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

state: generation 21783 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 09:57:56 +00:00
parent b23539f5c7
commit 0c1fefb935
10 changed files with 3039 additions and 3081 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2606,27 +2606,6 @@
"targetGpu": "Vastai_va16", "targetGpu": "Vastai_va16",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"vastai_va16|vllm|text-generation|architectures:gptneoforcausallm": {
"architectureSignature": "architectures:gptneoforcausallm",
"architectures": [
"gptneoforcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-07T09:45:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-07T09:45:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"KoboldAI/GPT-Neo-2.7B-Janeway"
],
"sourceTaskIds": [
"4079146"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
},
"vastai_va16|vllm|text-generation|architectures:llavallamaforcausallm": { "vastai_va16|vllm|text-generation|architectures:llavallamaforcausallm": {
"architectureSignature": "architectures:llavallamaforcausallm", "architectureSignature": "architectures:llavallamaforcausallm",
"architectures": [ "architectures": [
@@ -2836,9 +2815,9 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-07T09:37:05.051528+00:00", "generatedAt": "2026-10-07T09:53:21.538410+00:00",
"summary": { "summary": {
"activeBlockCount": 143, "activeBlockCount": 142,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 9, "Ascend_910-b3|vllm": 9,
"Ascend_910-b3|vllm_tokenizer_patch": 7, "Ascend_910-b3|vllm_tokenizer_patch": 7,
@@ -2862,7 +2841,7 @@
"Mthreads_s4000|vllm": 6, "Mthreads_s4000|vllm": 6,
"Sunrise_pt-200-x1|vllm": 3, "Sunrise_pt-200-x1|vllm": 3,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4, "Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
"Vastai_va16|vllm": 12, "Vastai_va16|vllm": 11,
"Vastai_va16|vllm_fix_tokenizer": 2, "Vastai_va16|vllm_fix_tokenizer": 2,
"hygon_k100-ai|vllm": 8, "hygon_k100-ai|vllm": 8,
"hygon_k100-ai|vllm-patch-tokenizer": 4 "hygon_k100-ai|vllm-patch-tokenizer": 4

300
.modelhub_state/market_intelligence.json
View File

@@ -434,121 +434,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-07T09:48:38.069449+00:00", "generatedAt": "2026-10-07T09:54:41.656922+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1005.548780487805, "backlogHours": 1037.0566037735848,
"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": 1.0445040272123471, "qualityFactor": 1.017558172125273,
"queueFactor": 1.0022639422411619, "queueFactor": 0.9981367712594166,
"queueWeight": 1.0022639422411619, "queueWeight": 0.9981367712594166,
"recentSuccess": 51, "recentSuccess": 48,
"recentSuccessRate": 0.31097560975609756, "recentSuccessRate": 0.3018867924528302,
"recentTerminal": 164, "recentTerminal": 159,
"recentWilsonLowerBound": 0.2451381121786042, "recentWilsonLowerBound": 0.23589451878319367,
"running": 7, "running": 8,
"selectionWeight": 1.046868724000617, "selectionWeight": 1.0156622284937538,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 27.333333333333332, "throughputPerHour": 26.5,
"waiting": 27485 "waiting": 27482
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1268.5774647887324, "backlogHours": 1305.0434782608695,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b4", "gpu": "Ascend_910-b4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.9679324035959381, "queueFactor": 0.9643100152802925,
"queueWeight": 0.9679324035959381, "queueWeight": 0.9643100152802925,
"recentSuccess": 63, "recentSuccess": 60,
"recentSuccessRate": 0.44366197183098594, "recentSuccessRate": 0.43478260869565216,
"recentTerminal": 142, "recentTerminal": 138,
"recentWilsonLowerBound": 0.364499679538778, "recentWilsonLowerBound": 0.3549471151477231,
"running": 7, "running": 8,
"selectionWeight": 2.419831008989845, "selectionWeight": 2.410775038200731,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.666666666666668, "throughputPerHour": 23.0,
"waiting": 30023 "waiting": 30016
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 132.79591836734696, "backlogHours": 135.46875,
"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": 0.26443705263165873, "qualityFactor": 0.29367512186355976,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 35, "recentSuccess": 35,
"recentSuccessRate": 0.17857142857142858, "recentSuccessRate": 0.18229166666666666,
"recentTerminal": 196, "recentTerminal": 192,
"recentWilsonLowerBound": 0.13129088009696172, "recentWilsonLowerBound": 0.13409212213072985,
"running": 6, "running": 7,
"selectionWeight": 0.3437681684211564, "selectionWeight": 0.38177765842262773,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 32.666666666666664, "throughputPerHour": 32.0,
"waiting": 4338 "waiting": 4335
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1369.6, "backlogHours": 1351.657894736842,
"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": 0.23786361378953835, "qualityFactor": 0.24469146368413294,
"queueFactor": 0.9568712714501738, "queueFactor": 0.9592469050401333,
"queueWeight": 0.9568712714501738, "queueWeight": 0.9592469050401333,
"recentSuccess": 15, "recentSuccess": 15,
"recentSuccessRate": 0.2, "recentSuccessRate": 0.19736842105263158,
"recentTerminal": 75, "recentTerminal": 76,
"recentWilsonLowerBound": 0.12512038203120296, "recentWilsonLowerBound": 0.12341879212336242,
"running": 6, "running": 7,
"selectionWeight": 0.22760485855852866, "selectionWeight": 0.2347195292287447,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.5, "throughputPerHour": 12.666666666666666,
"waiting": 17120 "waiting": 17121
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 461.1219512195122, "backlogHours": 468.694214876033,
"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": 0.5530662588572335, "qualityFactor": 0.6618560988702369,
"queueFactor": 1.126601197035025, "queueFactor": 1.124415918899644,
"queueWeight": 1.126601197035025, "queueWeight": 1.124415918899644,
"recentSuccess": 31, "recentSuccess": 32,
"recentSuccessRate": 0.25203252032520324, "recentSuccessRate": 0.2644628099173554,
"recentTerminal": 123, "recentTerminal": 121,
"recentWilsonLowerBound": 0.18360980012600733, "recentWilsonLowerBound": 0.1940040187978015,
