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

state: generation 25297 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-10-16 06:23:09 +00:00
parent a2aacd4c3e
commit 9f47d56a6f
7 changed files with 1032 additions and 966 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -2394,7 +2394,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-16T05:53:12.962410+00:00", "generatedAt": "2026-10-16T06:20:13.050772+00:00",
"summary": { "summary": {
"activeBlockCount": 119, "activeBlockCount": 119,
"byGpuFramework": { "byGpuFramework": {

286
.modelhub_state/market_intelligence.json
View File

@@ -1,8 +1,8 @@
{ {
"communityAttemptedAt": "2026-10-16T05:54:41.457078+00:00", "communityAttemptedAt": "2026-10-16T06:21:56.958883+00:00",
"communityError": null, "communityError": null,
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": "2026-10-16T05:54:41.457078+00:00", "communityUpdatedAt": "2026-10-16T06:21:56.958883+00:00",
"frameworkAttemptedAt": "2026-10-16T04:26:52.157172+00:00", "frameworkAttemptedAt": "2026-10-16T04:26:52.157172+00:00",
"frameworkError": null, "frameworkError": null,
"frameworkStats": { "frameworkStats": {
@@ -443,121 +443,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-16T05:54:41.457078+00:00", "generatedAt": "2026-10-16T06:21:56.958883+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 901.9459459459459, "backlogHours": 896.9354838709677,
"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": 1.3642557027980922, "qualityFactor": 1.5547395049568262,
"queueFactor": 0.9866389473257239, "queueFactor": 0.9870388569657047,
"queueWeight": 0.9866389473257239, "queueWeight": 0.9870388569657047,
"recentSuccess": 43, "recentSuccess": 46,
"recentSuccessRate": 0.23243243243243245, "recentSuccessRate": 0.24731182795698925,
"recentTerminal": 185, "recentTerminal": 186,
"recentWilsonLowerBound": 0.177386141453544, "recentWilsonLowerBound": 0.19083770318821605,
"running": 8, "running": 8,
"selectionWeight": 1.3460278104918253, "selectionWeight": 1.5345883038520114,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 30.833333333333332, "throughputPerHour": 31.0,
"waiting": 27810 "waiting": 27805
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1234.5098039215686, "backlogHours": 1250.4238410596026,
"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": 0.9412633530119361, "queueFactor": 0.9390524367542323,
"queueWeight": 0.9412633530119361, "queueWeight": 0.9390524367542323,
"recentSuccess": 46, "recentSuccess": 46,
"recentSuccessRate": 0.3006535947712418, "recentSuccessRate": 0.304635761589404,
"recentTerminal": 153, "recentTerminal": 151,
"recentWilsonLowerBound": 0.23360667413404657, "recentWilsonLowerBound": 0.2368257366335642,
"running": 8, "running": 8,
"selectionWeight": 2.3531583825298403, "selectionWeight": 2.3476310918855807,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.5, "throughputPerHour": 25.166666666666668,
"waiting": 31480 "waiting": 31469
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 134.3835616438356, "backlogHours": 133.24886877828052,
"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": 0.4344132727391361, "qualityFactor": 0.4474600458764205,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 32, "recentSuccess": 33,
"recentSuccessRate": 0.1461187214611872, "recentSuccessRate": 0.1493212669683258,
"recentTerminal": 219, "recentTerminal": 221,
"recentWilsonLowerBound": 0.10544206869273674, "recentWilsonLowerBound": 0.10834253982842994,
"running": 8, "running": 7,
"selectionWeight": 0.564737254560877, "selectionWeight": 0.5816980596393467,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 36.5, "throughputPerHour": 36.833333333333336,
"waiting": 4905 "waiting": 4908
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1109.8709677419354, "backlogHours": 1172.3863636363637,
"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": 0.7466624863782496, "qualityFactor": 1.0799734426550056,
"queueFactor": 0.956410770186666, "queueFactor": 0.9481735082102948,
"queueWeight": 0.956410770186666, "queueWeight": 0.9481735082102948,
"recentSuccess": 19, "recentSuccess": 21,
"recentSuccessRate": 0.20430107526881722, "recentSuccessRate": 0.23863636363636365,
"recentTerminal": 93, "recentTerminal": 88,
"recentWilsonLowerBound": 0.1348753753056426, "recentWilsonLowerBound": 0.1617092401848666,
"running": 7, "running": 7,
"selectionWeight": 0.7141160436665127, "selectionWeight": 1.0240022078961464,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.5, "throughputPerHour": 14.666666666666666,
"waiting": 17203 "waiting": 17195
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 348.6835443037975, "backlogHours": 372.08108108108104,
"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": 0.4236755950892532, "qualityFactor": 0.3772887062823197,
"queueFactor": 1.1378122730224647, "queueFactor": 1.1262966504700438,
"queueWeight": 1.1378122730224647, "queueWeight": 1.1262966504700438,
"recentSuccess": 24, "recentSuccess": 22,
"recentSuccessRate": 0.1518987341772152, "recentSuccessRate": 0.14864864864864866,
"recentTerminal": 158, "recentTerminal": 148,
"recentWilsonLowerBound": 0.10424930622012753, "recentWilsonLowerBound": 0.10025962527909334,
"running": 7, "running": 7,
"selectionWeight": 0.4820632918726485, "selectionWeight": 0.42493900614595287,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 26.333333333333332, "throughputPerHour": 24.666666666666668,
"waiting": 9182 "waiting": 9178
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 72.51245551601423, "backlogHours": 81.39759036144578,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -566,197 +566,197 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 6, "recentSuccess": 5,
"recentSuccessRate": 0.021352313167259787, "recentSuccessRate": 0.020080321285140562,
"recentTerminal": 281, "recentTerminal": 249,
"recentWilsonLowerBound": 0.009821690875373879, "recentWilsonLowerBound": 0.008606744392803315,
"running": 24, "running": 21,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 46.833333333333336, "throughputPerHour": 41.5,
"waiting": 3396 "waiting": 3378
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 152.66211604095562, "backlogHours": 160.36559139784947,
"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": 0.22653850293334218, "qualityFactor": 0.265592549217764,
