File

@@ -645,6 +645,7 @@
{"batchId": "907987834148411ea675a5e6a75ca42a", "completedAt": "2026-09-10T14:46:38.200736+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-10T14:46:30.271611+00:00", "framework": "vllm", "intentId": "28a76d8eaec247d6bb2628db7901d520", "lastModified": "2026-09-10T05:57:11+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "reason": null, "reconciledAt": "2026-09-10T15:27:09.087043+00:00", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761530", "taskType": "text-generation"} {"batchId": "907987834148411ea675a5e6a75ca42a", "completedAt": "2026-09-10T14:46:38.200736+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-10T14:46:30.271611+00:00", "framework": "vllm", "intentId": "28a76d8eaec247d6bb2628db7901d520", "lastModified": "2026-09-10T05:57:11+00:00", "modelAddress": "https://modelscope.cn/models/CohereLabs/tiny-aya-en-thinker", "reason": null, "reconciledAt": "2026-09-10T15:27:09.087043+00:00", "repoId": "CohereLabs/tiny-aya-en-thinker", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761530", "taskType": "text-generation"}
{"batchId": "907987834148411ea675a5e6a75ca42a", "completedAt": "2026-09-10T14:46:38.200738+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-10T14:46:30.271653+00:00", "framework": "vllm", "intentId": "0a351039ed9e443999fbb111a9ba1df7", "lastModified": "2026-08-11T14:42:47+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "reason": null, "reconciledAt": "2026-09-10T15:27:09.087175+00:00", "repoId": "BAAI/AREX-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761531", "taskType": "text-generation"} {"batchId": "907987834148411ea675a5e6a75ca42a", "completedAt": "2026-09-10T14:46:38.200738+00:00", "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configSource": "modelhub_live", "createdAt": "2026-09-10T14:46:30.271653+00:00", "framework": "vllm", "intentId": "0a351039ed9e443999fbb111a9ba1df7", "lastModified": "2026-08-11T14:42:47+00:00", "modelAddress": "https://modelscope.cn/models/BAAI/AREX-Turbo", "reason": null, "reconciledAt": "2026-09-10T15:27:09.087175+00:00", "repoId": "BAAI/AREX-Turbo", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4761531", "taskType": "text-generation"}
{"batchId": "c3b3a3e3df6e4a6c8f33bece0f8ec90d", "completedAt": "2026-09-10T15:13:34.008724+00:00", "configFingerprint": "e4ab8f6cadfae4845d02aa9c1f89de5907e1f311ae817b1e8e370b501bd7f2e9", "configSource": "modelhub_live", "createdAt": "2026-09-10T15:13:25.575035+00:00", "framework": "llamacpp", "intentId": "4831e017dc354a2da3332acef4a9cf4d", "lastModified": "2026-09-10T14:58:25+00:00", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "reason": null, "reconciledAt": "2026-09-10T15:27:09.087463+00:00", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4761809", "taskType": "text-generation"} {"batchId": "c3b3a3e3df6e4a6c8f33bece0f8ec90d", "completedAt": "2026-09-10T15:13:34.008724+00:00", "configFingerprint": "e4ab8f6cadfae4845d02aa9c1f89de5907e1f311ae817b1e8e370b501bd7f2e9", "configSource": "modelhub_live", "createdAt": "2026-09-10T15:13:25.575035+00:00", "framework": "llamacpp", "intentId": "4831e017dc354a2da3332acef4a9cf4d", "lastModified": "2026-09-10T14:58:25+00:00", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "reason": null, "reconciledAt": "2026-09-10T15:27:09.087463+00:00", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "4761809", "taskType": "text-generation"}
{"batchId": "eb410d3235d340868c8cf6ab7434f833", "configFingerprint": "2be5f709184000d7e6bae759e29c6586ad3430b235ef3eb2dab86a5c2487a2f7", "configSource": "modelhub_live", "createdAt": "2026-09-10T15:29:42.957367+00:00", "framework": "llamacpp", "intentId": "b88d7ddd69e94be882df8a64076be3e2", "lastModified": "2026-09-10T14:58:25+00:00", "modelAddress": "https://modelscope.cn/models/webAI-Official/TwIL-LM3", "repoId": "webAI-Official/TwIL-LM3", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "93abbd86b4564ff2b94a94e46d15997c", "completedAt": "2026-09-10T02:01:15.152981+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-10T02:01:07.997982+00:00", "framework": "vllm", "intentId": "f62de0b86d234667845793d4dabba8be", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"} {"batchId": "93abbd86b4564ff2b94a94e46d15997c", "completedAt": "2026-09-10T02:01:15.152981+00:00", "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configSource": "modelhub_live", "createdAt": "2026-09-10T02:01:07.997982+00:00", "framework": "vllm", "intentId": "f62de0b86d234667845793d4dabba8be", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Iluvatar_mrv-100", "taskId": null, "taskType": "text-generation"}
{"batchId": "60b640169cee4eb6aeaf36aa752d68d4", "completedAt": "2026-09-09T21:08:33.584377+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-09T21:08:21.304731+00:00", "framework": "vllm_fix_tokenizer", "intentId": "31500eb429ef4b3cbc844e4096a6b5f6", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"} {"batchId": "60b640169cee4eb6aeaf36aa752d68d4", "completedAt": "2026-09-09T21:08:33.584377+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-09-09T21:08:21.304731+00:00", "framework": "vllm_fix_tokenizer", "intentId": "31500eb429ef4b3cbc844e4096a6b5f6", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Kunlunxin_p-800", "taskId": null, "taskType": "text-generation"}
{"batchId": "395e59f0f1df48fcb2e0269b69d9bce5", "completedAt": "2026-09-09T16:24:21.684805+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-09T16:24:14.160686+00:00", "framework": "vllm", "intentId": "e2523fa4e63645688fd5e7c0c7c1a5d5", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"} {"batchId": "395e59f0f1df48fcb2e0269b69d9bce5", "completedAt": "2026-09-09T16:24:21.684805+00:00", "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configSource": "modelhub_live", "createdAt": "2026-09-09T16:24:14.160686+00:00", "framework": "vllm", "intentId": "e2523fa4e63645688fd5e7c0c7c1a5d5", "repoId": "nv-community/Qwen3.8-27B-NVFP4", "safeConfigVector": {"dtype": "-", "gpuMemoryUtilization": 0.9, "gpuNum": 1, "maxModelLen": 4096, "tensorParallel": 1}, "status": "uniqueness_rejected", "targetGpu": "Biren_166m", "taskId": null, "taskType": "text-generation"}