"running": 7, "running": 7,
"selectionWeight": 0.6230851092682422, "selectionWeight": 0.7442015335905111,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.5, "throughputPerHour": 20.166666666666668,
"waiting": 9453 "waiting": 9452
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 46.80893300248139, "backlogHours": 44.93586698337292,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -557,197 +557,197 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 13, "recentSuccess": 14,
"recentSuccessRate": 0.03225806451612903, "recentSuccessRate": 0.0332541567695962,
"recentTerminal": 403, "recentTerminal": 421,
"recentWilsonLowerBound": 0.018946835349343365, "recentWilsonLowerBound": 0.019910173557583847,
"running": 12, "running": 9,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 67.16666666666667, "throughputPerHour": 70.16666666666667,
"waiting": 3144 "waiting": 3153
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 195.84615384615384, "backlogHours": 174.3835616438356,
"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": 0.35395336189694093, "qualityFactor": 0.25221108845506984,
"queueFactor": 1.2810182613963137, "queueFactor": 1.3,
"queueWeight": 1.2810182613963137, "queueWeight": 1.3,
"recentSuccess": 39, "recentSuccess": 37,
"recentSuccessRate": 0.2, "recentSuccessRate": 0.1689497716894977,
"recentTerminal": 195, "recentTerminal": 219,
"recentWilsonLowerBound": 0.14989626176513593, "recentWilsonLowerBound": 0.12512856219683152,
"running": 6, "running": 5,
"selectionWeight": 0.4534207202725995, "selectionWeight": 0.3278744149915908,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 32.5, "throughputPerHour": 36.5,
"waiting": 6365 "waiting": 6365
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 1636.1052631578948, "backlogHours": 1608.0,
"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": 0.6336774410609467, "qualityFactor": 0.7570153048131438,
"queueFactor": 0.931688836096815, "queueFactor": 0.9345822270485478,
"queueWeight": 0.931688836096815, "queueWeight": 0.9345822270485478,
"recentSuccess": 17, "recentSuccess": 18,
"recentSuccessRate": 0.2982456140350877, "recentSuccessRate": 0.3103448275862069,
"recentTerminal": 57, "recentTerminal": 58,
"recentWilsonLowerBound": 0.19532392409243257, "recentWilsonLowerBound": 0.20621934414805676,
"running": 2, "running": 2,
"selectionWeight": 0.5903901975228815, "selectionWeight": 0.7074930494821032,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 9.5, "throughputPerHour": 9.666666666666666,
"waiting": 15543 "waiting": 15544
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 404.82608695652175, "backlogHours": 401.9136690647482,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.15088693832642197, "qualityFactor": 0.1573869182913337,
"queueFactor": 1.1488208375074558, "queueFactor": 1.1506427567217319,
"queueWeight": 1.1488208375074558, "queueWeight": 1.1506427567217319,
"recentSuccess": 21, "recentSuccess": 21,
"recentSuccessRate": 0.15217391304347827, "recentSuccessRate": 0.1510791366906475,
"recentTerminal": 138, "recentTerminal": 139,
"recentWilsonLowerBound": 0.101736119387597, "recentWilsonLowerBound": 0.10098748819284317,
"running": 8, "running": 7,
"selectionWeight": 0.17334205885709592, "selectionWeight": 0.18109611753467816,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.0, "throughputPerHour": 23.166666666666668,
"waiting": 9311 "waiting": 9311
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 681.1546391752577, "backlogHours": 688.0625,
"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": 0.7269289141117421, "qualityFactor": 0.7160731979439665,
"queueFactor": 1.062565522438012, "queueFactor": 1.0614908161951635,
"queueWeight": 1.062565522438012, "queueWeight": 1.0614908161951635,
"recentSuccess": 28, "recentSuccess": 27,
"recentSuccessRate": 0.28865979381443296, "recentSuccessRate": 0.28125,
"recentTerminal": 97, "recentTerminal": 96,
"recentWilsonLowerBound": 0.20790125991766098, "recentWilsonLowerBound": 0.20107282637501533,
"running": 3, "running": 4,
"selectionWeight": 0.77240960139844, "selectionWeight": 0.7601051233410219,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.166666666666668, "throughputPerHour": 16.0,
"waiting": 11012 "waiting": 11009
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1921.941176470588, "backlogHours": 1950.44776119403,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Mthreads_s4000", "gpu": "Mthreads_s4000",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 2.001582560737856, "qualityFactor": 2.004535585847546,
"queueFactor": 0.9094557312657439, "queueFactor": 0.9079047243428812,
"queueWeight": 0.9094557312657439, "queueWeight": 0.9079047243428812,
"recentSuccess": 30, "recentSuccess": 29,
"recentSuccessRate": 0.4411764705882353, "recentSuccessRate": 0.43283582089552236,
"recentTerminal": 68, "recentTerminal": 67,
"recentWilsonLowerBound": 0.329460449863809, "recentWilsonLowerBound": 0.32104123341736546,
"running": 4, "running": 4,
"selectionWeight": 1.820350731464607, "selectionWeight": 1.8199273285044122,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.333333333333334, "throughputPerHour": 11.166666666666666,
"waiting": 21782 "waiting": 21780
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 2008.7058823529412, "backlogHours": 1932.6792452830186,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Sunrise_pt-200-x1", "gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.062412612828517296, "qualityFactor": 0.06067161018244557,
"queueFactor": 0.9034520863876111, "queueFactor": 0.9091519132705788,
"queueWeight": 0.9034520863876111, "queueWeight": 0.9091519132705788,
"recentSuccess": 7, "recentSuccess": 7,
"recentSuccessRate": 0.13725490196078433, "recentSuccessRate": 0.1320754716981132,
"recentTerminal": 51, "recentTerminal": 53,
"recentWilsonLowerBound": 0.06811015331542725, "recentWilsonLowerBound": 0.0654777020068957,
"running": 1, "running": 2,
"selectionWeight": 0.05638680527682613, "selectionWeight": 0.05515971047857712,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.5, "throughputPerHour": 8.833333333333334,
"waiting": 17074 "waiting": 17072