"queueFactor": 1.2878807151623515, "queueFactor": 1.2778555168597565,
"queueWeight": 1.2878807151623515, "queueWeight": 1.2778555168597565,
"recentSuccess": 32, "recentSuccess": 33,
"recentSuccessRate": 0.10921501706484642, "recentSuccessRate": 0.11827956989247312,
"recentTerminal": 293, "recentTerminal": 279,
"recentWilsonLowerBound": 0.07843071305732743, "recentWilsonLowerBound": 0.08547262135783752,
"running": 9, "running": 6,
"selectionWeight": 0.2917545691696012, "selectionWeight": 0.33938890425476614,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 48.833333333333336, "throughputPerHour": 46.5,
"waiting": 7455 "waiting": 7457
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2410.7999999999997, "backlogHours": 2755.3714285714286,
"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": 0.6113672023891638, "qualityFactor": 0.5670415666840495,
"queueFactor": 0.8513559083276921, "queueFactor": 0.834106312988876,
"queueWeight": 0.8513559083276921, "queueWeight": 0.834106312988876,
"recentSuccess": 9, "recentSuccess": 8,
"recentSuccessRate": 0.225, "recentSuccessRate": 0.22857142857142856,
"recentTerminal": 40, "recentTerminal": 35,
"recentWilsonLowerBound": 0.12315953254678531, "recentWilsonLowerBound": 0.120657367461791,
"running": 2, "running": 2,
"selectionWeight": 0.5204910799117866, "selectionWeight": 0.47297295049826843,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.666666666666667, "throughputPerHour": 5.833333333333333,
"waiting": 16072 "waiting": 16073
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 340.2967741935484, "backlogHours": 351.72,
"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": 0.8706127088589724, "qualityFactor": 0.6958540660124342,
"queueFactor": 1.1419751589099612, "queueFactor": 1.1358444783089505,
"queueWeight": 1.1419751589099612, "queueWeight": 1.1358444783089505,
"recentSuccess": 31, "recentSuccess": 28,
"recentSuccessRate": 0.2, "recentSuccessRate": 0.18666666666666668,
"recentTerminal": 155, "recentTerminal": 150,
"recentWilsonLowerBound": 0.1446275910955794, "recentWilsonLowerBound": 0.13242330549709996,
"running": 8, "running": 8,
"selectionWeight": 0.9942180865482567, "selectionWeight": 0.7903819985890553,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.833333333333332, "throughputPerHour": 25.0,
"waiting": 8791 "waiting": 8793
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 209.31645569620255, "backlogHours": 208.0,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "MetaX_c-500", "gpu": "MetaX_c-500",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 0.09004685115360883, "qualityFactor": 0.10643496528181656,
"queueFactor": 1.2283293409443317, "queueFactor": 1.2289633470562744,
"queueWeight": 1.2283293409443317, "queueWeight": 1.2289633470562744,
"recentSuccess": 24, "recentSuccess": 26,
"recentSuccessRate": 0.0759493670886076, "recentSuccessRate": 0.08176100628930817,
"recentTerminal": 316, "recentTerminal": 318,
"recentWilsonLowerBound": 0.051565810379044764, "recentWilsonLowerBound": 0.056404360024248985,
"running": 4, "running": 3,
"selectionWeight": 0.11060718933162467, "selectionWeight": 0.13080467117655964,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 52.666666666666664, "throughputPerHour": 53.0,
"waiting": 11024 "waiting": 11024
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2392.5230769230766, "backlogHours": 2392.6153846153843,
"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": 0.46625711789004937, "qualityFactor": 0.5682942876583329,
"queueFactor": 0.8523283055115501, "queueFactor": 0.8519566499707223,
"queueWeight": 0.8523283055115501, "queueWeight": 0.8519566499707223,
"recentSuccess": 12, "recentSuccess": 13,
"recentSuccessRate": 0.18461538461538463, "recentSuccessRate": 0.2,
"recentTerminal": 65, "recentTerminal": 65,
"recentWilsonLowerBound": 0.10888765378062987, "recentWilsonLowerBound": 0.12077845770945214,
"running": 4, "running": 4,
"selectionWeight": 0.39740413922392487, "selectionWeight": 0.4841620975108913,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.833333333333334, "throughputPerHour": 10.833333333333334,
"waiting": 25919 "waiting": 25920
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 747.2244897959183, "backlogHours": 747.5102040816327,
"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": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.01488694777022, "queueFactor": 1.0143921085952623,
"queueWeight": 1.01488694777022, "queueWeight": 1.0143921085952623,
"recentSuccess": 9, "recentSuccess": 9,
"recentSuccessRate": 0.061224489795918366, "recentSuccessRate": 0.061224489795918366,
"recentTerminal": 147, "recentTerminal": 147,
"recentWilsonLowerBound": 0.032541132146123544, "recentWilsonLowerBound": 0.032541132146123544,
"running": 2, "running": 2,
"selectionWeight": 0.050744347388511, "selectionWeight": 0.050719605429763115,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 24.5, "throughputPerHour": 24.5,
"waiting": 18307 "waiting": 18314
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 1047.221052631579, "backlogHours": 1081.4347826086955,
"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": 0.9647828550225915, "queueFactor": 0.9597284756204465,
"queueWeight": 0.9647828550225915, "queueWeight": 0.9597284756204465,
"recentSuccess": 5, "recentSuccess": 5,
"recentSuccessRate": 0.05263157894736842, "recentSuccessRate": 0.05434782608695652,
"recentTerminal": 95, "recentTerminal": 92,
"recentWilsonLowerBound": 0.022687778480124217, "recentWilsonLowerBound": 0.02343471836850414,
"running": 16, "running": 16,
"selectionWeight": 0.04823914275112958, "selectionWeight": 0.04798642378102233,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 15.833333333333334, "throughputPerHour": 15.333333333333334,
"waiting": 16581 "waiting": 16582
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 971.1739130434783, "backlogHours": 985.6764705882352,
"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": 1.2313634385893262, "qualityFactor": 1.2351523787537828,
"queueFactor": 0.9757549890849518, "queueFactor": 0.9731690139374808,
"queueWeight": 0.9757549890849518, "queueWeight": 0.9731690139374808,
"recentSuccess": 32, "recentSuccess": 32,
"recentSuccessRate": 0.2318840579710145, "recentSuccessRate": 0.23529411764705882,
