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

state: generation 21941 (intent)

Browse Source
This commit is contained in:
CoolBoy
2026-10-07 18:27:21 +00:00
parent 51081f69a2
commit aa30e7bac8
9 changed files with 3246 additions and 3572 deletions
Download Patch File Download Diff File Expand all files Collapse all files

25
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -938,6 +938,25 @@
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-11-05T09:57:50.069956+00:00",
"framework": "vllm-mlu",
"latestFailureAt": "2026-10-06T09:57:50.069956+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"prithivMLmods/Nexus-9B-CodeCore-Merge"
],
"sourceTaskIds": [
"5321221"
],
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:qwen3_5_mtp": {
"architectureSignature": "model_type:qwen3_5_mtp",
"architectures": [],
@@ -2798,9 +2817,9 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-07T17:46:10.348728+00:00",
"generatedAt": "2026-10-07T18:18:52.319057+00:00",
"summary": {
"activeBlockCount": 141,
"activeBlockCount": 142,
"byGpuFramework": {
"Ascend_910-b3|vllm": 9,
"Ascend_910-b3|vllm_tokenizer_patch": 7,
@@ -2811,7 +2830,7 @@
"Cambricon_mlu-370-x4|vllm-customized": 1,
"Cambricon_mlu-370-x8|vllm": 16,
"Cambricon_mlu-370-x8|vllm-customized": 6,
"Cambricon_mlu-370-x8|vllm-mlu": 3,
"Cambricon_mlu-370-x8|vllm-mlu": 4,
"Iluvatar_bi-150|transformers": 5,
"Iluvatar_bi-150|vllm": 6,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,

270
.modelhub_state/market_intelligence.json
View File

@@ -434,121 +434,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-07T18:17:49.573399+00:00",
"generatedAt": "2026-10-07T18:22:59.769331+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1041.4177215189875,
"backlogHours": 1067.8051948051948,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 1.467300123582137,
"queueFactor": 0.9973317914827462,
"queueWeight": 0.9973317914827462,
"recentSuccess": 44,
"recentSuccessRate": 0.27848101265822783,
"recentTerminal": 158,
"recentWilsonLowerBound": 0.21447831071810888,
"qualityFactor": 1.4409981719659737,
"queueFactor": 0.9926853497008864,
"queueWeight": 0.9926853497008864,
"recentSuccess": 43,
"recentSuccessRate": 0.2792207792207792,
"recentTerminal": 154,
"recentWilsonLowerBound": 0.21440072731911766,
"running": 8,
"selectionWeight": 1.4633850608950276,
"selectionWeight": 1.4304577742563807,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 26.333333333333332,
"waiting": 27424
"throughputPerHour": 25.666666666666668,
"waiting": 27407
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1095.5487804878048,
"backlogHours": 1080.6144578313254,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.5,
"queueFactor": 0.9897799445375906,
"queueWeight": 0.9897799445375906,
"recentSuccess": 56,
"recentSuccessRate": 0.34146341463414637,
"recentTerminal": 164,
"recentWilsonLowerBound": 0.27325918506598024,
"running": 7,
"selectionWeight": 2.4744498613439765,
"queueFactor": 0.9909113453013606,
"queueWeight": 0.9909113453013606,
"recentSuccess": 57,
"recentSuccessRate": 0.3433734939759036,
"recentTerminal": 166,
"recentWilsonLowerBound": 0.2754154730299584,
"running": 8,
"selectionWeight": 2.4772783632534017,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 27.333333333333332,
"waiting": 29945
"throughputPerHour": 27.666666666666668,
"waiting": 29897
},
"Biren_166m": {
"available": true,
"backlogHours": 138.28421052631577,
"backlogHours": 138.1578947368421,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.5751172978880593,
"qualityFactor": 0.5254129884076475,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 36,
"recentSuccessRate": 0.18947368421052632,
"recentSuccess": 35,
"recentSuccessRate": 0.18421052631578946,
"recentTerminal": 190,
"recentWilsonLowerBound": 0.14011715932170268,
"recentWilsonLowerBound": 0.13553810975683692,
"running": 8,
"selectionWeight": 0.7476524872544772,
"selectionWeight": 0.6830368849299417,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 31.666666666666668,
"waiting": 4379
"waiting": 4375
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1004.6470588235294,
"backlogHours": 1012.930693069307,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.3698568846755388,
"queueFactor": 1.0027239312525447,
"queueWeight": 1.0027239312525447,
"recentSuccess": 18,
"recentSuccessRate": 0.17647058823529413,
"recentTerminal": 102,
"recentWilsonLowerBound": 0.11464223172099423,
"qualityFactor": 0.31766175061434804,
"queueFactor": 1.0005722576403715,
"queueWeight": 1.0005722576403715,
"recentSuccess": 17,
"recentSuccessRate": 0.16831683168316833,
"recentTerminal": 101,
"recentWilsonLowerBound": 0.1078268539078673,
"running": 7,
"selectionWeight": 0.3708643494026753,
"selectionWeight": 0.3178435349781909,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 17.0,
"waiting": 17079
"throughputPerHour": 16.833333333333332,
"waiting": 17051
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 413.69117647058823,
"backlogHours": 409.44525547445255,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.8293522382621326,
"queueFactor": 1.1454653828960821,
"queueWeight": 1.1454653828960821,
"qualityFactor": 0.8016835750544743,
"queueFactor": 1.1461884833554217,
"queueWeight": 1.1461884833554217,
"recentSuccess": 31,
"recentSuccessRate": 0.22794117647058823,
"recentTerminal": 136,
"recentWilsonLowerBound": 0.16548404884189266,
"recentSuccessRate": 0.22627737226277372,
"recentTerminal": 137,
"recentWilsonLowerBound": 0.1642371904152058,
"running": 7,
"selectionWeight": 0.9499942791566564,
"selectionWeight": 0.9188804810226403,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.666666666666668,
"waiting": 9377
"throughputPerHour": 22.833333333333332,
"waiting": 9349
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 87.68,
"backlogHours": 88.64864864864865,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -557,197 +557,197 @@
"qualityFactor": 0.05,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 8,
"recentSuccessRate": 0.035555555555555556,
"recentTerminal": 225,
"recentWilsonLowerBound": 0.01812443580627004,
"recentSuccess": 9,
"recentSuccessRate": 0.04054054054054054,
"recentTerminal": 222,
"recentWilsonLowerBound": 0.021472458952407104,
"running": 24,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 37.5,
"waiting": 3288
"throughputPerHour": 37.0,
"waiting": 3280
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 175.03636363636366,