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1349.842105263158, "backlogHours": 1465.5428571428572,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Vastai_va16", "gpu": "Vastai_va16",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 16, "maxConcurrentTasks": 16,
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 0.9589592049209992, "queueFactor": 0.9476776666377522,
"queueWeight": 0.9589592049209992, "queueWeight": 0.9476776666377522,
"recentSuccess": 2, "recentSuccess": 2,
"recentSuccessRate": 0.02631578947368421, "recentSuccessRate": 0.02857142857142857,
"recentTerminal": 76, "recentTerminal": 70,
"recentWilsonLowerBound": 0.00724650713060782, "recentWilsonLowerBound": 0.007870446893806289,
"running": 16, "running": 16,
"selectionWeight": 0.04794796024604996, "selectionWeight": 0.047383883331887616,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 12.666666666666666, "throughputPerHour": 11.666666666666666,
"waiting": 17098 "waiting": 17098
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 1036.0975609756097, "backlogHours": 1011.4285714285714,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "hygon_k100-ai", "gpu": "hygon_k100-ai",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 6, "maxConcurrentTasks": 6,
"qualityFactor": 0.3469101253791057, "qualityFactor": 0.4653473855150459,
"queueFactor": 0.9977746829557308, "queueFactor": 1.0018902305172956,
"queueWeight": 0.9977746829557308, "queueWeight": 1.0018902305172956,
"recentSuccess": 26, "recentSuccess": 29,
"recentSuccessRate": 0.21138211382113822, "recentSuccessRate": 0.23015873015873015,
"recentTerminal": 123, "recentTerminal": 126,
"recentWilsonLowerBound": 0.1485330315397392, "recentWilsonLowerBound": 0.16529948502667766,
"running": 6, "running": 5,
"selectionWeight": 0.34613814036427004, "selectionWeight": 0.4662269993442902,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.5, "throughputPerHour": 21.0,
"waiting": 21240 "waiting": 21240
} }
}, },
"queueAttemptedAt": "2026-10-07T09:43:22.567627+00:00", "queueAttemptedAt": "2026-10-07T09:54:41.656922+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-07T09:43:22.567627+00:00", "queueUpdatedAt": "2026-10-07T09:54:41.656922+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",

1521
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

118
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-07T08:25:52.297334+00:00", "generatedAt": "2026-10-07T09:53:21.435952+00:00",
"lastSyncTime": "2026-10-07T08:25:52.062262+00:00", "lastSyncTime": "2026-10-07T09:53:21.160613+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -2610,27 +2610,6 @@
"targetGpu": "Vastai_va16", "targetGpu": "Vastai_va16",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"vastai_va16|vllm|text-generation|architectures:gptneoforcausallm": {
"architectureSignature": "architectures:gptneoforcausallm",
"architectures": [
"gptneoforcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-07T09:45:21+00:00",
"framework": "vllm",
"latestFailureAt": "2026-09-07T09:45:21+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"KoboldAI/GPT-Neo-2.7B-Janeway"
],
"sourceTaskIds": [
"4079146"
],
"targetGpu": "Vastai_va16",
"taskType": "text-generation"
},
"vastai_va16|vllm|text-generation|architectures:llavallamaforcausallm": { "vastai_va16|vllm|text-generation|architectures:llavallamaforcausallm": {
"architectureSignature": "architectures:llavallamaforcausallm", "architectureSignature": "architectures:llavallamaforcausallm",
"architectures": [ "architectures": [
@@ -2841,7 +2820,7 @@
} }
}, },
"architectureCompatibilitySummary": { "architectureCompatibilitySummary": {
"activeBlockCount": 143, "activeBlockCount": 142,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 9, "Ascend_910-b3|vllm": 9,
"Ascend_910-b3|vllm_tokenizer_patch": 7, "Ascend_910-b3|vllm_tokenizer_patch": 7,
@@ -2865,7 +2844,7 @@
"Mthreads_s4000|vllm": 6, "Mthreads_s4000|vllm": 6,
"Sunrise_pt-200-x1|vllm": 3, "Sunrise_pt-200-x1|vllm": 3,
"Sunrise_pt-200-x1|vllm_fix_tokenizer": 4, "Sunrise_pt-200-x1|vllm_fix_tokenizer": 4,
"Vastai_va16|vllm": 12, "Vastai_va16|vllm": 11,
"Vastai_va16|vllm_fix_tokenizer": 2, "Vastai_va16|vllm_fix_tokenizer": 2,
"hygon_k100-ai|vllm": 8, "hygon_k100-ai|vllm": 8,
"hygon_k100-ai|vllm-patch-tokenizer": 4 "hygon_k100-ai|vllm-patch-tokenizer": 4
@@ -4142,10 +4121,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 9, "decisionTotal": 9,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 47, "ambiguous_runtime": 48,
"memory_capacity": 9 "memory_capacity": 9
}, },
"failureCount": 56, "failureCount": 57,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"pendingCount": 0, "pendingCount": 0,
@@ -4155,8 +4134,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 56, "total": 57,
"unresolvedFailureCount": 47 "unresolvedFailureCount": 48
}, },
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": { "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 10, "attributableFailureCount": 10,
@@ -5691,7 +5670,7 @@
"decisionSuccessRate": 0.0281, "decisionSuccessRate": 0.0281,
"decisionTotal": 178, "decisionTotal": 178,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 364, "ambiguous_runtime": 365,
"backend_operator": 9, "backend_operator": 9,
"framework_architecture_unsupported": 47, "framework_architecture_unsupported": 47,
"memory_capacity": 10, "memory_capacity": 10,
@@ -5700,15 +5679,15 @@
"tokenizer_compatibility": 95, "tokenizer_compatibility": 95,
"参数/模板问题": 13 "参数/模板问题": 13
}, },
"failureCount": 575, "failureCount": 576,
"failureRate": 0.9914, "failureRate": 0.9914,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 25, "platformFailureCount": 25,
"successCount": 5, "successCount": 5,
"successRate": 0.0086, "successRate": 0.0086,
"total": 580, "total": 581,
"unresolvedFailureCount": 377 "unresolvedFailureCount": 378
}, },
"vllm_tokenizer_patch": { "vllm_tokenizer_patch": {
"attributableFailureCount": 153, "attributableFailureCount": 153,
@@ -5739,7 +5718,7 @@
"unresolvedFailureCount": 237 "unresolvedFailureCount": 237
} }
}, },
"generatedAt": "2026-10-07T08:25:52.279800+00:00", "generatedAt": "2026-10-07T09:53:21.417055+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 119, "attributableFailureCount": 119,