"recentTerminal": 138, "recentTerminal": 136,
"recentWilsonLowerBound": 0.16931213470916082, "recentWilsonLowerBound": 0.17188509908899885,
"running": 6, "running": 6,
"selectionWeight": 1.2015090185803368, "selectionWeight": 1.2020120224943527,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.0, "throughputPerHour": 22.666666666666668,
"waiting": 22337 "waiting": 22342
} }
}, },
"queueAttemptedAt": "2026-10-16T05:54:41.457078+00:00", "queueAttemptedAt": "2026-10-16T06:21:56.958883+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-10-16T05:54:41.457078+00:00", "queueUpdatedAt": "2026-10-16T06:21:56.958883+00:00",
"supportedGpus": [ "supportedGpus": [
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",
"Vastai_va16", "Vastai_va16",

1574
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

103
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-16T05:53:12.828551+00:00", "generatedAt": "2026-10-16T06:20:12.952195+00:00",
"lastSyncTime": "2026-10-16T05:53:11.946230+00:00", "lastSyncTime": "2026-10-16T06:20:12.468289+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -4596,14 +4596,14 @@
"unresolvedFailureCount": 12 "unresolvedFailureCount": 12
}, },
"Sunrise_pt-200-x1|vllm|text-generation": { "Sunrise_pt-200-x1|vllm|text-generation": {
"attributableFailureCount": 629, "attributableFailureCount": 630,
"decisionFailureRate": 0.9828, "decisionFailureRate": 0.9828,
"decisionSuccessRate": 0.0172, "decisionSuccessRate": 0.0172,
"decisionTotal": 640, "decisionTotal": 641,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 109, "ambiguous_runtime": 109,
"architecture_compatibility": 43, "architecture_compatibility": 43,
"backend_operator": 30, "backend_operator": 31,
"context_length": 34, "context_length": 34,
"framework_architecture_unsupported": 151, "framework_architecture_unsupported": 151,
"memory_capacity": 113, "memory_capacity": 113,
@@ -4613,7 +4613,7 @@
"tokenizer_compatibility": 182, "tokenizer_compatibility": 182,
"参数/模板问题": 9 "参数/模板问题": 9
}, },
"failureCount": 969, "failureCount": 970,
"failureRate": 0.9888, "failureRate": 0.9888,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -4623,7 +4623,7 @@
"successRate": 0.0112, "successRate": 0.0112,
"targetGpu": "Sunrise_pt-200-x1", "targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation", "taskType": "text-generation",
"total": 980, "total": 981,
"unresolvedFailureCount": 118 "unresolvedFailureCount": 118
}, },
"Sunrise_pt-200-x1|vllm|unknown": { "Sunrise_pt-200-x1|vllm|unknown": {
@@ -5126,15 +5126,15 @@
"unresolvedFailureCount": 6552 "unresolvedFailureCount": 6552
}, },
"vllm": { "vllm": {
"attributableFailureCount": 3700, "attributableFailureCount": 3701,
"decisionFailureRate": 0.9709, "decisionFailureRate": 0.9709,
"decisionSuccessRate": 0.0291, "decisionSuccessRate": 0.0291,
"decisionTotal": 3811, "decisionTotal": 3812,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1606, "ambiguous_runtime": 1606,
"architecture_compatibility": 112, "architecture_compatibility": 112,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 95, "backend_operator": 96,
"context_length": 161, "context_length": 161,
"framework_architecture_unsupported": 1415, "framework_architecture_unsupported": 1415,
"memory_capacity": 725, "memory_capacity": 725,
@@ -5145,14 +5145,14 @@
"tokenizer_compatibility": 425, "tokenizer_compatibility": 425,
"参数/模板问题": 87 "参数/模板问题": 87
}, },
"failureCount": 6279, "failureCount": 6280,
"failureRate": 0.9826, "failureRate": 0.9826,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 886, "platformFailureCount": 886,
"successCount": 111, "successCount": 111,
"successRate": 0.0174, "successRate": 0.0174,
"total": 6390, "total": 6391,
"unresolvedFailureCount": 1693 "unresolvedFailureCount": 1693
}, },
"vllm-customized": { "vllm-customized": {
@@ -5303,7 +5303,7 @@
"unresolvedFailureCount": 336 "unresolvedFailureCount": 336
} }
}, },
"generatedAt": "2026-10-16T05:53:12.814955+00:00", "generatedAt": "2026-10-16T06:20:12.936035+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 130, "attributableFailureCount": 130,
@@ -5639,14 +5639,14 @@
"unresolvedFailureCount": 331 "unresolvedFailureCount": 331
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"attributableFailureCount": 785, "attributableFailureCount": 786,
"decisionFailureRate": 0.883, "decisionFailureRate": 0.8831,
"decisionSuccessRate": 0.117, "decisionSuccessRate": 0.1169,
"decisionTotal": 889, "decisionTotal": 890,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 165, "ambiguous_runtime": 165,
"architecture_compatibility": 44, "architecture_compatibility": 44,
"backend_operator": 41, "backend_operator": 42,
"context_length": 39, "context_length": 39,
"framework_architecture_unsupported": 182, "framework_architecture_unsupported": 182,
"memory_capacity": 113, "memory_capacity": 113,
@@ -5657,14 +5657,14 @@
"参数/模板问题": 231, "参数/模板问题": 231,
"验证失败": 32 "验证失败": 32
}, },
"failureCount": 1467, "failureCount": 1468,
"failureRate": 0.9338, "failureRate": 0.9338,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 254, "platformFailureCount": 254,
"successCount": 104, "successCount": 104,
"successRate": 0.0662, "successRate": 0.0662,
"total": 1571, "total": 1572,
"unresolvedFailureCount": 428 "unresolvedFailureCount": 428
}, },
"Vastai_va16": { "Vastai_va16": {
@@ -23444,6 +23444,29 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|gemma2|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq": { "Sunrise_pt-200-x1|vllm|text-generation|llama|awq": {
"attributableFailureCount": 2, "attributableFailureCount": 2,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -55154,6 +55177,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Sunrise_pt-200-x1|vllm|text-generation|gemma2|none|34": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"backend_operator": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 34,
"modelType": "gemma2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|llama|awq|32": { "Sunrise_pt-200-x1|vllm|text-generation|llama|awq|32": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -59211,18 +59258,18 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17876, "terminalRecords": 17877,
"totalRecords": 18405, "totalRecords": 18406,
"totals": { "totals": {