"backlogHours": 175.11818181818182,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.41348131611306316,
"qualityFactor": 0.4362168889658891,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 36,
"recentSuccessRate": 0.16363636363636364,
"recentSuccess": 37,
"recentSuccessRate": 0.16818181818181818,
"recentTerminal": 220,
"recentWilsonLowerBound": 0.12060205689531912,
"running": 4,
"selectionWeight": 0.5375257109469821,
"recentWilsonLowerBound": 0.12454747050749367,
"running": 3,
"selectionWeight": 0.5670819556556559,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 36.666666666666664,
"waiting": 6418
"waiting": 6421
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 2737.0588235294117,
"backlogHours": 2584.5,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 1.1410927211685187,
"queueFactor": 0.8627615617869286,
"queueWeight": 0.8627615617869286,
"qualityFactor": 0.9812774601205452,
"queueFactor": 0.8694186187100271,
"queueWeight": 0.8694186187100271,
"recentSuccess": 11,
"recentSuccessRate": 0.3235294117647059,
"recentTerminal": 34,
"recentWilsonLowerBound": 0.19131451326458573,
"recentSuccessRate": 0.3055555555555556,
"recentTerminal": 36,
"recentWilsonLowerBound": 0.18004270282805357,
"running": 2,
"selectionWeight": 0.9844909382590474,
"selectionWeight": 0.8531408939492882,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 5.666666666666667,
"waiting": 15510
"throughputPerHour": 6.0,
"waiting": 15507
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 387.7762237762238,
"backlogHours": 393.1063829787234,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.4649279817099022,
"queueFactor": 1.1566347364671137,
"queueWeight": 1.1566347364671137,
"recentSuccess": 26,
"recentSuccessRate": 0.18181818181818182,
"recentTerminal": 143,
"recentWilsonLowerBound": 0.1272051286979661,
"qualityFactor": 0.42497272126697516,
"queueFactor": 1.1532113352805518,
"queueWeight": 1.1532113352805518,
"recentSuccess": 25,
"recentSuccessRate": 0.1773049645390071,
"recentTerminal": 141,
"recentWilsonLowerBound": 0.12307779859865452,
"running": 8,
"selectionWeight": 0.5377518536012198,
"selectionWeight": 0.49008335935009817,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 23.833333333333332,
"waiting": 9242
"throughputPerHour": 23.5,
"waiting": 9238
},
"MetaX_c-500": {
"available": true,
"backlogHours": 602.0366972477063,
"backlogHours": 618.7924528301886,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.6945252081756815,
"queueFactor": 1.0827793457885098,
"queueWeight": 1.0827793457885098,
"recentSuccess": 24,
"recentSuccessRate": 0.22018348623853212,
"recentTerminal": 109,
"recentWilsonLowerBound": 0.1526627048081528,
"running": 3,
"selectionWeight": 0.752017550542093,
"qualityFactor": 0.6486505644065117,
"queueFactor": 1.077342185073066,
"queueWeight": 1.077342185073066,
"recentSuccess": 23,
"recentSuccessRate": 0.2169811320754717,
"recentTerminal": 106,
"recentWilsonLowerBound": 0.14916154641951038,
"running": 4,
"selectionWeight": 0.6988186164065888,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.166666666666668,
"waiting": 10937
"throughputPerHour": 17.666666666666668,
"waiting": 10932
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 1483.6363636363637,
"backlogHours": 1500.2758620689656,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 2.450599969167924,
"queueFactor": 0.9457672848935571,
"queueWeight": 0.9457672848935571,
"recentSuccess": 32,
"recentSuccessRate": 0.36363636363636365,
"recentTerminal": 88,
"recentWilsonLowerBound": 0.2707914560503069,
"qualityFactor": 2.2724866289034655,
"queueFactor": 0.9433215341023127,
"queueWeight": 0.9433215341023127,
"recentSuccess": 31,
"recentSuccessRate": 0.3563218390804598,
"recentTerminal": 87,
"recentWilsonLowerBound": 0.26372577394831054,
"running": 4,
"selectionWeight": 2.3176972792001824,
"selectionWeight": 2.14368557300421,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 14.666666666666666,
"waiting": 21760
"throughputPerHour": 14.5,
"waiting": 21754
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 2387.162790697674,
"backlogHours": 2386.6046511627906,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.10815034123514687,
"queueFactor": 0.8806454633266292,
"queueWeight": 0.8806454633266292,
"qualityFactor": 0.10629627540138555,
"queueFactor": 0.879869664153345,
"queueWeight": 0.879869664153345,
"recentSuccess": 6,
"recentSuccessRate": 0.13953488372093023,
"recentTerminal": 43,
"recentWilsonLowerBound": 0.06555634267713947,
"running": 2,
"selectionWeight": 0.09524210736595896,
"selectionWeight": 0.09352686813816857,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.166666666666667,
"waiting": 17108
"waiting": 17104
},
"Vastai_va16": {
"available": true,
"backlogHours": 1421.5833333333333,
"backlogHours": 1501.3235294117646,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.05,
"queueFactor": 0.9518479066994876,
"queueWeight": 0.9518479066994876,
"queueFactor": 0.9432227632136103,
"queueWeight": 0.9432227632136103,
"recentSuccess": 0,
"recentSuccessRate": 0.0,
"recentTerminal": 72,
"recentTerminal": 68,
"recentWilsonLowerBound": 0.0,
"running": 16,
"selectionWeight": 0.047592395334974384,
"selectionWeight": 0.047161138160680516,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 12.0,
"waiting": 17059
"throughputPerHour": 11.333333333333334,
"waiting": 17015
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 1072.1344537815128,
"backlogHours": 1020.672,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.6347421417593692,
"queueFactor": 0.9929926175551047,
"queueWeight": 0.9929926175551047,
"recentSuccess": 25,
"recentSuccessRate": 0.21008403361344538,
"recentTerminal": 119,
"recentWilsonLowerBound": 0.14654279199949027,
"qualityFactor": 0.6195635985366971,
"queueFactor": 0.9994302420660641,
"queueWeight": 0.9994302420660641,
"recentSuccess": 26,
"recentSuccessRate": 0.208,
"recentTerminal": 125,
"recentWilsonLowerBound": 0.14608314206747489,
"running": 6,
"selectionWeight": 0.6302942608181693,
"selectionWeight": 0.6192105972608529,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.833333333333332,
"throughputPerHour": 20.833333333333332,
"waiting": 21264
}
},
"queueAttemptedAt": "2026-10-07T18:11:07.246531+00:00",
"queueAttemptedAt": "2026-10-07T18:22:59.769331+00:00",
"queueError": null,
"queueUpdatedAt": "2026-10-07T18:11:07.246531+00:00",
"queueUpdatedAt": "2026-10-07T18:22:59.769331+00:00",
"supportedGpus": [
"Vastai_va16",
"Cambricon_mlu-370-x4",