22
manifest.json
View File

@@ -1,24 +1,24 @@
{ {
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "235d7475bd098befbcf8c18f39eb0741f5cfa3ce9428ecc170e36cb43290f04c", ".modelhub_state/architecture_compatibility_blacklist.json": "568ca073a7f43a3a3fb770afcc579db6ce7a5d45bbd87d171034761f422548c1",
".modelhub_state/architecture_history_backfill.json": "212e68ed32b8c9406e433da8bd736d14b608fd4dc8bce490120b00c43f527f40", ".modelhub_state/architecture_history_backfill.json": "212e68ed32b8c9406e433da8bd736d14b608fd4dc8bce490120b00c43f527f40",
".modelhub_state/market_intelligence.json": "53ff670dc86f3341335610c4ce38b4717d729b906dd9a64eb0131b4db5933f43", ".modelhub_state/market_intelligence.json": "e2624a55c80c0e1b5ed8e13203bd981a46a6a0ff2f1f701577a516c9f535aac7",
".modelhub_state/official_capabilities.json": "ee1e65d13607aca2ff9276b35341953e2234261c1645bbc5288009da97504605", ".modelhub_state/official_capabilities.json": "3d6016ce14b275ff12bdb7afe5652adbfdfb2b73a5248b463e0d284da831145b",
".modelhub_state/outcome_checkpoint.json": "108177bc497814844051121e936e96f0700fc5281361e3d9a5770d59f3746280", ".modelhub_state/outcome_checkpoint.json": "58029266bb92b932d377336c9fccb3b6ebe1a82cdd97af970a66ed989f9c8b82",
".modelhub_state/queue_cleanup_latest.json": "a596175137b8adfa14ee62a71c9a7bc915b25b1d8f0f57451a25c2e257396039", ".modelhub_state/queue_cleanup_latest.json": "c4c0c2f745124fbabf68b2aa082c5aeee0f45dbb41d40369e8064e674a33adbe",
".modelhub_state/recent_outcomes.jsonl": "1ec5cb7fbc28c985edb48f86fba95f976f7d0a1ce5ff1f48a9023fbdc22e6e77", ".modelhub_state/recent_outcomes.jsonl": "9e9cb1dd0f2d6f58384a1234e9beec7ab6c7ae3a92d636f21215b319e8b90f3a",
".modelhub_state/recovery_active_tasks.jsonl": "758f4706189a2f3afe240425077b9475217166dd358888f2f3dac2eea1c46ca8", ".modelhub_state/recovery_active_tasks.jsonl": "758f4706189a2f3afe240425077b9475217166dd358888f2f3dac2eea1c46ca8",
".modelhub_state/recovery_intents.jsonl": "ff4fadd012130a96172439815e060600dba3b279610bbd31646053ea5dc7cca2", ".modelhub_state/recovery_intents.jsonl": "38d6d643700900c888bf36771e71c56c7952a68197c205c3b4beb73808f2083c",
".modelhub_state/routing_intelligence.json": "8901830c5979661bd91c7ff07bb088fddcd15c778651eb726d0d1d62df70e228", ".modelhub_state/routing_intelligence.json": "8901830c5979661bd91c7ff07bb088fddcd15c778651eb726d0d1d62df70e228",
".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03", ".modelhub_state/submission_exclusions.jsonl": "b2de1125bf1f3e0597cd50cc30b563a5bfee39459e843767163eb72101cebc03",
".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba", ".modelhub_state/worker_crashes.jsonl": "7fa483580e87374493226e80bcf40bf8044847acba70045c96fa175966a1a8ba",
"ledger/submissions.jsonl": "5cd9fb7f33b669b6f7abe4d47d9552e490231dcb1e0df0349f76c8eaac67656a", "ledger/submissions.jsonl": "5cd9fb7f33b669b6f7abe4d47d9552e490231dcb1e0df0349f76c8eaac67656a",
"outcomes/submissions.jsonl": "5562d3c4413dc849f39649dd11745b00e8dbafdf04c96bc271a89549f9ef0c92" "outcomes/submissions.jsonl": "c87ab0ad9e02c3f12d5e8f14b56e812e8fdfe26a8e271df3c60a3bfec5046918"
}, },
"generation": 5229, "generation": 5230,
"phase": "startup", "phase": "intent",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-10T15:27:09.162273+00:00", "updatedAt": "2026-09-10T15:29:43.016437+00:00",
"writerId": "18252d8a8ef94333abd55823b2d81c42" "writerId": "18252d8a8ef94333abd55823b2d81c42"
} }

4
outcomes/submissions.jsonl
View File

@@ -173,7 +173,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T11:53:42.913364+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9536343971, "modelscopeLicense": null, "modelscopeParams": 2519020032, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9536343971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T03:52:18.510578+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660434", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T11:53:42.913364+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9514532079, "estimatedRequiredGiB": 10.658, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9536343971, "modelscopeLicense": null, "modelscopeParams": 2519020032, "modelscopeTags": ["model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9536343971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T03:52:18.510578+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660434", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T12:21:22.998937+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T04:17:45.285806+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660827", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T12:21:22.998937+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-NVFP4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8818103892, "estimatedRequiredGiB": 9.883, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 8842796317, "modelscopeLicense": "mit", "modelscopeParams": 6728625904, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 8842796317}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T04:17:45.285806+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4660827", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T12:39:38.309054+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20034587064, "estimatedRequiredGiB": 22.