"attributableFailureCount": 6330, "attributableFailureCount": 6331,
"decisionFailureRate": 0.8655, "decisionFailureRate": 0.8655,
"decisionSuccessRate": 0.1345, "decisionSuccessRate": 0.1345,
"decisionTotal": 7314, "decisionTotal": 7315,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4640, "ambiguous_runtime": 4640,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 132, "backend_operator": 133,
"context_length": 327, "context_length": 327,
"framework_architecture_unsupported": 2340, "framework_architecture_unsupported": 2340,
"memory_capacity": 1206, "memory_capacity": 1206,
@@ -59235,14 +59282,14 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16892, "failureCount": 16893,
"failureRate": 0.945, "failureRate": 0.945,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 966, "platformFailureCount": 966,
"successCount": 984, "successCount": 984,
"successRate": 0.055, "successRate": 0.055,
"total": 17876, "total": 17877,
"unresolvedFailureCount": 9596 "unresolvedFailureCount": 9596
}, },
"warnings": [ "warnings": [
@@ -59305,6 +59352,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 18405, "summarizedRecords": 18406,
"version": 1 "version": 1
} }

12
.modelhub_state/recovery_intents.jsonl
View File

@@ -3628,6 +3628,18 @@
{"batchId": "0c5bdecc2ea74891b2a8857412ca837b", "completedAt": "2026-10-15T21:59:18.744644+00:00", "configFingerprint": "009fc97a918caf620bbf7e2f303f8358c81f71f6acbbaccb4b07beb42ed53fef", "configSource": "modelhub_live", "createdAt": "2026-10-15T21:40:45.759803+00:00", "framework": "llamacpp", "intentId": "dfa4c58702074a3593ebb0f1d5d72c83", "lastModified": "2026-10-15T13:20:15+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "reason": null, "reconciledAt": "2026-10-16T06:16:04.228266+00:00", "repoId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5570020", "taskType": "text-generation"} {"batchId": "0c5bdecc2ea74891b2a8857412ca837b", "completedAt": "2026-10-15T21:59:18.744644+00:00", "configFingerprint": "009fc97a918caf620bbf7e2f303f8358c81f71f6acbbaccb4b07beb42ed53fef", "configSource": "modelhub_live", "createdAt": "2026-10-15T21:40:45.759803+00:00", "framework": "llamacpp", "intentId": "dfa4c58702074a3593ebb0f1d5d72c83", "lastModified": "2026-10-15T13:20:15+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "reason": null, "reconciledAt": "2026-10-16T06:16:04.228266+00:00", "repoId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5570020", "taskType": "text-generation"}
{"batchId": "4f111eebb42f4d41a30644b1f83a8e8f", "completedAt": "2026-10-16T00:38:37.615391+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-16T00:19:35.667368+00:00", "framework": "vllm_tokenizer_patch", "intentId": "92784d4097d24f36b44d2f0a828bab88", "lastModified": "2026-10-15T14:13:15+00:00", "modelAddress": "https://modelscope.cn/models/castorini/gaggle-nanochat-pretrained-climbmix-20260924", "reason": null, "reconciledAt": "2026-10-16T06:16:04.226520+00:00", "repoId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5572093", "taskType": "text-generation"} {"batchId": "4f111eebb42f4d41a30644b1f83a8e8f", "completedAt": "2026-10-16T00:38:37.615391+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-16T00:19:35.667368+00:00", "framework": "vllm_tokenizer_patch", "intentId": "92784d4097d24f36b44d2f0a828bab88", "lastModified": "2026-10-15T14:13:15+00:00", "modelAddress": "https://modelscope.cn/models/castorini/gaggle-nanochat-pretrained-climbmix-20260924", "reason": null, "reconciledAt": "2026-10-16T06:16:04.226520+00:00", "repoId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5572093", "taskType": "text-generation"}
{"batchId": "29836839f014447d89961a66093bc606", "completedAt": "2026-10-16T04:48:00.737557+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T04:28:15.287005+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5cb8a52aa10a45dca34a87430fff749a", "lastModified": "2026-10-15T11:41:45+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2", "reason": null, "reconciledAt": "2026-10-16T06:16:04.226875+00:00", "repoId": "DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5575924", "taskType": "text-generation"} {"batchId": "29836839f014447d89961a66093bc606", "completedAt": "2026-10-16T04:48:00.737557+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T04:28:15.287005+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5cb8a52aa10a45dca34a87430fff749a", "lastModified": "2026-10-15T11:41:45+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2", "reason": null, "reconciledAt": "2026-10-16T06:16:04.226875+00:00", "repoId": "DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2", "safeConfigVector": {"gpuNum": 1}, "status": "recovered_active", "targetGpu": "Ascend_910-b4", "taskId": "5575924", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "228b6bc2745650abd95687d8da71c138b5e7b7e9cbd7ff60115887f5ff13ac2c", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068336+00:00", "framework": "llamacpp", "intentId": "0cdcfb6774ea4e6b85117c146fe9f98d", "lastModified": "2026-10-15T11:37:55+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B-GGUF", "repoId": "DavidAU/DeepSeek-BlackRoot-R1-Distill-Llama-3.1-8B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "f15ba589f8fc347b06d694c47e50f0ec39eb094f4731fb654c6ecbc9c8faac9b", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068454+00:00", "framework": "llamacpp", "intentId": "c91e493be58a4ecabf73ab958bb8ed6d", "lastModified": "2026-10-15T23:18:06+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/microsoft-UserRepGen-4B-GGUF", "repoId": "prithivMLmods/microsoft-UserRepGen-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "985c1a262240355b84d40534de792b4a647e7fa0834c0d20610ec5c7239b7dfc", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068515+00:00", "framework": "llamacpp", "intentId": "239e5d8e60bc4c48842e12eabedb1a74", "lastModified": "2026-10-14T18:26:51+00:00", "modelAddress": "https://modelscope.cn/models/OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "repoId": "OpenBMB/MiniCPM-V-4.7-1B-DSpark-gguf", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "hygon_k100-ai", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "e9c4f4f15802a39a57c6e07956c53755f75fc438be43d1164a8a2eda32456b1e", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068574+00:00", "framework": "llamacpp", "intentId": "825788a845ed44978070e1a616c7d910", "lastModified": "2026-10-15T13:20:15+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "repoId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "61898f295f143f06988745beef05f856402c5162f007122829060f3694145199", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068632+00:00", "framework": "llamacpp", "intentId": "69139f4223ba4a36baf5214fd61b35a1", "lastModified": "2026-10-15T14:56:28+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "repoId": "DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068688+00:00", "framework": "vllm_tokenizer_patch", "intentId": "19af41bc08e64c55b42546353ae01071", "lastModified": "2026-10-15T14:13:15+00:00", "modelAddress": "https://modelscope.cn/models/castorini/gaggle-nanochat-pretrained-climbmix-20260924", "repoId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068742+00:00", "framework": "vllm_tokenizer_patch", "intentId": "cbfb57f0ac5a4e62b58fec84a514482f", "lastModified": "2026-10-15T08:32:12+00:00", "modelAddress": "https://modelscope.cn/models/mrm8488/mistral-7b-ft-h4-no_robots_instructions", "repoId": "mrm8488/mistral-7b-ft-h4-no_robots_instructions", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068792+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4b022b2afaf64716b68dab16ee997011", "lastModified": "2026-10-15T13:48:47+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/Qwen3-Great-Bowels-Of-Horror-FREAKSTORM-6B", "repoId": "DavidAU/Qwen3-Great-Bowels-Of-Horror-FREAKSTORM-6B", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068841+00:00", "framework": "vllm_tokenizer_patch", "intentId": "256c51b24c1f48518154ab0096266b91", "lastModified": "2026-10-15T23:21:49+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-3.7B-FP8", "repoId": "IFM/Jais-3-3.7B-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068890+00:00", "framework": "vllm_tokenizer_patch", "intentId": "9741b207498b49adacbc246ebaf075ed", "lastModified": "2026-10-15T23:24:49+00:00", "modelAddress": "https://modelscope.cn/models/IFM/Jais-3-7B-FP8", "repoId": "IFM/Jais-3-7B-FP8", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068939+00:00", "framework": "vllm_tokenizer_patch", "intentId": "665395908cee41669ae26c943dfce1d0", "lastModified": "2026-10-15T14:01:42+00:00", "modelAddress": "https://modelscope.cn/models/DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "repoId": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "d2f73c21a4b7406eacbe3753729d9218", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T06:23:09.068988+00:00", "framework": "vllm_tokenizer_patch", "intentId": "39fb9764bdae44cab1a982e2597734c6", "lastModified": "2026-10-15T14:05:57+00:00", "modelAddress": "https://modelscope.cn/models/OsaurusAI/Diplodocus-preview-JANG_6M", "repoId": "OsaurusAI/Diplodocus-preview-JANG_6M", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "940604d71b194482b3be98bb9acbba27", "completedAt": "2026-10-16T06:15:54.290318+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:56:14.813462+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f6e59fd5d43e474696c3f48cea9cdeb4", "repoId": "DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "940604d71b194482b3be98bb9acbba27", "completedAt": "2026-10-16T06:15:54.290318+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:56:14.813462+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f6e59fd5d43e474696c3f48cea9cdeb4", "repoId": "DavidAU/LFM2-8B-A1B-SpeedDemon-The-Deckard-II-Series-A", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "940604d71b194482b3be98bb9acbba27", "completedAt": "2026-10-16T06:15:54.290316+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:56:14.813414+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4bf9c2334cc240059779b653e0cebc7f", "repoId": "OsaurusAI/Diplodocus-preview-JANG_6M", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "940604d71b194482b3be98bb9acbba27", "completedAt": "2026-10-16T06:15:54.290316+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:56:14.813414+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4bf9c2334cc240059779b653e0cebc7f", "repoId": "OsaurusAI/Diplodocus-preview-JANG_6M", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "940604d71b194482b3be98bb9acbba27", "completedAt": "2026-10-16T06:15:54.290313+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:56:14.813366+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d150f689c5a143349a5f9a8841242600", "repoId": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "940604d71b194482b3be98bb9acbba27", "completedAt": "2026-10-16T06:15:54.290313+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-16T05:56:14.813366+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d150f689c5a143349a5f9a8841242600", "repoId": "DavidAU/LFM2-8B-A1B-GLM-4.7-Flash-Thinking-Quantum-IQ1C-P", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "9afcfdb2eb7774dbfebcdf5a9d95f436393fcf886115c919e1f73a96360a5603", ".modelhub_state/account_capacity.json": "9afcfdb2eb7774dbfebcdf5a9d95f436393fcf886115c919e1f73a96360a5603",
".modelhub_state/architecture_compatibility_blacklist.json": "23715fa720dccc712ec7f006eca5464e4c3a2dd4b29d82cb358ced52ac2aa919", ".modelhub_state/architecture_compatibility_blacklist.json": "4844d827cd1d6d3eb33ce30036ff120976e8c5ab6abf65b699f249f186148a88",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "695a67533c63064fbdddf32252f61b0fcb0c99bd1cd1d0c11adf9fb0009ffb31", ".modelhub_state/market_intelligence.json": "cbdf34fdb5919c5afa60b0d18c53354734e580ce06bc269981013c9b9a42baa2",
".modelhub_state/official_capabilities.json": "33397d61822a99417d67dc794233fd298a02003a243387a476f411a9afea8e34", ".modelhub_state/official_capabilities.json": "efceecce22a6c6722484ec666c9df62a5f55764c6ad461447eb6926a05e9f24b",
".modelhub_state/outcome_checkpoint.json": "3b720a6ad76e784731814ee86f13eadc1c8644d6f5c0edfd08b0a67e9f358a7b", ".modelhub_state/outcome_checkpoint.json": "f72927f0f76b481353b570772d29fa9e4d90e5ed7355c1572aeaebefa8d091d7",
".modelhub_state/queue_cleanup_latest.json": "7c0b1b5520f4b6a7571c7e40b71037196e6382971bfb5973626e31489b4fd6ff", ".modelhub_state/queue_cleanup_latest.json": "7c0b1b5520f4b6a7571c7e40b71037196e6382971bfb5973626e31489b4fd6ff",