@@ -5909,7 +5888,7 @@
"decisionSuccessRate": 0.1639, "decisionSuccessRate": 0.1639,
"decisionTotal": 915, "decisionTotal": 915,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 660, "ambiguous_runtime": 661,
"architecture_compatibility": 15, "architecture_compatibility": 15,
"backend_operator": 12, "backend_operator": 12,
"context_length": 29, "context_length": 29,
@@ -5924,15 +5903,15 @@
"日志缺失": 155, "日志缺失": 155,
"验证失败": 30 "验证失败": 30
}, },
"failureCount": 1952, "failureCount": 1953,
"failureRate": 0.9286, "failureRate": 0.9287,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 21, "platformFailureCount": 21,
"successCount": 150, "successCount": 150,
"successRate": 0.0714, "successRate": 0.0713,
"total": 2102, "total": 2103,
"unresolvedFailureCount": 1166 "unresolvedFailureCount": 1167
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"attributableFailureCount": 984, "attributableFailureCount": 984,
@@ -16846,9 +16825,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 6, "decisionTotal": 6,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1,
"memory_capacity": 6 "memory_capacity": 6
}, },
"failureCount": 6, "failureCount": 7,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5", "modelType": "qwen3_5",
@@ -16860,8 +16840,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 6, "total": 7,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 1
}, },
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|fp8": { "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|fp8": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -25230,9 +25210,9 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 0, "decisionTotal": 0,
"failureBreakdown": { "failureBreakdown": {
"参数/模板问题": 2 "参数/模板问题": 1
}, },
"failureCount": 2, "failureCount": 1,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "unknown", "framework": "unknown",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -25244,8 +25224,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b4", "targetGpu": "Ascend_910-b4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 1,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 1
}, },
"Ascend_910-b4|vllm_tokenizer_patch|text-generation": { "Ascend_910-b4|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -25590,14 +25570,14 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 2,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 14, "ambiguous_runtime": 15,
"memory_capacity": 2 "memory_capacity": 2
}, },
"failureCount": 16, "failureCount": 17,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-22T02:26:33.565797+00:00", "lastTerminalAt": "2026-10-07T09:53:21.160613+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -25605,8 +25585,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 16, "total": 17,
"unresolvedFailureCount": 14 "unresolvedFailureCount": 15
}, },
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": { "Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 7, "attributableFailureCount": 7,
@@ -27788,12 +27768,13 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 2,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1,
"memory_capacity": 2 "memory_capacity": 2
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-09-22T02:26:33.565797+00:00", "lastTerminalAt": "2026-10-07T09:53:21.160613+00:00",
"modelType": "qwen3_5", "modelType": "qwen3_5",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
@@ -27803,8 +27784,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 1
}, },
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": { "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -45877,9 +45858,10 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 3, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1,
"memory_capacity": 3 "memory_capacity": 3
}, },
"failureCount": 3, "failureCount": 4,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm_fix_tokenizer", "framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34, "loadSizeLog2Bucket": 34,
@@ -45892,8 +45874,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Iluvatar_bi-150", "targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation", "taskType": "text-generation",
"total": 3, "total": 4,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 1
}, },
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": { "Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -58397,15 +58379,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17362, "terminalRecords": 17363,
"totalRecords": 17619, "totalRecords": 17620,
"totals": { "totals": {
"attributableFailureCount": 6244, "attributableFailureCount": 6244,
"decisionFailureRate": 0.8646, "decisionFailureRate": 0.8646,
"decisionSuccessRate": 0.1354, "decisionSuccessRate": 0.1354,
"decisionTotal": 7222, "decisionTotal": 7222,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4560, "ambiguous_runtime": 4561,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 129, "backend_operator": 129,
@@ -58421,15 +58403,15 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16384, "failureCount": 16385,
"failureRate": 0.9437, "failureRate": 0.9437,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 952, "platformFailureCount": 952,
"successCount": 978, "successCount": 978,
"successRate": 0.0563, "successRate": 0.0563,
"total": 17362, "total": 17363,
"unresolvedFailureCount": 9188 "unresolvedFailureCount": 9189
}, },
"warnings": [ "warnings": [
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -58438,14 +58420,14 @@
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x8 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Vastai_va16|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -58490,6 +58472,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17619, "summarizedRecords": 17620,
"version": 1 "version": 1
} }