5075
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

486
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-07T17:51:09.683466+00:00",
"lastSyncTime": "2026-10-07T17:51:09.564148+00:00",
"generatedAt": "2026-10-07T18:22:59.673964+00:00",
"lastSyncTime": "2026-10-07T18:22:59.552965+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -942,6 +942,25 @@
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:qwen3_5": {
"architectureSignature": "model_type:qwen3_5",
"architectures": [],
"evidenceCount": 1,
"expiresAt": "2026-11-05T09:57:50.069956+00:00",
"framework": "vllm-mlu",
"latestFailureAt": "2026-10-06T09:57:50.069956+00:00",
"latestSuccessfulAt": null,
"matchType": "model_type",
"modelType": "qwen3_5",
"sourceModelIds": [
"prithivMLmods/Nexus-9B-CodeCore-Merge"
],
"sourceTaskIds": [
"5321221"
],
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation"
},
"cambricon_mlu-370-x8|vllm-mlu|text-generation|model_type:qwen3_5_mtp": {
"architectureSignature": "model_type:qwen3_5_mtp",
"architectures": [],
@@ -2803,7 +2822,7 @@
}
},
"architectureCompatibilitySummary": {
"activeBlockCount": 141,
"activeBlockCount": 142,
"byGpuFramework": {
"Ascend_910-b3|vllm": 9,
"Ascend_910-b3|vllm_tokenizer_patch": 7,
@@ -2814,7 +2833,7 @@
"Cambricon_mlu-370-x4|vllm-customized": 1,
"Cambricon_mlu-370-x8|vllm": 16,
"Cambricon_mlu-370-x8|vllm-customized": 6,
"Cambricon_mlu-370-x8|vllm-mlu": 3,
"Cambricon_mlu-370-x8|vllm-mlu": 4,
"Iluvatar_bi-150|transformers": 5,
"Iluvatar_bi-150|vllm": 6,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 3,
@@ -3505,28 +3524,28 @@
"unresolvedFailureCount": 47
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 18,
"decisionFailureRate": 0.5806,
"decisionSuccessRate": 0.4194,
"decisionTotal": 31,
"attributableFailureCount": 19,
"decisionFailureRate": 0.5938,
"decisionSuccessRate": 0.4062,
"decisionTotal": 32,
"failureBreakdown": {
"ambiguous_runtime": 54,
"framework_architecture_unsupported": 14,
"framework_architecture_unsupported": 15,
"model_load": 3,
"tokenizer_compatibility": 1,
"参数/模板问题": 3
},
"failureCount": 75,
"failureRate": 0.8523,
"failureCount": 76,
"failureRate": 0.8539,
"framework": "vllm-mlu",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"successCount": 13,
"successRate": 0.1477,
"successRate": 0.1461,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 88,
"total": 89,
"unresolvedFailureCount": 57
},
"Cambricon_mlu-370-x8|vllm|text-generation": {
@@ -4104,10 +4123,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 9,
"failureBreakdown": {
"ambiguous_runtime": 50,
"ambiguous_runtime": 51,
"memory_capacity": 9
},
"failureCount": 59,
"failureCount": 60,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -4117,8 +4136,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 59,
"unresolvedFailureCount": 50
"total": 60,
"unresolvedFailureCount": 51
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 10,
@@ -4970,28 +4989,28 @@
"unresolvedFailureCount": 296
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation": {
"attributableFailureCount": 127,
"attributableFailureCount": 129,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 127,
"decisionTotal": 129,
"failureBreakdown": {
"backend_operator": 9,
"framework_architecture_unsupported": 23,
"platform_infrastructure": 25,
"tokenizer_compatibility": 95,
"framework_architecture_unsupported": 24,
"platform_infrastructure": 26,
"tokenizer_compatibility": 96,
"参数/模板问题": 6
},
"failureCount": 158,
"failureCount": 161,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"platformFailureCount": 26,
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 158,
"total": 161,
"unresolvedFailureCount": 6
},
"Sunrise_pt-200-x1|vllm|text-generation": {
@@ -5006,23 +5025,23 @@
"context_length": 34,
"framework_architecture_unsupported": 146,
"memory_capacity": 113,
"platform_infrastructure": 215,
"platform_infrastructure": 216,
"repository_structure": 75,
"runtime_memory": 1,
"tokenizer_compatibility": 180,
"参数/模板问题": 9
},
"failureCount": 954,
"failureCount": 955,
"failureRate": 0.9948,
"framework": "vllm",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 215,
"platformFailureCount": 216,
"successCount": 5,
"successRate": 0.0052,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 959,
"total": 960,
"unresolvedFailureCount": 118
},
"Sunrise_pt-200-x1|vllm|unknown": {
@@ -5538,20 +5557,20 @@
"framework_architecture_unsupported": 1390,
"memory_capacity": 725,
"model_load": 228,
"platform_infrastructure": 879,
"platform_infrastructure": 880,
"repository_structure": 470,
"runtime_memory": 66,
"tokenizer_compatibility": 420,
"参数/模板问题": 50
},
"failureCount": 6200,
"failureCount": 6201,
"failureRate": 0.9833,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 879,
"platformFailureCount": 880,
"successCount": 105,
"successRate": 0.0167,
"total": 6305,
"total": 6306,
"unresolvedFailureCount": 1652
},
"vllm-customized": {
@@ -5578,27 +5597,27 @@
"unresolvedFailureCount": 51
},
"vllm-mlu": {
"attributableFailureCount": 44,
"decisionFailureRate": 0.6667,
"decisionSuccessRate": 0.3333,
"decisionTotal": 66,
"attributableFailureCount": 45,
"decisionFailureRate": 0.6716,
"decisionSuccessRate": 0.3284,
"decisionTotal": 67,
"failureBreakdown": {
"ambiguous_runtime": 103,
"framework_architecture_unsupported": 36,
"framework_architecture_unsupported": 37,
"model_load": 7,
"platform_infrastructure": 1,
"tokenizer_compatibility": 1,
"参数/模板问题": 4,
"验证失败": 3
},
"failureCount": 155,
"failureRate": 0.8757,
"failureCount": 156,
"failureRate": 0.8764,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"successCount": 22,
"successRate": 0.1243,
"total": 177,
"successRate": 0.1236,
"total": 178,
"unresolvedFailureCount": 110
},
"vllm-patch-tokenizer": {
@@ -5649,29 +5668,29 @@
"unresolvedFailureCount": 34
},
"vllm_fix_tokenizer": {
"attributableFailureCount": 175,
"decisionFailureRate": 0.9722,
"decisionSuccessRate": 0.0278,
"decisionTotal": 180,
"attributableFailureCount": 177,
"decisionFailureRate": 0.9725,
"decisionSuccessRate": 0.0275,
"decisionTotal": 182,
"failureBreakdown": {
"ambiguous_runtime": 373,
"ambiguous_runtime": 374,
"backend_operator": 9,
"framework_architecture_unsupported": 48,
"framework_architecture_unsupported": 49,
"memory_capacity": 10,
"model_load": 13,
"platform_infrastructure": 25,
"tokenizer_compatibility": 95,
"platform_infrastructure": 26,
"tokenizer_compatibility": 96,
"参数/模板问题": 13
},
"failureCount": 586,
"failureRate": 0.9915,
"failureCount": 590,
"failureRate": 0.9916,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 25,
"platformFailureCount": 26,
"successCount": 5,
"successRate": 0.0085,
"total": 591,
"unresolvedFailureCount": 386
"successRate": 0.0084,
"total": 595,
"unresolvedFailureCount": 387
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 157,
@@ -5702,7 +5721,7 @@
"unresolvedFailureCount": 257
}
},
"generatedAt": "2026-10-07T17:51:09.667015+00:00",
"generatedAt": "2026-10-07T18:22:59.655554+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 119,
@@ -5819,13 +5838,13 @@
"unresolvedFailureCount": 856
},
"Cambricon_mlu-370-x8": {
"attributableFailureCount": 64,
"decisionFailureRate": 0.8101,
"decisionSuccessRate": 0.1899,
"decisionTotal": 79,
"attributableFailureCount": 65,
"decisionFailureRate": 0.8125,
"decisionSuccessRate": 0.1875,
"decisionTotal": 80,
"failureBreakdown": {
"ambiguous_runtime": 158,
"framework_architecture_unsupported": 51,
"framework_architecture_unsupported": 52,
"memory_capacity": 4,
"model_load": 6,
"platform_infrastructure": 2,
@@ -5833,14 +5852,14 @@
"参数/模板问题": 41,
"验证失败": 22
},
"failureCount": 287,
"failureRate": 0.9503,
"failureCount": 288,
"failureRate": 0.9505,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 15,
"successRate": 0.0497,
"total": 302,
"successRate": 0.0495,
"total": 303,
"unresolvedFailureCount": 221
},
"Iluvatar_bi-100": {
@@ -5872,7 +5891,7 @@
"decisionSuccessRate": 0.1639,
"decisionTotal": 915,
"failureBreakdown": {
"ambiguous_runtime": 663,
"ambiguous_runtime": 664,
"architecture_compatibility": 15,
"backend_operator": 12,
"context_length": 29,
@@ -5887,15 +5906,15 @@
"日志缺失": 155,
"验证失败": 30
},
"failureCount": 1955,
"failureRate": 0.9287,
"failureCount": 1956,
"failureRate": 0.9288,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 21,
"successCount": 150,
"successRate": 0.0713,
"total": 2105,
"unresolvedFailureCount": 1169
"successRate": 0.0712,
"total": 2106,
"unresolvedFailureCount": 1170
},
"Iluvatar_mrv-100": {
"attributableFailureCount": 984,
@@ -6038,32 +6057,32 @@
"unresolvedFailureCount": 303
},
"Sunrise_pt-200-x1": {
"attributableFailureCount": 767,
"decisionFailureRate": 0.8867,
"decisionSuccessRate": 0.1133,
"decisionTotal": 865,
"attributableFailureCount": 769,
"decisionFailureRate": 0.887,
"decisionSuccessRate": 0.113,
"decisionTotal": 867,
"failureBreakdown": {
"ambiguous_runtime": 162,
"architecture_compatibility": 44,
"backend_operator": 38,
"context_length": 39,
"framework_architecture_unsupported": 171,
"framework_architecture_unsupported": 172,
"memory_capacity": 113,
"platform_infrastructure": 240,
"platform_infrastructure": 242,
"repository_structure": 83,
"runtime_memory": 1,
"tokenizer_compatibility": 278,
"tokenizer_compatibility": 279,
"参数/模板问题": 228,
"验证失败": 32
},
"failureCount": 1429,
"failureRate": 0.9358,
"failureCount": 1433,
"failureRate": 0.936,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 240,
"platformFailureCount": 242,
"successCount": 98,
"successRate": 0.0642,
"total": 1527,
"successRate": 0.064,
"total": 1531,
"unresolvedFailureCount": 422
},
"Vastai_va16": {
@@ -6143,7 +6162,7 @@
"hygon_k100-ai": 64.0
},
"pendingRecords": 0,
"policyCancelledRecords": 279,
"policyCancelledRecords": 291,
"profileCombinationStats": {
"Ascend_910-b3|llamacpp|text-generation|smollm3|none": {
"attributableFailureCount": 0,
@@ -13622,14 +13641,14 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5|none": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2
"framework_architecture_unsupported": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen3_5",