".modelhub_state/recent_outcomes.jsonl": "530c3f3f681469cb91364456a0b40c6fcc13b4df04b6e2659e523f96bbbc2ce5", ".modelhub_state/recent_outcomes.jsonl": "530c3f3f681469cb91364456a0b40c6fcc13b4df04b6e2659e523f96bbbc2ce5",
".modelhub_state/recovery_active_tasks.jsonl": "008c7642ae03ee308d4b3b6906e37693209ca8b9e49f1dfee9a4920522c7d87a", ".modelhub_state/recovery_active_tasks.jsonl": "008c7642ae03ee308d4b3b6906e37693209ca8b9e49f1dfee9a4920522c7d87a",
".modelhub_state/recovery_intents.jsonl": "bfc4348371dc89e0003b20087d7425244afb84d2a4fea706a76a6fa8f22b89ac", ".modelhub_state/recovery_intents.jsonl": "a6bcb8d82376bcd6d6e55dbdcb02b534b87be24dd6ffab4b1293bb1f35697786",
".modelhub_state/routing_intelligence.json": "5a99e5017783cdbffc5e15f699e428fd3b24cd5e64876e4747d53a4d6b4e035a", ".modelhub_state/routing_intelligence.json": "5a99e5017783cdbffc5e15f699e428fd3b24cd5e64876e4747d53a4d6b4e035a",
".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b", ".modelhub_state/submission_exclusions.jsonl": "660ad77b924d3b0cc76f46aacd1f91a924d13a02bc68057eb5a964647441283b",
".modelhub_state/worker_crashes.jsonl": "c6b627ba4bfe6f0f89b6dfc017d052f3b1717feac7f9dd06d3003f04166819a9", ".modelhub_state/worker_crashes.jsonl": "c6b627ba4bfe6f0f89b6dfc017d052f3b1717feac7f9dd06d3003f04166819a9",
"ledger/submissions.jsonl": "927946e35dc3e3dfc424659c1341a26f0a0d5d94c313f2f3c2273161add6f787", "ledger/submissions.jsonl": "927946e35dc3e3dfc424659c1341a26f0a0d5d94c313f2f3c2273161add6f787",
"outcomes/submissions.jsonl": "d786767c75e73d57213e358a3b5c0888a14b89c4a99d45b38315fec053dd5eba" "outcomes/submissions.jsonl": "17f3c87ab4969442f96ca3f6811552f3609cae61431cf0f2a8b190763c6e7d40"
}, },
"generation": 25296, "generation": 25297,
"phase": "cycle", "phase": "intent",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-16T06:16:04.441577+00:00", "updatedAt": "2026-10-16T06:23:09.240698+00:00",
"writerId": "9b5b3ed8772344608455c7e3b71f5c9f" "writerId": "9b5b3ed8772344608455c7e3b71f5c9f"
} }

3
outcomes/submissions.jsonl
View File

@@ -138,7 +138,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T03:02:20.757780+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:32.459840+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985911", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T03:02:20.757780+00:00", "modelId": "inclusionAI/Ling-3.0-tiny", "modelProfile": {"architectures": ["BailingMoeV3ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15787992416, "estimatedRequiredGiB": 17.659, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_hybrid", "modelscopeFileSize": 15801179822, "modelscopeLicense": "mit", "modelscopeParams": 7893392800, "modelscopeTags": ["license:mit", "model_type:bailing_hybrid", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15801179822}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:01:32.459840+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4985911", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:45:50.542869+00:00", "modelId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325064, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325064}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:30:14.636274+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986332", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T03:45:50.542869+00:00", "modelId": "RedHatAI/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325064, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325064}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:30:14.636274+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986332", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T03:45:50.542801+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6711252896, "estimatedRequiredGiB": 7.503, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6713123803, "modelscopeLicense": "mit", "modelscopeParams": 3355609600, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6713123803}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:31:34.206245+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986333", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T03:45:50.542801+00:00", "modelId": "sbintuitions/sarashina2.2-3b-instruct-v0.1", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6711252896, "estimatedRequiredGiB": 7.503, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 6713123803, "modelscopeLicense": "mit", "modelscopeParams": 3355609600, "modelscopeTags": ["license:mit", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6713123803}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T19:31:34.206245+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4986333", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T05:42:03.443555+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v3-9B", "modelProfile": {"architectures": ["Gemma2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18483466448, "estimatedRequiredGiB": 20.702, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma2", "modelscopeFileSize": 18523972484, "modelscopeLicense": "gemma", "modelscopeParams": 9241705984, "modelscopeTags": ["license:gemma", "model_type:gemma2", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18523972484}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:26:40.552644+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4987963", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T05:42:03.443590+00:00", "modelId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3040272206, "estimatedRequiredGiB": 3.409, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3050595322, "modelscopeLicense": "apache-2.0", "modelscopeParams": 824389120, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:spark2_5", "custom_tag:long-context"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3050595322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:28:22.564707+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4988004", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-21T05:42:03.443590+00:00", "modelId": "mlx-community/Spark-X2.5-4B-OptiQ-4bit", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3040272206, "estimatedRequiredGiB": 3.409, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 3050595322, "modelscopeLicense": "apache-2.0", "modelscopeParams": 