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -62,6 +62,7 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082807+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:32+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4881076", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082807+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:32+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4881076", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082789+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:31+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4925021", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082789+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:31+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4925021", "taskType": "text-generation", "verifyResult": null}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm-customized", "lastSyncTime": "2026-09-25T01:41:30.953868+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 4, "model_load": 1}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:49:53.770533+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "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-customized", "lastSyncTime": "2026-09-25T01:41:30.953868+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Thinking-6bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1b41437401598cde7836ccc25883635c2738b06a5af924b7497b6e747e655b4b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 951093016, "estimatedRequiredGiB": 1.068, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 955857175, "modelscopeLicense": "other", "modelscopeParams": 256113408, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"ambiguous_runtime": 4, "model_load": 1}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm-customized", "lastTerminalAt": "2026-09-21T19:49:37.657075+00:00", "modelType": "lfm2", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x8", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 955857175}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:49:53.770533+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5006460", "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", "failureDetectedFramework": "vllm_fix_tokenizer", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T09:53:21.160613+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 3, "consecutiveFailures": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": {"memory_capacity": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-20T12:21:49.901832+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T19:21:51.849661+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006201", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-23T23:59:25.752461+00:00", "modelId": "nm-testing/Qwen2-1.5B-Instruct-FP8W8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245332464, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256814377, "modelscopeLicense": null, "modelscopeParams": 1777088000, "modelscopeTags": ["model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256814377}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:50:52.437033+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005783", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-23T23:59:25.752461+00:00", "modelId": "nm-testing/Qwen2-1.5B-Instruct-FP8W8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2245332464, "estimatedRequiredGiB": 2.522, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 2256814377, "modelscopeLicense": null, "modelscopeParams": 1777088000, "modelscopeTags": ["model_type:qwen2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 2256814377}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:50:52.437033+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005783", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-23T19:08:31.650327+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1047023664, "estimatedRequiredGiB": 1.172, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1048871402, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1048871402}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:50:52.306184+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005756", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-23T19:08:31.650327+00:00", "modelId": "nm-testing/tinyllama-one-shot-w4a16-group-packed", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1047023664, "estimatedRequiredGiB": 1.172, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1048871402, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1048871402}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:50:52.306184+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5005756", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-22T04:16:12.463726+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "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", "repositoryOnDiskBytes": 17788663591}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:32:49.780633+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005549", "taskType": "text-generation", "verifyResult": -1} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "transformers", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "transformers", "lastSyncTime": "2026-09-22T04:16:12.463726+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "3086a71adcdca90005b4967eb30749c44cd82389aff8d599758e4b91675d40dc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "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", "repositoryOnDiskBytes": 17788663591}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T18:32:49.780633+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5005549", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"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": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-22T20:46:09.364297+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:55:59.067045+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994201", "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": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-22T20:46:09.364297+00:00", "modelId": "nv-community/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 21561882284, "estimatedRequiredGiB": 24.122, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 21583784354, "modelscopeLicense": "other", "modelscopeParams": 17820210764, "modelscopeTags": ["license:other", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 