@@ -13641,7 +13660,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 2,
"total": 3,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_vl|none": {
@@ -16532,9 +16551,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "mini_k3",
@@ -16546,8 +16565,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors": {
"attributableFailureCount": 0,
@@ -22444,15 +22463,15 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 5,
"attributableFailureCount": 6,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 5,
"decisionTotal": 6,
"failureBreakdown": {
"backend_operator": 2,
"tokenizer_compatibility": 3
"tokenizer_compatibility": 4
},
"failureCount": 5,
"failureCount": 6,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "llama",
@@ -22464,7 +22483,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 5,
"total": 6,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|mistral3|none": {
@@ -22607,15 +22626,15 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 3,
"attributableFailureCount": 4,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 3,
"decisionTotal": 4,
"failureBreakdown": {
"framework_architecture_unsupported": 3,
"framework_architecture_unsupported": 4,
"platform_infrastructure": 1
},
"failureCount": 4,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "qwen3_5_moe",
@@ -22627,7 +22646,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 4,
"total": 5,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_mtp|none": {
@@ -22723,6 +22742,29 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|spark2_5|fp8": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"platform_infrastructure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors": {
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
@@ -23004,21 +23046,21 @@
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"platform_infrastructure": 5
"platform_infrastructure": 6
},
"failureCount": 7,
"failureCount": 8,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 5,
"platformFailureCount": 6,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 7,
"total": 8,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3|none": {
@@ -25332,10 +25374,10 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 14,
"ambiguous_runtime": 13,
"framework_architecture_unsupported": 2
},
"failureCount": 16,
"failureCount": 15,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastPlatformFailureAt": null,
@@ -25347,8 +25389,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 16,
"unresolvedFailureCount": 14
"total": 15,
"unresolvedFailureCount": 13
},
"Ascend_910-b4|vllm|text-generation": {
"attributableFailureCount": 0,
@@ -25410,9 +25452,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 14
"ambiguous_runtime": 13
},
"failureCount": 14,
"failureCount": 13,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -25424,8 +25466,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 14,
"unresolvedFailureCount": 14
"total": 13,
"unresolvedFailureCount": 13
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -25583,20 +25625,21 @@
"unresolvedFailureCount": 18
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"consecutivePlatformFailures": 0,
"decisionFailureRate": 0.0,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 1
"ambiguous_runtime": 1,
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-24T18:34:46.362994+00:00",
"lastTerminalAt": "2026-10-07T18:18:51.743140+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -25604,7 +25647,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 1
},
"Iluvatar_bi-150|transformers|text-generation": {
@@ -25667,14 +25710,14 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"failureBreakdown": {
"ambiguous_runtime": 17,
"ambiguous_runtime": 18,
"memory_capacity": 2
},
"failureCount": 19,
"failureCount": 20,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
"lastTerminalAt": "2026-10-07T15:52:48.873111+00:00",
"lastTerminalAt": "2026-10-07T18:18:51.743129+00:00",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
@@ -25682,8 +25725,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 19,
"unresolvedFailureCount": 17
"total": 20,
"unresolvedFailureCount": 18
},
"Iluvatar_bi-150|vllm_tokenizer_patch|text-generation": {
"attributableFailureCount": 7,
@@ -26392,9 +26435,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 13
"ambiguous_runtime": 12
},
"failureCount": 13,
"failureCount": 12,
"failureRate": 1.0,
"framework": "vllm_tokenizer_patch",
"lastTerminalAt": "2026-09-23T02:06:44.350356+00:00",
@@ -26407,8 +26450,8 @@
"successRate": 0.0,
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation",
"total": 13,
"unresolvedFailureCount": 13
"total": 12,
"unresolvedFailureCount": 12
},
"Ascend_910-b4|vllm_tokenizer_patch|text-generation|mini_k3|none": {
"attributableFailureCount": 2,
@@ -26667,9 +26710,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 5
},
"failureCount": 6,
"failureCount": 5,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-07T11:42:31.164621+00:00",
@@ -26682,8 +26725,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 5,
"unresolvedFailureCount": 5
},
"Biren_166m|vllm_fix_tokenizer|text-generation|smollm3|none": {
"attributableFailureCount": 0,
@@ -27260,6 +27303,31 @@
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5|none": {
"attributableFailureCount": 1,
"consecutiveFailures": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"lastTerminalAt": "2026-10-07T18:18:51.743140+00:00",
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Iluvatar_bi-150|transformers|text-generation|aquila3|none": {
"attributableFailureCount": 0,
"consecutiveFailures": 0,
@@ -27667,12 +27735,12 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-07T15:52:48.873111+00:00",
"lastTerminalAt": "2026-10-07T18:18:51.743129+00:00",
"modelType": "mini_k3",
"pendingCount": 0,
"pendingRate": 0.0,
@@ -27682,8 +27750,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|phi3small|compressed-tensors": {
"attributableFailureCount": 0,
@@ -41196,14 +41264,14 @@
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_5|none|34": {
"attributableFailureCount": 1,
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"decisionTotal": 2,
"failureBreakdown": {
"framework_architecture_unsupported": 1
"framework_architecture_unsupported": 2
},
"failureCount": 1,
"failureCount": 2,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 34,
@@ -41216,7 +41284,7 @@
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"total": 2,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|qwen3_vl|none|34": {
@@ -45322,9 +45390,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30,
@@ -45337,8 +45405,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Iluvatar_bi-150|vllm_fix_tokenizer|text-generation|nemotron_h|compressed-tensors|34": {
"attributableFailureCount": 0,
@@ -54311,6 +54379,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"tokenizer_compatibility": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|llama|compressed-tensors|33": {
"attributableFailureCount": 2,
"decisionFailureRate": 1.0,
@@ -54529,15 +54621,15 @@
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|34": {
"attributableFailureCount": 2,
"attributableFailureCount": 3,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 2,
"decisionTotal": 3,
"failureBreakdown": {
"framework_architecture_unsupported": 2,
"framework_architecture_unsupported": 3,
"platform_infrastructure": 1
},
"failureCount": 3,
"failureCount": 4,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 34,
@@ -54550,7 +54642,7 @@
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 3,
"total": 4,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none|35": {
@@ -54698,6 +54790,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|spark2_5|fp8|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"platform_infrastructure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 32,
"modelType": "spark2_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"quantizationMethod": "fp8",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Sunrise_pt-200-x1",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|starcoder2|compressed-tensors|31": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -55103,6 +55219,30 @@
"total": 1,
"unresolvedFailureCount": 0
},
"Sunrise_pt-200-x1|vllm|text-generation|qwen3_5|none|12": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"platform_infrastructure": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 12,
"modelType": "qwen3_5",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 1,
"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|qwen3_5|none|33": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
@@ -58468,39 +58608,39 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17414,
"totalRecords": 17693,
"terminalRecords": 17420,
"totalRecords": 17711,
"totals": {
"attributableFailureCount": 6251,
"decisionFailureRate": 0.8647,
"decisionSuccessRate": 0.1353,
"decisionTotal": 7229,
"attributableFailureCount": 6254,
"decisionFailureRate": 0.8648,
"decisionSuccessRate": 0.1352,
"decisionTotal": 7232,
"failureBreakdown": {
"ambiguous_runtime": 4572,
"ambiguous_runtime": 4573,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 129,
"context_length": 327,
"framework_architecture_unsupported": 2271,
"framework_architecture_unsupported": 2273,
"memory_capacity": 1206,
"model_load": 571,
"platform_infrastructure": 952,
"platform_infrastructure": 954,
"repository_structure": 742,
"runtime_memory": 101,
"tokenizer_compatibility": 689,
"tokenizer_compatibility": 690,
"参数/模板问题": 3266,
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16436,
"failureRate": 0.9438,
"failureCount": 16442,
"failureRate": 0.9439,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 952,
"platformFailureCount": 954,
"successCount": 978,
"successRate": 0.0562,
"total": 17414,
"unresolvedFailureCount": 9233
"successRate": 0.0561,
"total": 17420,
"unresolvedFailureCount": 9234
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -58561,6 +58701,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 17693,
"summarizedRecords": 17711,
"version": 1
}

