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

state: generation 6241 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-12 14:43:21 +00:00
parent 15af86d9ff
commit b84b20cb04
10 changed files with 2529 additions and 2774 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -65,17 +65,17 @@
"architectureSignature": "model_type:qwen3_5", "architectureSignature": "model_type:qwen3_5",
"architectures": [], "architectures": [],
"evidenceCount": 1, "evidenceCount": 1,
"expiresAt": "2026-10-05T18:17:21+00:00", "expiresAt": "2026-10-12T14:35:21+00:00",
"framework": "vllm", "framework": "vllm",
"latestFailureAt": "2026-09-05T18:17:21+00:00", "latestFailureAt": "2026-09-12T14:35:21+00:00",
"latestSuccessfulAt": null, "latestSuccessfulAt": null,
"matchType": "model_type", "matchType": "model_type",
"modelType": "qwen3_5", "modelType": "qwen3_5",
"sourceModelIds": [ "sourceModelIds": [
"Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16" "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8"
], ],
"sourceTaskIds": [ "sourceTaskIds": [
"4332826" "4543632"
], ],
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation" "taskType": "text-generation"
@@ -1383,7 +1383,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-12T14:40:32.637696+00:00", "generatedAt": "2026-09-12T14:43:20.539348+00:00",
"summary": { "summary": {
"activeBlockCount": 70, "activeBlockCount": 70,
"byGpuFramework": { "byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -27,7 +27,7 @@
"11": { "11": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 449, "listingErrors": 450,
"nextPage": 1, "nextPage": 1,
"recordsScanned": 0, "recordsScanned": 0,
"uniqueRecords": 0 "uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00", "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0, "failureLogsInspected": 0,
"mode": "incremental_decision_only", "mode": "incremental_decision_only",
"nextAccountIndex": 11, "nextAccountIndex": 0,
"recordsScanned": 0, "recordsScanned": 0,
"seenTaskIds": [], "seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00", "startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0, "terminalRecords": 0,
"uniqueRecords": 0, "uniqueRecords": 0,
"updatedAt": "2026-09-12T14:40:32.612392+00:00", "updatedAt": "2026-09-12T14:43:20.516346+00:00",
"version": 1 "version": 1
} }