824389120, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:spark2_5", "custom_tag:long-context"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3050595322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T21:28:22.564707+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4988004", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T08:17:25.672470+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236688, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236688}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:03:59.684853+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4990026", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T08:17:25.672470+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236688, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236688}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:03:59.684853+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4990026", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T08:17:25.672531+00:00", "modelId": "LiquidAI/LFM2.5-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427456, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412393192, "modelscopeLicense": "other", "modelscopeParams": 2697198592, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412393192}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:04:08.492018+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4990027", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-21T08:17:25.672531+00:00", "modelId": "LiquidAI/LFM2.5-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427456, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412393192, "modelscopeLicense": "other", "modelscopeParams": 2697198592, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412393192}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T00:04:08.492018+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4990027", "taskType": "text-generation", "verifyResult": null}
@@ -1098,6 +1097,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-16T05:23:47.560303+00:00", "modelId": "DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "24a2d6b7ec33b5b33490e8c32fc08d8f540fe0fc4a02ad4f6b5454302b27d53e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5058317248, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 27199896379, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:256k context", "custom_tag:Qwen3", "custom_tag:All use cases", "custom_tag:creative", "custom_tag:creative writing", "custom_tag:fiction writing", "custom_tag:plot generation", "custom_tag:sub-plot generation", "custom_tag:story generation", "custom_tag:scene continue", "custom_tag:storytelling", "custom_tag:fiction story", "custom_tag:science fiction", "custom_tag:romance", "custom_tag:all genres", "custom_tag:story", "custom_tag:writing", "custom_tag:vivid prosing", "custom_tag:vivid writing", "custom_tag:fiction", "custom_tag:roleplaying", "custom_tag:bfloat16", "custom_tag:Neo Imatrix Max", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 27199896379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T21:05:38.661525+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5569445", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-16T05:23:47.560303+00:00", "modelId": "DavidAU/Qwen3-4B-Hivemind-Instruct-NEO-MAX-Imatrix-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "24a2d6b7ec33b5b33490e8c32fc08d8f540fe0fc4a02ad4f6b5454302b27d53e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5058317248, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 27199896379, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:256k context", "custom_tag:Qwen3", "custom_tag:All use cases", "custom_tag:creative", "custom_tag:creative writing", "custom_tag:fiction writing", "custom_tag:plot generation", "custom_tag:sub-plot generation", "custom_tag:story generation", "custom_tag:scene continue", "custom_tag:storytelling", "custom_tag:fiction story", "custom_tag:science fiction", "custom_tag:romance", "custom_tag:all genres", "custom_tag:story", "custom_tag:writing", "custom_tag:vivid prosing", "custom_tag:vivid writing", "custom_tag:fiction", "custom_tag:roleplaying", "custom_tag:bfloat16", "custom_tag:Neo Imatrix Max", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 27199896379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T21:05:38.661525+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5569445", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-16T05:23:47.560327+00:00", "modelId": "primitive-ai/LFM2.5-24B-A2B-NVFP4A16", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14953608064, "estimatedRequiredGiB": 16.734, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 14973587440, "modelscopeLicense": "other", "modelscopeParams": 8153731584, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:lfm2.5", "custom_tag:liquid", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14973587440}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T21:10:23.852106+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5569464", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-16T05:23:47.560327+00:00", "modelId": "primitive-ai/LFM2.5-24B-A2B-NVFP4A16", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14953608064, "estimatedRequiredGiB": 16.734, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 14973587440, "modelscopeLicense": "other", "modelscopeParams": 8153731584, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:lfm2.5", "custom_tag:liquid", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14973587440}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T21:10:23.852106+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5569464", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-16T05:53:11.946207+00:00", "modelId": "primitive-ai/LFM2.5-24B-A2B-NVFP4A16", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14953608064, "estimatedRequiredGiB": 16.734, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 14973587440, "modelscopeLicense": "other", "modelscopeParams": 8153731584, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:lfm2.5", "custom_tag:liquid", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14973587440}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T21:35:37.282510+00:00", "targetGpu": "MetaX_c-500", "taskId": "5569757", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-16T05:53:11.946207+00:00", "modelId": "primitive-ai/LFM2.5-24B-A2B-NVFP4A16", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14953608064, "estimatedRequiredGiB": 