912
.modelhub_state/queue_cleanup_latest.json
View File

File diff suppressed because it is too large Load Diff

4
.modelhub_state/recent_outcomes.jsonl
View File

@@ -1,6 +1,7 @@
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:31:58.345448+00:00", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-07T03:47:04.956076+00:00", "targetGpu": "MetaX_c-500", "taskId": "5347242", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164536+00:00", "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T23:17:07.153265+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5343702", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:31:58.345546+00:00", "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T22:44:43.576920+00:00", "targetGpu": "MetaX_c-500", "taskId": "5343307", "taskType": "text-generation", "verifyResult": null}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T18:18:51.743140+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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, "repositoryOnDiskBytes": 19329296879}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:57:50.069956+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321221", "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": ["gpt_oss"], "framework": "vllm", "lastSyncTime": "2026-10-07T06:48:39.066266+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:47:42.556514+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321077", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164561+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:46.359396+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320892", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164611+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:35:46.356016+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320886", "taskType": "text-generation", "verifyResult": null}
@@ -97,6 +98,7 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T01:23:49.082798+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T01:23:32+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4850852", "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": "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": "2026-10-07T18:18:51.743129+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": 2039076183}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T22:21:59.843515+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5008078", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T16:12:59.741949+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "failed", "status": "success", "submitTime": "2026-09-21T20:38:42.646739+00:00", "targetGpu": "Biren_166m", "taskId": "5007027", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T16:12:59.741980+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "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": "failed", "status": "success", "submitTime": "2026-09-21T20:37:39.964394+00:00", "targetGpu": "Biren_166m", "taskId": "5007017", "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": "2026-10-07T15:52:48.873111+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2031106928, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": "failed", "status": "success", "submitTime": "2026-09-21T20:16:38.547857+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5006761", "taskType": "text-generation", "verifyResult": -1}
@@ -296,5 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-30T11:55:48.444086+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084014480, "estimatedRequiredGiB": 10.162, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093198689, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093198689}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:02:30.537080+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4997592", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-23T05:26:10.454831+00:00", "modelId": "RedHatAI/SmolLM-135M-Instruct-quantized.w8a16", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219876272, "estimatedRequiredGiB": 0.25, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223261617, "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": 223261617}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T09:02:30.534692+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997591", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T23:26:35.259297+00:00", "modelId": "blue2star/Qwen-Image-2.1-PE-I2I-ComfyUI", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29306922460, "estimatedRequiredGiB": 32.775, "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": 29326959151, "modelscopeLicense": "other", "modelscopeParams": 18821595084, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:qwen", "custom_tag:prompt-rewriting", "custom_tag:image-editing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29326959151}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:59:28.154388+00:00", "targetGpu": "Biren_166m", "taskId": "4997528", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-22T21:35:04.154893+00:00", "modelId": "nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1231252716, "estimatedRequiredGiB": 1.378, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 1233101396, "modelscopeLicense": null, "modelscopeParams": 1100048384, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 1233101396}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:46:11.874749+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4997349", "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": "2026-09-23T02:39:29.759242+00:00", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29952488643, "estimatedRequiredGiB": 33.497, "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": 29972714678, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8027131120, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:macos", "custom_tag:speculative-decoding", "custom_tag:multi-token-prediction", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:coding", "custom_tag:qwen3-8", "custom_tag:qwen-3.8", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-pro", "custom_tag:mac-studio", "custom_tag:opencode", "custom_tag:claude-code", "custom_tag:27b", "custom_tag:qwen3.8-27b", "custom_tag:qwen3-8-27b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29972714678}, "outcome": "failed", "status": "success", "submitTime": "2026-09-21T08:43:01.453596+00:00", "targetGpu": "Biren_166m", "taskId": "4997304", "taskType": "text-generation", "verifyResult": -1}

6
.modelhub_state/recovery_intents.jsonl
View File

@@ -3161,6 +3161,12 @@
{"batchId": "957ee1c4b1d54c608f79cc509702c5b7", "completedAt": "2026-10-07T18:10:58.130841+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-07T17:55:53.601970+00:00", "framework": "vllm", "intentId": "d346842db70541128a8d3de5c3b06785", "lastModified": "2026-09-28T16:42:31+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-llama-mha-standard-v1", "reason": null, "reconciledAt": "2026-10-07T18:15:57.976457+00:00", "repoId": "nkkbr/Mini-K3-1H-llama-mha-standard-v1", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5358968", "taskType": "text-generation"}
{"batchId": "957ee1c4b1d54c608f79cc509702c5b7", "completedAt": "2026-10-07T18:10:58.130845+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-07T17:55:53.602027+00:00", "framework": "vllm", "intentId": "41bc96d585964b46ad3ae9daaea1a37c", "lastModified": "2026-09-26T14:40:03+00:00", "modelAddress": "https://modelscope.cn/models/Akahsizrr/Cyber-Prime-1.1-2.6B", "reason": null, "reconciledAt": "2026-10-07T18:15:58.034450+00:00", "repoId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5358869", "taskType": "text-generation"}
{"batchId": "8faff7cfe65d4d429caf9d6e9ef4e02f", "completedAt": "2026-10-07T18:15:44.427285+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-07T18:14:20.126226+00:00", "framework": "vllm_tokenizer_patch", "intentId": "751889a3e281484b97b1d1b66245520b", "lastModified": "2026-10-07T17:37:13+00:00", "modelAddress": "https://modelscope.cn/models/mlx-community/LFM2.5-1.2B-Thinking-5bit", "reason": null, "reconciledAt": "2026-10-07T18:15:57.973298+00:00", "repoId": "mlx-community/LFM2.5-1.2B-Thinking-5bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5359099", "taskType": "text-generation"}
{"batchId": "10ce1d0967074b3e857a79d7225f59ec", "configFingerprint": "58bd440e460cf3e4d9271b3c32c451e80254e59faf47ce55dcda11588cf4117e", "configSource": "modelhub_live", "createdAt": "2026-10-07T18:27:21.491538+00:00", "framework": "vllm", "intentId": "cc4535859328447b9224ae9aca3ab018", "lastModified": "2026-09-24T05:29:17+00:00", "modelAddress": "https://modelscope.cn/models/bench-labs/tinctura-v1", "repoId": "bench-labs/tinctura-v1", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
{"batchId": "10ce1d0967074b3e857a79d7225f59ec", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-07T18:27:21.491684+00:00", "framework": "vllm", "intentId": "1e546d3086354309b178f6662b37ffb9", "lastModified": "2026-09-24T18:29:33+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/K2-Horizon-7B-AWQ-INT4", "repoId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
{"batchId": "10ce1d0967074b3e857a79d7225f59ec", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-07T18:27:21.491746+00:00", "framework": "vllm", "intentId": "845d27151ece4a67be7fdeeea79404be", "lastModified": "2026-09-21T18:33:19+00:00", "modelAddress": "https://modelscope.cn/models/GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "repoId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
{"batchId": "10ce1d0967074b3e857a79d7225f59ec", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-07T18:27:21.491806+00:00", "framework": "vllm", "intentId": "581eb137d166429eb7a70fb479326f51", "lastModified": "2026-09-25T13:06:21+00:00", "modelAddress": "https://modelscope.cn/models/danish-foundation-models/DFM-Mimir-v1.5", "repoId": "danish-foundation-models/DFM-Mimir-v1.5", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
{"batchId": "10ce1d0967074b3e857a79d7225f59ec", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-07T18:27:21.491863+00:00", "framework": "vllm", "intentId": "9b4eb6bb46bb4a3b92495e506fb16075", "lastModified": "2026-09-22T14:23:22+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "repoId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
{"batchId": "10ce1d0967074b3e857a79d7225f59ec", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-07T18:27:21.491921+00:00", "framework": "vllm", "intentId": "ee9967a7f8514d0785d922d71a1b2327", "lastModified": "2026-09-22T13:08:25+00:00", "modelAddress": "https://modelscope.cn/models/nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "repoId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"}
{"batchId": "957ee1c4b1d54c608f79cc509702c5b7", "completedAt": "2026-10-07T18:10:58.130867+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-07T17:55:53.602318+00:00", "framework": "vllm", "intentId": "acb5ddd7c7424e17951ce52d23b2aca8", "repoId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "957ee1c4b1d54c608f79cc509702c5b7", "completedAt": "2026-10-07T18:10:58.130862+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-07T17:55:53.602261+00:00", "framework": "vllm", "intentId": "ae1f88d773f7494d8c647b88b362ee49", "repoId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "957ee1c4b1d54c608f79cc509702c5b7", "completedAt": "2026-10-07T18:10:58.130858+00:00", "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configSource": "modelhub_live", "createdAt": "2026-10-07T17:55:53.602203+00:00", "framework": "vllm", "intentId": "cdd6b8e8d9b8404b86019b8f7e6e18b2", "repoId": "danish-foundation-models/DFM-Mimir-v1.5", "safeConfigVector": {"dtype": "-", "gpuNum": 1, "maxModelLen": 4096}, "status": "age_policy_deferred", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}