21583784354}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:55:59.067045+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994201", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-23T10:44:10.250908+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124576, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124576}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:55:59.065763+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994202", "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", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-23T10:44:10.250908+00:00", "modelId": "RedHatAI/gemma-2-9b-it-quantized.w4a16", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7963207224, "estimatedRequiredGiB": 8.924, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 7985124576, "modelscopeLicense": "llama2", "modelscopeParams": 10159209984, "modelscopeTags": ["license:llama2", "model_type:gemma2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 7985124576}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:55:59.065763+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994202", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-22T16:03:02.581809+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "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": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:55:59.063595+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994203", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedArchitectures": ["Spark2_5ForCausalLM"], "framework": "vllm", "lastSyncTime": "2026-09-22T16:03:02.581809+00:00", "modelId": "XHToken/Spark-X2.5-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2ebd1d3ee8ed952dd08e24120ad5d7342c9a018f55c478225a242b664721e8d0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192408, "estimatedRequiredGiB": 9.209, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 8239718268, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "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": null, "repositoryOnDiskBytes": 8239718268}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T04:55:59.063595+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4994203", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-21T04:51:55.164989+00:00", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-6bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-21T04:49:27+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4895729", "taskType": "text-generation", "verifyResult": null}

2072
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

2054
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

3
ledger/submissions.jsonl
View File

@@ -27,7 +27,6 @@
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T12:42:26.505824+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4695129", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"} {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T12:42:26.505824+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4695129", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T12:50:14.422978+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4695252", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"} {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T12:50:14.422978+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4695252", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T13:14:08.050211+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4695580", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"} {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T13:14:08.050211+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4695580", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-mthreads-s4000"}
{"framework": "vllm_fix_tokenizer", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B-FP8", "modelId": "XHToken/Spark-X2.5-4B-FP8", "submitTime": "2026-09-07T16:06:40.552870+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4699585", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-fix-tokenizer-sunrise-pt-200-x1"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T17:27:44.564043+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4701029", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"} {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B-GGUF", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "submitTime": "2026-09-07T17:27:44.564043+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4701029", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-gguf", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "submitTime": "2026-09-08T00:43:38.323540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4707395", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"} {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-gguf", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "submitTime": "2026-09-08T00:43:38.323540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4707395", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-hygon-k100-ai"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-gguf", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "submitTime": "2026-09-08T00:49:03.895304+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4707512", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"} {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM5-2B-gguf", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "submitTime": "2026-09-08T00:49:03.895304+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4707512", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-ascend-910-b4"}
@@ -933,7 +932,6 @@