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20054851725, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:qwen3.5-architecture", "custom_tag:gptq-pro", "custom_tag:gptq", "custom_tag:4-bit", "custom_tag:4bit", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:text-generation", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 20054851725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T04:38:16.005175+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4661079", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T12:39:38.309054+00:00", "modelId": "groxaxo/Qwen3.8-27B-GPTQ-Pro-4bit-g64-calib128", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20034587064, "estimatedRequiredGiB": 22.413, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20054851725, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen3.8", "custom_tag:qwen3.5-architecture", "custom_tag:gptq-pro", "custom_tag:gptq", "custom_tag:4-bit", "custom_tag:4bit", "custom_tag:mtp", "custom_tag:speculative-decoding", "custom_tag:text-generation", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "gptq", "repositoryOnDiskBytes": 20054851725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T04:38:16.005175+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4661079", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T13:08:06.614699+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a8", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785240496, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788612468, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 2, "consecutiveFailures": 2, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 2, "failureBreakdown": {"backend_operator": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastTerminalAt": "2026-09-05T10:14:38.509276+00:00", "modelType": "starcoder2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 17788612468}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T05:06:36.456528+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661426", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T13:08:06.614723+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T05:06:36.493823+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661437", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-06T13:08:06.614723+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-FP8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14289052464, "estimatedRequiredGiB": 15.972, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14291553638, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14291553638}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T05:06:36.493823+00:00", "targetGpu": "MetaX_c-500", "taskId": "4661437", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-06T14:42:01.034713+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T06:30:19.979390+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4662535", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-06T14:42:01.034713+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T06:30:19.979390+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4662535", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-06T15:03:37.399221+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T07:02:35.712857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4662918", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-09-06T15:03:37.399221+00:00", "modelId": "cyankiwi/Apodex-1.1-mini-AWQ-INT4", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 26119812080, "estimatedRequiredGiB": 29.233, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 26156887523, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35951822704, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:apodex", "custom_tag:arxiv:2608.23283"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 26156887523}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T07:02:35.712857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4662918", "taskType": "text-generation", "verifyResult": null}
@@ -244,7 +243,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T13:16:14.206207+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T05:08:32.946681+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4711416", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-08T13:16:14.206207+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T05:08:32.946681+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4711416", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614464+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:06.785300+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712808", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614464+00:00", "modelId": "zstack/qwen3-4b-fake", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 25165824, "estimatedRequiredGiB": 0.028, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 25169485, "modelscopeLicense": null, "modelscopeParams": 25165435, "modelscopeTags": ["model_type:qwen3", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 25169485}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:06.785300+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712808", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614275+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:06.799047+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712803", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614275+00:00", "modelId": "OpenBMB/MiniCPM5-2B", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557096, "estimatedRequiredGiB": 