22
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4",
"checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "db2e3d0bf9f413723d97bcc0e0b4db66f660e256a23bccdd7b87266cc4c896a8",
".modelhub_state/architecture_compatibility_blacklist.json": "a82cd232f6cd344ac39ab76b9d34c5fbd43ce0d0a55f44aec5c1b7b754ca609c",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "e76b3c22092d2f1e6656b0b58ee6a00eb65d7e39bccc71774346acf46ea9497f",
".modelhub_state/official_capabilities.json": "082e653cad1d37eefa4b5067d9415862ec4b1902d4d873eada1592ca8352bc99",
".modelhub_state/outcome_checkpoint.json": "31cde81af37d0f31c232dde97260d57a150cf5aad72c132bbae1b921a1a577fd",
".modelhub_state/queue_cleanup_latest.json": "d687975ef22f8f71c1ec1655519eafe96ea44f72b4b3b937afcf49b297712448",
".modelhub_state/recent_outcomes.jsonl": "1cb2dd6992a8b16d850b3d3e6288a576e79fe449bed02c46fe8c27ceb6b62b2c",
".modelhub_state/market_intelligence.json": "1c0f92d3de6d5f3b2d9cb1241f171a2dbece2e21178b0922cf1d3f1a443fddc4",
".modelhub_state/official_capabilities.json": "35204cae90f1da41cddbf1b845fc018f9c28802fd86838e32e38ee7df13c3af7",
".modelhub_state/outcome_checkpoint.json": "a5fccfea856345f346a45b534890585ea2c18a70aca187e5ced0d8f9faa85a48",
".modelhub_state/queue_cleanup_latest.json": "159f6df0b5b371fa1dddd726670836470a936ad493a4d7241524d02584c428b7",
".modelhub_state/recent_outcomes.jsonl": "ccbed4e3e9a8ccfca56856b049a43ea7a271d026cd0125a697aba416165ef37a",
".modelhub_state/recovery_active_tasks.jsonl": "51e9206eea89b6def82cc23d50d7b7554178c01f87e8808c3ab785d1260f4889",
".modelhub_state/recovery_intents.jsonl": "12eb4f0c4ac641cf00c05aa96137894f259807e5e48fe462f9ebf9e24fc87f86",
".modelhub_state/recovery_intents.jsonl": "600049424b4e4626414f9606d546afc35807db0a213291de003794dc69833013",
".modelhub_state/routing_intelligence.json": "6840c2b3d7d4af25eb9331354c313e9f478b6e413911a519d7cbe9b16ffd0a2c",
".modelhub_state/submission_exclusions.jsonl": "dca7091e8b1da8bf9b3ecb95fe573b2a41666601edf86cea13ce9ce738b9eb7b",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "37955fb16301735ba6c8e67687d169c8e22c334d39b84efb401f14596d112874",
"outcomes/submissions.jsonl": "b2b0820fdc30e117e8b28db915bd7772f2c2f15eaa8b0c37e1db2b59d6bbd8c0"
"outcomes/submissions.jsonl": "d9728dc4449823c2d85a18e5977177ef67e7b63809233a6d2c3332747cf67a3b"
},
"generation": 21940,
"phase": "cycle",
"generation": 21941,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-10-07T18:17:50.713507+00:00",
"updatedAt": "2026-10-07T18:27:21.722991+00:00",
"writerId": "33ed03361c5848e88b8ce6204fb4f7d2"
}