16.734, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 14973587440, "modelscopeLicense": "other", "modelscopeParams": 8153731584, "modelscopeTags": ["license:other", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:lfm2.5", "custom_tag:liquid", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14973587440}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T21:35:37.282510+00:00", "targetGpu": "MetaX_c-500", "taskId": "5569757", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "009fc97a918caf620bbf7e2f303f8358c81f71f6acbbaccb4b07beb42ed53fef", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3120573152, "estimatedRequiredGiB": 21.793, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 19499943240, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:12 reasoning modes", "custom_tag:12 instruct modes", "custom_tag:Turbo-Brilliance", "custom_tag:NEO Imatrix", "custom_tag:Max Quants", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19499943240}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-15T21:40:46.965193+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5570020", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-16T06:20:12.468266+00:00", "modelId": "DavidAU/LFM2.5-2.6B-Qwen3.8-Turbo-Brilliance-Power-X12-NEO-MAX-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "009fc97a918caf620bbf7e2f303f8358c81f71f6acbbaccb4b07beb42ed53fef", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3120573152, "estimatedRequiredGiB": 21.793, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 19499943240, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:12 reasoning modes", "custom_tag:12 instruct modes", "custom_tag:Turbo-Brilliance", "custom_tag:NEO Imatrix", "custom_tag:Max Quants", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19499943240}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-15T21:40:46.965193+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5570020", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "modelProfile": {"architectures": ["GaggleForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10579649968, "estimatedRequiredGiB": 23.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gaggle", "modelscopeFileSize": 21162857476, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:gaggle", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nanochat", "custom_tag:pretraining", "custom_tag:climbmix", "custom_tag:d34", "custom_tag:base-model", "custom_tag:custom_code", "custom_tag:vllm", "custom_tag:gaggle"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21162857476}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-16T00:19:38.082196+00:00", "targetGpu": "MetaX_c-500", "taskId": "5572093", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "castorini/gaggle-nanochat-pretrained-climbmix-20260924", "modelProfile": {"architectures": ["GaggleForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 10579649968, "estimatedRequiredGiB": 23.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gaggle", "modelscopeFileSize": 21162857476, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:gaggle", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nanochat", "custom_tag:pretraining", "custom_tag:climbmix", "custom_tag:d34", "custom_tag:base-model", "custom_tag:custom_code", "custom_tag:vllm", "custom_tag:gaggle"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21162857476}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-16T00:19:38.082196+00:00", "targetGpu": "MetaX_c-500", "taskId": "5572093", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22561854096, "estimatedRequiredGiB": 25.221, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 22566975607, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:finetune", "custom_tag:unsloth", "custom_tag:mixture of experts", "custom_tag:sparse moe", "custom_tag:moe", "custom_tag:heretic", "custom_tag:uncensored", "custom_tag:aliterated", "custom_tag:all use cases", "custom_tag:coder", "custom_tag:creative", "custom_tag:creative writing", "custom_tag:fiction writing", "custom_tag:plot generation", "custom_tag:sub-plot generation", "custom_tag:story generation", "custom_tag:scene continue", "custom_tag:storytelling", "custom_tag:fiction story", "custom_tag:science fiction", "custom_tag:romance", "custom_tag:all genres", "custom_tag:story", "custom_tag:writing", "custom_tag:vivid prosing", "custom_tag:vivid writing", "custom_tag:fiction", "custom_tag:roleplaying", "custom_tag:bfloat16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22566975607}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-16T04:28:16.853363+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5575924", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "DavidAU/LFM2-12B-A1B-GLM-4.7-Thinking-Quantum-IQ1C-P-TR1-S2", "modelProfile": {"architectures": ["Lfm2MoeForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22561854096, "estimatedRequiredGiB": 25.221, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2_moe", "modelscopeFileSize": 22566975607, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:lfm2_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:finetune", "custom_tag:unsloth", "custom_tag:mixture of experts", "custom_tag:sparse moe", "custom_tag:moe", "custom_tag:heretic", "custom_tag:uncensored", "custom_tag:aliterated", "custom_tag:all use cases", "custom_tag:coder", "custom_tag:creative", "custom_tag:creative writing", "custom_tag:fiction writing", "custom_tag:plot generation", "custom_tag:sub-plot generation", "custom_tag:story generation", "custom_tag:scene continue", "custom_tag:storytelling", "custom_tag:fiction story", "custom_tag:science fiction", "custom_tag:romance", "custom_tag:all genres", "custom_tag:story", "custom_tag:writing", "custom_tag:vivid prosing", "custom_tag:vivid writing", "custom_tag:fiction", "custom_tag:roleplaying", "custom_tag:bfloat16"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22566975607}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-16T04:28:16.853363+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5575924", "taskType": "text-generation", "verifyResult": null}