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "submitTime": "2026-10-06T09:57:49.944154+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321215", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "submitTime": "2026-10-06T09:57:49.944154+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321215", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlabonne/LFM2.5-230M-Chess", "modelId": "mlabonne/LFM2.5-230M-Chess", "submitTime": "2026-10-06T09:57:49.962484+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321218", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/mlabonne/LFM2.5-230M-Chess", "modelId": "mlabonne/LFM2.5-230M-Chess", "submitTime": "2026-10-06T09:57:49.962484+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321218", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "submitTime": "2026-10-06T09:57:49.759129+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321212", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "submitTime": "2026-10-06T09:57:49.759129+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321212", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Nexus-9B-CodeCore-Merge", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "submitTime": "2026-10-06T09:57:50.069956+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321221", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "submitTime": "2026-10-06T09:57:49.850687+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321219", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "submitTime": "2026-10-06T09:57:49.850687+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321219", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/togethercomputer/Tev1-4B-experimental", "modelId": "togethercomputer/Tev1-4B-experimental", "submitTime": "2026-10-06T09:57:49.857043+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321213", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/togethercomputer/Tev1-4B-experimental", "modelId": "togethercomputer/Tev1-4B-experimental", "submitTime": "2026-10-06T09:57:49.857043+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321213", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/togethercomputer/Tev1-0.8B-experimental", "modelId": "togethercomputer/Tev1-0.8B-experimental", "submitTime": "2026-10-06T09:57:50.064744+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321223", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"} {"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/togethercomputer/Tev1-0.8B-experimental", "modelId": "togethercomputer/Tev1-0.8B-experimental", "submitTime": "2026-10-06T09:57:50.064744+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321223", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
@@ -1176,6 +1174,7 @@
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "submitTime": "2026-10-06T09:35:46.359396+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320892", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "submitTime": "2026-10-06T09:35:46.359396+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320892", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "submitTime": "2026-10-06T09:35:46.356016+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320886", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "submitTime": "2026-10-06T09:35:46.356016+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320886", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-10-06T09:47:42.556514+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321077", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/mlx-community/gpt-oss-20b-OptiQ-4bit", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "submitTime": "2026-10-06T09:47:42.556514+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321077", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm-mlu", "modelAddress": "https://modelscope.cn/models/prithivMLmods/Nexus-9B-CodeCore-Merge", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "submitTime": "2026-10-06T09:57:50.069956+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321221", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mlu-cambricon-mlu-370-x8"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/groxaxo/Hemmingway-1-oQ5-MLX", "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "submitTime": "2026-10-06T22:44:43.576920+00:00", "targetGpu": "MetaX_c-500", "taskId": "5343307", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/groxaxo/Hemmingway-1-oQ5-MLX", "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "submitTime": "2026-10-06T22:44:43.576920+00:00", "targetGpu": "MetaX_c-500", "taskId": "5343307", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}
{"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/groxaxo/Hemmingway-1-oQ5-MLX", "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "submitTime": "2026-10-06T23:17:07.153265+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5343702", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"} {"framework": "vllm-patch-tokenizer", "modelAddress": "https://modelscope.cn/models/groxaxo/Hemmingway-1-oQ5-MLX", "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "submitTime": "2026-10-06T23:17:07.153265+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5343702", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-patch-tokenizer-hygon-k100-ai"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "submitTime": "2026-10-07T03:47:04.956076+00:00", "targetGpu": "MetaX_c-500", "taskId": "5347242", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "submitTime": "2026-10-07T03:47:04.956076+00:00", "targetGpu": "MetaX_c-500", "taskId": "5347242", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-metax-c-500"}

22
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "fb6abf4504b585e187e67f24f4fbb4f7f7e219233e48badb045a2956df18807d", ".modelhub_state/architecture_compatibility_blacklist.json": "f895a96f8e43705a09d0e37605085269e7b1e424183923a41ecb7b02dac1b323",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "054ea913978842706b81328c20d2ddaed0b385705feb18d4890bd9c4b9481a0f", ".modelhub_state/market_intelligence.json": "e49a28952dd78ba46d31da081714bedcd3ef8489a8c941ef98e8dc31db70a3af",
".modelhub_state/official_capabilities.json": "328016c09007d7d9daebc8be2bd820e4291a8bdadf37aa80f4ed1da20a77224f", ".modelhub_state/official_capabilities.json": "33b237c0aa64641a8339c490a1ea5dfe1d0faf98409bbfa54f783e3f50b3a1b1",
".modelhub_state/outcome_checkpoint.json": "14aafd75cd0b725b7338990c3d4f899f059d03f88d3b7852216715d71e646484", ".modelhub_state/outcome_checkpoint.json": "3c835c294212d85f3d25eda86ea614cb4bb091a112cb23837e2467efa2477cbb",
".modelhub_state/queue_cleanup_latest.json": "7f569be3fbe746570a2cdb33f54784d130294aa154d93e9ad9102b01386bc4cf", ".modelhub_state/queue_cleanup_latest.json": "7f569be3fbe746570a2cdb33f54784d130294aa154d93e9ad9102b01386bc4cf",