18
outcomes/submissions.jsonl
View File

@@ -1,6 +1,5 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T11:58:24.844524+00:00", "modelId": "inclusionAI/Ling-3.0-tiny-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "efcec92f0f61cfcfef2bff75fcc3b460aac2425880772995e6373e3f88061c16", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8408187808, "estimatedRequiredGiB": 46.011, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 41170267110, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 41170267110}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T03:57:15.312611+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4610785", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-04T12:43:05.302313+00:00", "modelId": "b77968543/Spark-X2.5-4B-Q8_0", "modelProfile": {"architectures": [], "configFingerprint": "054a7592edf89d789e18b12765c567c3c34b2ebb58661fdd49255aad03c66d40", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 4.889, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 4375025003, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "library:", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 4375025003}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T04:40:16.372199+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4611339", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-05T03:32:15.596901+00:00", "modelId": "neuralmagic/Llama-3.2-3B-Instruct-FP8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4395007696, "estimatedRequiredGiB": 4.922, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 4404161088, "modelscopeLicense": "llama3.2", "modelscopeParams": 3606752256, "modelscopeTags": ["license:llama3.2", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:llama", "custom_tag:llama-3", "custom_tag:neuralmagic", "custom_tag:llmcompressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4404161088}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T19:29:42.987166+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4632974", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:40:37.707812+00:00", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8dbcfce641caa83ec7080451f0410ae2c4732d92c35c6ea116cea836d3424ea2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2076674432, "estimatedRequiredGiB": 11.564, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10347343046, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1942653248, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "custom_tag:edge", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10347343046}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:38:07.789820+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641229", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T12:57:50.112723+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "7fcefcc66e6b781d939ce31d9aa1c7a89bdfb773b9556e6dcde4e21754b1189f", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4610579744, "estimatedRequiredGiB": 25.463, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 22784105135, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4326350848, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:gated-deltanet", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22784105135}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T04:56:19.745119+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-05T17:06:08.800571+00:00", "modelId": "LiquidAI/LFM2.5-230M-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "c331f3d8906467b7947cec00daebfec4ccad1f351223a1eced4dea452a1012df", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 149080928, "estimatedRequiredGiB": 2.218, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1984559598, "modelscopeLicense": "other", "modelscopeParams": 229693184, "modelscopeTags": ["license:other", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:gguf", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1984559598}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-05T09:04:21.884770+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4645136", "taskType": "text-generation", "verifyResult": null}
@@ -16,7 +15,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-06T22:43:37.806846+00:00", "modelId": "RedHatAI/Meta-Llama-3.1-70B-Instruct-FP8-dynamic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 72669954704, "estimatedRequiredGiB": 81.225, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 72679220993, "modelscopeLicense": "llama3.1", "modelscopeParams": 70553706496, "modelscopeTags": ["license:llama3.1", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:fp8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 72679220993}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T14:33:50.986624+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4668642", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T02:37:59.437424+00:00", "modelId": "RWKV/RWKV7-1.5B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3055418240, "estimatedRequiredGiB": 3.417, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 3057371034, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1527668736, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3057371034}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T18:34:36.628828+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4674757", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:05:30.903841+00:00", "modelId": "OpenOneRec/OneReason-8B-pretrain-competition", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16779959216, "estimatedRequiredGiB": 18.783, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 8389956608, "modelscopeTags": ["model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:recommendation", "custom_tag:generative-recommendation", "custom_tag:reasoning", "custom_tag:itemic-token", "custom_tag:qwen3", "custom_tag:pretraining", "custom_tag:competition"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16806898419}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T20:54:07.883252+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4677960", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:18:43.228865+00:00", "modelId": "empero-ai/Qwen3.8-4B-Distill", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5777, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342747188, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4659865088, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:empero-ai", "custom_tag:qwen3.5", "custom_tag:qwen3.8", "custom_tag:distillation", "custom_tag:reasoning", "custom_tag:function-calling", "custom_tag:sft"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342747188}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:15:16.244457+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678529", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-07T05:31:35.012291+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-06T21:25:37.107095+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4678756", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T17:31:43.302628+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "9fba363aef42aed2b52f3be34868ab5830a7c956f45e65fceed6561122eb8743", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8229925227, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T09:29:07.790789+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4691709", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T18:00:51.826326+00:00", "modelId": "XHToken/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "8bb72add25c6bbefdaaa3d4fc9d420176b02cfa13433975a607b2e5a23d944d6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021152, "estimatedRequiredGiB": 14.087, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 8229925227, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 12604946379}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T09:53:15.317620+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4692145", "taskType": "text-generation", "verifyResult": null}
@@ -27,7 +25,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T20:52:41.332115+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "5b544f6f344d670dc906febb49993caf4b7d39b21860557b2416591a1a8c41bf", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 3420936797, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T12:42:26.505824+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4695129", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T20:52:41.332095+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "5f7f0613db77a9df3302ec352997953a9eba59a0aa6b38bb4fbb9466fb50fd7b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T12:50:14.422978+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4695252", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-07T21:18:24.608680+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "ea2321217291fd0be7b6ccbad7b7c81bf62a9ac5c888c7ee1e080e1ea85862ae", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T13:14:08.050211+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4695580", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-08T00:12:24.015192+00:00", "modelId": "XHToken/Spark-X2.5-4B-FP8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4450260320, "estimatedRequiredGiB": 4.991, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4465562659, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 4465562659}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T16:06:40.552870+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4699585", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T01:37:35.725250+00:00", "modelId": "XHToken/Spark-X2.5-1.7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "0e96112008e09ac1841408e47a35f72b68023fca4efc76695e6eb96ba540ba1c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1820112704, "estimatedRequiredGiB": 7.095, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 6348507357, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1707657216, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:ollama", "custom_tag:lm-studio", "custom_tag:sparkx2_5", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6348507357}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-07T17:27:44.564043+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4701029", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T09:05:31.097982+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "cfe08978e062dae728d260488110f70f7f12953c8f377a0f9c0a93bc3f6b0862", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.371, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280253884, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280253884}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T00:43:38.323540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4707395", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-08T09:05:31.097932+00:00", "modelId": "OpenBMB/MiniCPM5-2B-gguf", "modelProfile": {"architectures": [], "configFingerprint": "78f026e44886f960cbcecb5cfbfc4b0b2239d86ba4b225a73df72965f73e0ed2", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2679710688, "estimatedRequiredGiB": 10.371, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 9280253884, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2516756480, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:long-context", "custom_tag:tool-calling", "custom_tag:on-device", "custom_tag:edge-ai", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9280253884}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-08T00:49:03.895304+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4707512", "taskType": "text-generation", "verifyResult": null}
@@ -102,7 +99,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T19:09:56.106587+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "f0079c5722ce37ff9d929e5e96de8925a4670b711936f17faab5f7565f2ecb43", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 32173498806, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496536}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T10:59:43.480777+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4847964", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-14T20:39:18.216494+00:00", "modelId": "aucaCQS/Spark-X2.5-4B-Coder-Flash", "modelProfile": {"architectures": [], "configFingerprint": "327b4fcce82afa7c692364047b27c53d2b6ae7a0f2522806938c3c935ae9a735", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021120, "estimatedRequiredGiB": 37.948, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 33955496529, "modelscopeLicense": null, "modelscopeParams": 4112079360, "modelscopeTags": ["library:gguf", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 33955496529}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-14T12:34:59.173731+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4849005", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-15T14:38:14.995844+00:00", "modelId": "yujianboisme/qwen2.5-1.5b-darkhorse-code-fine-tuning", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3087467712, "estimatedRequiredGiB": 3.468, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 3103395696, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1543714304, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:lora", "library:safetensors", "task:text-generation", "custom_tag:text-generation", "custom_tag:qwen2.5", "custom_tag:lora", "custom_tag:json", "custom_tag:instruction-following", "custom_tag:chinese", "custom_tag:command-translation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3103395696}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T06:30:01.353257+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867729", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-15T14:38:14.995852+00:00", "modelId": "Edge0/Edge0-35B-A3B-preview", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19689863445, "estimatedRequiredGiB": 22.059, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 19738195355, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5419330688, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:lora", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:moe", "custom_tag:edge-inference", "custom_tag:prerouter", "custom_tag:lora", "custom_tag:ssd-offload"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19738195355}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T06:30:01.349241+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867727", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-15T14:38:14.995826+00:00", "modelId": "hcnote/SparkMuse-4B", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8224192576, "estimatedRequiredGiB": 9.203, "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": 8234364261, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:long-context", "custom_tag:1M-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8234364261}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T06:30:01.347118+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867731", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-15T14:38:14.995814+00:00", "modelId": "mlx-community/Agents-A1-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529500, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529500}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T06:30:01.355295+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867726", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-15T14:38:14.995834+00:00", "modelId": "mlx-community/Ornith-1.0-35B-OptiQ-4bit-REAP-19B", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 13249080076, "estimatedRequiredGiB": 14.83, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 13269529926, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3825799024, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:expert-pruning", "custom_tag:reap", "custom_tag:moe", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13269529926}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-15T06:30:01.357590+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4867730", "taskType": "text-generation", "verifyResult": null}
@@ -295,7 +291,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T06:13:01.261080+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2044205392, "estimatedRequiredGiB": 2.469, "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": 2209448692, "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": 2209448692}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T22:12:40.245394+00:00", "targetGpu": "Biren_166m", "taskId": "5007978", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-22T06:16:41.859329+00:00", "modelId": "nkkbr/Mini-K3-1H-attnres-block6-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-09-21T22:14:33.594032+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5008009", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-22T06:16:41.859310+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g16-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "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": "2026-09-21T22:14:33.592720+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5008010", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T06:22:45.060437+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "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": 2039076183}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T22:21:59.843515+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5008078", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-22T06:39:24.754141+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g2-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030713792, "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": 2039076183}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T22:38:57.960315+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5008253", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T07:42:35.356628+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g8-v1_C", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2018871528, "estimatedRequiredGiB": 2.26, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "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": 2022478516}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T22:54:40.090323+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5008420", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T07:42:35.356546+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-64-v2", "modelProfile": {"architectures": [], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2044205392, "estimatedRequiredGiB": 2.469, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2209448692, "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": 2209448692}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-21T22:58:24.607631+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5008471", "taskType": "text-generation", "verifyResult": null}