5.637, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5043805854, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5043805854}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:06.799047+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712803", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614439+00:00", "modelId": "RedHatAI/Phi-3-medium-128k-instruct-quantized.w8a8", "modelProfile": {"architectures": ["Phi3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14293335560, "estimatedRequiredGiB": 15.977, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "phi3", "modelscopeFileSize": 14295942065, "modelscopeLicense": "mit", "modelscopeParams": 13960238080, "modelscopeTags": ["license:mit", "model_type:phi3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14295942065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:06.810137+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712809", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614292+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:11.590454+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712813", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614292+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:11.590454+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712813", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614454+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:11.606547+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712821", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614454+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:11.606547+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712821", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614444+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:11.792714+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712824", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-08T14:58:38.614444+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T06:46:11.792714+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4712824", "taskType": "text-generation", "verifyResult": null}
@@ -570,7 +568,7 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009053+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.204766+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755596", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009053+00:00", "modelId": "primitive-ai/Nex-N2.5-mini-FP8", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 38136526544, "estimatedRequiredGiB": 42.65, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 38162746086, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:fp8", "custom_tag:quantized", "custom_tag:moe", "custom_tag:nex-n2.5", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 38162746086}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.204766+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755596", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009045+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.209710+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755597", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009045+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.209710+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755597", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009069+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "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": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:21:21.949441+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": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.214438+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755598", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-10T15:19:40.009069+00:00", "modelId": "BAAI/AREX-Turbo", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9078620368, "estimatedRequiredGiB": 10.18, "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": 9109259594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4539265536, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:agent", "custom_tag:deep-research", "custom_tag:reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:qwen3.5", "custom_tag:dense"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:21:21.949441+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": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9109259594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:12:26.214438+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4755598", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T07:23:10.180003+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4755805", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-10T15:27:09.820539+00:00", "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-10T07:23:10.180003+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4755805", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T07:33:41.787375+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4756078", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T07:33:41.787375+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4756078", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T07:50:25.385741+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4756398", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T07:50:25.385741+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4756398", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T09:52:16.471862+00:00", "targetGpu": "MetaX_c-500", "taskId": "4758203", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "CohereLabs/tiny-aya-en-thinker", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730844445, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:reasoning", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730844445}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-10T09:52:16.471862+00:00", "targetGpu": "MetaX_c-500", "taskId": "4758203", "taskType": "text-generation", "verifyResult": null}