".modelhub_state/recent_outcomes.jsonl": "d5fbd67ab11ba282114e0a6e6e26d2b50a42a7a49656649d1663ca1840d97bc8", ".modelhub_state/recent_outcomes.jsonl": "f74d21d7ff253ad19a9bad388f4ec1d5406b254f86ede265c76fe77af4840bcb",
".modelhub_state/recovery_active_tasks.jsonl": "7c76fdee620958409e1dd76146ac0f638dac9772fec9bf95186d78c3b19d9860", ".modelhub_state/recovery_active_tasks.jsonl": "295b3f62b0e8a3424abbaade08742be19088b158a4cdfe0c367958e3ebbe7063",
".modelhub_state/recovery_intents.jsonl": "76d2c12acf1f296542ba47c00698c5ba54dcd422221a1370468452eb2fc87db9", ".modelhub_state/recovery_intents.jsonl": "02cb8c3a79588a9b752c1b06e302517bd24ebc4f6f97ab30f138225086bfe642",
".modelhub_state/routing_intelligence.json": "6ef38b890462db1d27431955b27b093a7f49784f93c0ead00d04e97dbae7b069", ".modelhub_state/routing_intelligence.json": "6ef38b890462db1d27431955b27b093a7f49784f93c0ead00d04e97dbae7b069",
".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5", ".modelhub_state/submission_exclusions.jsonl": "43b628022463d9d87ea16d9daf4f7ef224ee1ed83550feb9eaa30a59a885b4a5",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f", ".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "d09ce22b3a48920206a9381e864055f1c430c8f436b11394a7f45d8965be9e51", "ledger/submissions.jsonl": "ba1dcedb757f5c5cc6e6b547a12c11eb229ee8300c6718da52718da93270192d",
"outcomes/submissions.jsonl": "f5e06b1ff32a634dfbdf77b5ba98d1575a2a0ba0f45615e131f66893481816cb" "outcomes/submissions.jsonl": "e77e50d1d0530bd449acd086f5a6929815605c6950d3f6afe6f0dc2b04c07d08"
}, },
"generation": 21782, "generation": 21783,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-07T09:52:18.088802+00:00", "updatedAt": "2026-10-07T09:57:56.392098+00:00",
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2" "writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
} }

1
outcomes/submissions.jsonl
View File

@@ -263,7 +263,6 @@
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057515+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.789058+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006198", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057515+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.789058+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006198", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057487+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.844977+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006200", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:22:42.057487+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.844977+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006200", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057455+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 35256868927}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.848154+00:00", "targetGpu": "Biren_166m", "taskId": "5006202", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057455+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 35196531592, "estimatedRequiredGiB": 39.403, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 1411666624, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:text-generation-inference", "custom_tag:qwen3_5", "custom_tag:mlx-vlm", "custom_tag:prompt-rewriter", "custom_tag:prompt enhancer", "custom_tag:apple-silicon", "custom_tag:4-bit", "custom_tag:8-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 5}, "failureCount": 5, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-21T16:50:30.559192+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 5, "unresolvedFailureCount": 5}, "repositoryOnDiskBytes": 35256868927}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.848154+00:00", "targetGpu": "Biren_166m", "taskId": "5006202", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T03:22:42.057435+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1562291952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:pytorch", "custom_tag:omnimergekit", "custom_tag:merge", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:chain-of-thought", "custom_tag:sft", "custom_tag:agent", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:coder", "custom_tag:9B"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 3, "consecutiveFailures": 3, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": {"memory_capacity": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-20T12:21:49.901832+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:21:51.849661+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006201", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600642+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.447446+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006364", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600642+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034251896, "estimatedRequiredGiB": 2.283, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042626482}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.447446+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006364", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600714+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.388268+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006357", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600714+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-standard-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2034135144, "estimatedRequiredGiB": 2.282, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2042280856}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.388268+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006357", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600703+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.384898+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006356", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T03:37:52.600703+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039475672}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T19:37:12.384898+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5006356", "taskType": "text-generation", "verifyResult": null}