@@ -898,26 +893,18 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952812+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.669715+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321080", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.951913+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.752950+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321085", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-06T18:06:36.952269+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:47:42.948174+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5321086", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952372+00:00", "modelId": "ukisai/Swift-1.5-4bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 15826764635, "estimatedRequiredGiB": 17.725, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 15859925253, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15859925253}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.868816+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321209", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952703+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "497ab91cb1ba127d73c571f3ec8297e040a03e575e3c6ce93ccd36aa425663ac", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.928461+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321201", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952592+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-16-v2", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2036242696, "estimatedRequiredGiB": 2.46, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2201523288, "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": 2201523288}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.932288+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321205", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952031+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-2-v2", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033920112, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199304207, "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": 2199304207}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.938848+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321210", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952378+00:00", "modelId": "BananaMind/TernaryBananaMind-10M", "modelProfile": {"architectures": ["BananaAllForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bananaall", "modelscopeFileSize": 36069420, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:bananaall", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model", "custom_tag:bananamind", "custom_tag:bananamind2", "custom_tag:ternary", "custom_tag:int8-embeddings", "custom_tag:digit-tokenizer", "custom_tag:pytorch", "custom_tag:safetensors", "custom_tag:custom-code", "custom_tag:trust-remote-code", "custom_tag:custom-architecture"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 36069420}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.951340+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321208", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952037+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "modelscopeTags": ["license:mit", "model_type:qwen3_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:qwen3.5", "custom_tag:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.866238+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321206", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951790+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-standard-v1", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1932905544, "estimatedRequiredGiB": 2.313, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2070028245, "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:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2070028245}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.936620+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321200", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952477+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.930642+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321203", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.953027+00:00", "modelId": "nkkbr/Mini-K3-1H-kda-kernel-1-v2", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2033754200, "estimatedRequiredGiB": 2.458, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2199119539, "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": 2199119539}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.935477+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321204", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952926+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-gqa-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1933022288, "estimatedRequiredGiB": 2.322, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2077758206, "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:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2077758206}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.873128+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321199", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952144+00:00", "modelId": "nkkbr/Mini-K3-1H-llama-mha-block4-v1", "modelProfile": {"architectures": [], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1960285320, "estimatedRequiredGiB": 2.353, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2105033791, "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:llama-style-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2105033791}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.876580+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321207", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952807+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19282103457, "estimatedRequiredGiB": 21.582, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19310950017, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:5-bit", "custom_tag:affine", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19310950017}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:56:23.934000+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321202", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952921+00:00", "modelId": "amd/Qwen3.6-35B-A3B-w4a16-llmcompressor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20321390048, "estimatedRequiredGiB": 22.734, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 20341996128, "modelscopeLicense": "apache-2.0", "modelscopeParams": 35107181936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20341996128}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.756665+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321211", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.953021+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20593110848, "estimatedRequiredGiB": 23.04, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20616225866, "modelscopeLicense": "apache-2.0", "modelscopeParams": 424699392, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:sglang", "custom_tag:gptq", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:compressed-tensors", "custom_tag:llm-compressor", "custom_tag:safetensors", "custom_tag:qwen3.8", "custom_tag:conversational", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:roleplay", "custom_tag:character", "custom_tag:humanlike", "custom_tag:uncensored"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 20616225866}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.944154+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321215", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951907+00:00", "modelId": "mlabonne/LFM2.5-230M-Chess", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5201, "estimatedRequiredGiB": 0.522, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 467369015, "modelscopeLicense": "other", "modelscopeParams": 230688512, "modelscopeTags": ["license:other", "model_type:lfm2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:chess"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 467369015}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.962484+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321218", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952138+00:00", "modelId": "prithivMLmods/Orion-9B-Agentic-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.61, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19336478290, "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"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19336478290}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.759129+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321212", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952915+00:00", "modelId": "prithivMLmods/Nexus-9B-CodeCore-Merge", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306311000, "estimatedRequiredGiB": 21.602, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "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, "repositoryOnDiskBytes": 19329296879}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.069956+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321221", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952698+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 11077974096, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.850687+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321219", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952585+00:00", "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 9342812725, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.857043+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321213", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952025+00:00", "modelId": "togethercomputer/Tev1-0.8B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1746942600, "estimatedRequiredGiB": 1.978, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 1769900320, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1769900320}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.064744+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321223", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952471+00:00", "modelId": "ProCreations/Auto-Reason-3b", "modelProfile": {"architectures": ["SmolLM3ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6150235016, "estimatedRequiredGiB": 6.913, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "smollm3", "modelscopeFileSize": 6185547167, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:smollm3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:smollm3", "custom_tag:agent-safety", "custom_tag:tool-calling", "custom_tag:reasoning", "custom_tag:synthetic-data"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6185547167}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.852267+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321216", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951782+00:00", "modelId": "bench-labs/cagliostro-v3.5", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "1a93fa08e096ea6199b10994f8676be8fc032d458e70f127ff1c57cd7cfe44fa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 585441264, "estimatedRequiredGiB": 0.677, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 605680752}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.062922+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321220", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952801+00:00", "modelId": "webAI-Official/TwIL-LM2", "modelProfile": {"architectures": ["GraniteForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5067121544, "estimatedRequiredGiB": 20.413, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "granite", "modelscopeFileSize": 18264867356, "modelscopeLicense": "other", "modelscopeParams": null, "modelscopeTags": ["license:other", "model_type:granite", "library:pytorch", "library:transformer", "library:lora", "library:safetensors", "library:gguf", "task:text-generation", "custom_tag:granite", "custom_tag:formal-logic", "custom_tag:reasoning", "custom_tag:lora", "custom_tag:model-merging", "custom_tag:wise-ft", "custom_tag:reinforcement-learning", "custom_tag:grpo", "custom_tag:twil-lm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18264867356}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:49.859242+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321214", "taskType": "text-generation", "verifyResult": null}
@@ -942,7 +929,6 @@
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952571+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20984462832, "estimatedRequiredGiB": 23.486, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 21014909211, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5865901936, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwen3-next", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:mixture-of-experts"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 21014909211}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.660792+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321235", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952014+00:00", "modelId": "Akahsizrr/Cyber-Prime-1.1-2.6B", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5394427432, "estimatedRequiredGiB": 6.049, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 5412809492, "modelscopeLicense": "other", "modelscopeParams": 209741824, "modelscopeTags": ["license:other", "model_type:lfm2", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:cybersecurity", "custom_tag:cyberbench", "custom_tag:threat-intelligence", "custom_tag:named-entity-recognition", "custom_tag:phishing-detection", "custom_tag:http-anomaly-detection", "custom_tag:lfm2", "custom_tag:2.6b"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5412809492}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.967998+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321245", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.953011+00:00", "modelId": "cyankiwi/K2-Horizon-3.7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4749242120, "estimatedRequiredGiB": 5.332, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 4771310100, "modelscopeLicense": "apache-2.0", "modelscopeParams": 641597440, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:3.7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4771310100}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.763496+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321241", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951876+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320426072, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320426072}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.947704+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321243", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952253+00:00", "modelId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5033557128, "estimatedRequiredGiB": 5.638, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:minicpm", "custom_tag:minicpm5", "custom_tag:llama", "custom_tag:text-generation", "custom_tag:thinking", "custom_tag:fable5", "custom_tag:tool-calling", "custom_tag:function-calling", "custom_tag:agentic", "custom_tag:coding", "custom_tag:instruction-following", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5045067151}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.961173+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321246", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.952355+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-5bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 804816628, "estimatedRequiredGiB": 0.905, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 809580733, "modelscopeLicense": "other", "modelscopeParams": 219544320, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 809580733}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:51.156951+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321247", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-06T18:06:36.951746+00:00", "modelId": "mlx-community/K2-Horizon-3.7B-8bit", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5374667178, "estimatedRequiredGiB": 6.03, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 5395463319, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:dense", "custom_tag:k2-horizon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5395463319}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:57:50.965243+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5321242", "taskType": "text-generation", "verifyResult": null}
@@ -993,7 +979,6 @@
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T07:17:20.543965+00:00", "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T23:00:25.957994+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5343527", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-07T07:34:09.664104+00:00", "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "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": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 4}, "failureCount": 4, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+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": 4, "unresolvedFailureCount": 4}, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T23:21:09.752397+00:00", "targetGpu": "Biren_166m", "taskId": "5343725", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T07:50:57.145330+00:00", "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "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": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T23:37:28.160203+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5343926", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T08:44:05.654731+00:00", "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T00:32:27.150657+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5344555", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T12:29:58.757236+00:00", "modelId": "NovelAI/clio-v1-legacy", "modelProfile": {"architectures": ["StableLmForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6358779576, "estimatedRequiredGiB": 27.418, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "stablelm", "modelscopeFileSize": 24533499859, "modelscopeLicense": "gpl-2.0", "modelscopeParams": 3043786240, "modelscopeTags": ["license:gpl-2.0", "model_type:stablelm", "library:safetensors", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:model", "custom_tag:novelai", "custom_tag:legacy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 24533499859}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T03:47:04.967444+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5347241", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T12:29:58.757260+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2176034009, "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": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T03:47:04.988602+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5347240", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T13:29:11.757335+00:00", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "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": 7120900461, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1915564544, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:qwen3.5", "custom_tag:reasoning", "custom_tag:long-context", "custom_tag:function-calling", "custom_tag:tool-use", "custom_tag:agentic", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120900461}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T05:25:18.483418+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5348833", "taskType": "text-generation", "verifyResult": null}
@@ -1001,9 +986,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T14:17:19.252938+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": 2152567281, "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": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T06:12:07.558309+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "5349427", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T14:38:59.667442+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": 8145035684, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8145035684}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T06:35:26.373231+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5349735", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T14:38:59.667420+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T06:35:26.367604+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5349731", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T14:38:59.667466+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T06:35:26.357823+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5349733", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T14:38:59.667459+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981021}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T06:35:26.381282+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5349734", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-10-07T14:38:59.667452+00:00", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120900461, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1915564544, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:qwen3.5", "custom_tag:reasoning", "custom_tag:long-context", "custom_tag:function-calling", "custom_tag:tool-use", "custom_tag:agentic", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120900461}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T06:35:26.352295+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "5349732", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T14:53:58.249032+00:00", "modelId": "mlx-community/Hemmingway-1-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18966599842, "estimatedRequiredGiB": 21.22, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18986905904, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:writing"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 18986905904}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T06:47:00.055697+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5349878", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T14:53:58.249040+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-1kda-3mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1987222504, "estimatedRequiredGiB": 2.406, "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": 2152567281, "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": 2152567281}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T06:47:00.063821+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5349877", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-07T14:53:58.248997+00:00", "modelId": "nkkbr/Mini-K3-1H-attn-2kda-2mla-nope-v2", "modelProfile": {"architectures": [], "configFingerprint": "8b3c0a82b858cf26b1a0f6075074234a66487d5734741dbbfd4743963b967faa", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2010737208, "estimatedRequiredGiB": 2.432, "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": 2176034009, "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": 2176034009}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-07T06:47:00.057616+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5349876", "taskType": "text-generation", "verifyResult": null}