288
.modelhub_state/market_intelligence.json
View File

@@ -416,121 +416,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T14:38:42.504238+00:00", "generatedAt": "2026-09-12T14:41:41.036180+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1010.2877697841726, "backlogHours": 1017.3478260869565,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b3", "gpu": "Ascend_910-b3",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 1.3188817983441763, "qualityFactor": 1.4175736989841956,
"queueFactor": 0.9815872020192699, "queueFactor": 0.9799703806167503,
"queueWeight": 0.9815872020192699, "queueWeight": 0.9799703806167503,
"recentSuccess": 58, "recentSuccess": 58,
"recentSuccessRate": 0.4172661870503597, "recentSuccessRate": 0.42028985507246375,
"recentTerminal": 139, "recentTerminal": 138,
"recentWilsonLowerBound": 0.33859380424958263, "recentWilsonLowerBound": 0.3411867089821718,
"running": 8, "running": 8,
"selectionWeight": 1.294597494230803, "selectionWeight": 1.3891802373458368,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.166666666666668, "throughputPerHour": 23.0,
"waiting": 23405 "waiting": 23399
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1329.4354838709676, "backlogHours": 1385.09243697479,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b4", "gpu": "Ascend_910-b4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 1.1134014071917375, "qualityFactor": 1.0380056681655727,
"queueFactor": 0.9419884152593109, "queueFactor": 0.9356459777979393,
"queueWeight": 0.9419884152593109, "queueWeight": 0.9356459777979393,
"recentSuccess": 49, "recentSuccess": 45,
"recentSuccessRate": 0.3951612903225806, "recentSuccessRate": 0.37815126050420167,
"recentTerminal": 124, "recentTerminal": 119,
"recentWilsonLowerBound": 0.313505613184297, "recentWilsonLowerBound": 0.29612237996338414,
"running": 8, "running": 8,
"selectionWeight": 1.0488112271080314, "selectionWeight": 0.9712058283505807,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.666666666666668, "throughputPerHour": 19.833333333333332,
"waiting": 27475 "waiting": 27471
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 180.58441558441558, "backlogHours": 181.49019607843138,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.3044980792316853, "qualityFactor": 0.3507697579851947,
"queueFactor": 1.2708480051113937, "queueFactor": 1.2691279046785904,
"queueWeight": 1.2708480051113937, "queueWeight": 1.2691279046785904,
"recentSuccess": 36, "recentSuccess": 37,
"recentSuccessRate": 0.23376623376623376, "recentSuccessRate": 0.24183006535947713,
"recentTerminal": 154, "recentTerminal": 153,
"recentWilsonLowerBound": 0.17390244213855313, "recentWilsonLowerBound": 0.18084212559818538,
"running": 8, "running": 8,
"selectionWeight": 0.38697077655183837, "selectionWeight": 0.4451716879763664,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.666666666666668, "throughputPerHour": 25.5,
"waiting": 4635 "waiting": 4628
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1669.0384615384617, "backlogHours": 1522.5263157894738,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x4", "gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.48668669805566006, "qualityFactor": 0.3505579562548259,
"queueFactor": 0.9103862715702695, "queueFactor": 0.9224623454698073,
"queueWeight": 0.9103862715702695, "queueWeight": 0.9224623454698073,
"recentSuccess": 17, "recentSuccess": 16,
"recentSuccessRate": 0.3269230769230769, "recentSuccessRate": 0.2807017543859649,
"recentTerminal": 52, "recentTerminal": 57,
"recentWilsonLowerBound": 0.2152190173110406, "recentWilsonLowerBound": 0.18079248284972232,
"running": 7, "running": 7,
"selectionWeight": 0.4430728884657379, "selectionWeight": 0.3233765145499288,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.666666666666666, "throughputPerHour": 9.5,
"waiting": 14465 "waiting": 14464
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 496.9906542056075, "backlogHours": 483.54545454545456,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x8", "gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.3954281467339861, "qualityFactor": 0.4682150773996907,
"queueFactor": 1.091800825767323, "queueFactor": 1.0956397316530382,
"queueWeight": 1.091800825767323, "queueWeight": 1.0956397316530382,
"recentSuccess": 29, "recentSuccess": 31,
"recentSuccessRate": 0.27102803738317754, "recentSuccessRate": 0.2818181818181818,
"recentTerminal": 107, "recentTerminal": 110,
"recentWilsonLowerBound": 0.19583435081989597, "recentWilsonLowerBound": 0.206210213519945,
"running": 7, "running": 7,
"selectionWeight": 0.4317287771358082, "selectionWeight": 0.5129950417581036,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.833333333333332, "throughputPerHour": 18.333333333333332,
"waiting": 8863 "waiting": 8865
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 42.79538904899135, "backlogHours": 47.65273311897106,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -539,197 +539,197 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 21, "recentSuccess": 23,
"recentSuccessRate": 0.06051873198847262, "recentSuccessRate": 0.07395498392282958,
"recentTerminal": 347, "recentTerminal": 311,
"recentWilsonLowerBound": 0.03992000666861856, "recentWilsonLowerBound": 0.049782298177424335,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 57.833333333333336, "throughputPerHour": 51.833333333333336,
"waiting": 2475 "waiting": 2470
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 74.9620253164557, "backlogHours": 92.21789883268482,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-150", "gpu": "Iluvatar_bi-150",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 50, "maxConcurrentTasks": 50,
"qualityFactor": 0.11327171375694076, "qualityFactor": 0.13313455837932414,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 46, "recentSuccess": 40,
"recentSuccessRate": 0.14556962025316456, "recentSuccessRate": 0.1556420233463035,
"recentTerminal": 316, "recentTerminal": 257,
"recentWilsonLowerBound": 0.11094179470680914, "recentWilsonLowerBound": 0.11642817349129465,
"running": 2, "running": 1,
"selectionWeight": 0.14725322788402298, "selectionWeight": 0.1730749258931214,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 52.666666666666664, "throughputPerHour": 42.833333333333336,
"waiting": 3948 "waiting": 3950
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2743.9411764705883, "backlogHours": 2914.875,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_mrv-100", "gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.3756275842863389, "qualityFactor": 0.4577502083944315,
"queueFactor": 0.8449663855809182, "queueFactor": 0.8368360451188179,
"queueWeight": 0.8449663855809182, "queueWeight": 0.8368360451188179,
"recentSuccess": 11, "recentSuccess": 11,
"recentSuccessRate": 0.3235294117647059, "recentSuccessRate": 0.34375,
"recentTerminal": 34, "recentTerminal": 32,
"recentWilsonLowerBound": 0.19131451326458573, "recentWilsonLowerBound": 0.2041023335432855,
"running": 2, "running": 2,
"selectionWeight": 0.3173926822189195, "selectionWeight": 0.3830618740451108,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 5.666666666666667, "throughputPerHour": 5.333333333333333,
"waiting": 15549 "waiting": 15546
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 817.7777777777778, "backlogHours": 838.5569620253165,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.274526896356359, "qualityFactor": 0.3072615501216139,
"queueFactor": 1.013212072981388, "queueFactor": 1.0087963060694622,
"queueWeight": 1.013212072981388, "queueWeight": 1.0087963060694622,
"recentSuccess": 20, "recentSuccess": 20,
"recentSuccessRate": 0.24691358024691357, "recentSuccessRate": 0.25316455696202533,
"recentTerminal": 81, "recentTerminal": 79,
"recentWilsonLowerBound": 0.1659018738026735, "recentWilsonLowerBound": 0.1702773604894678,
"running": 7, "running": 7,
"selectionWeight": 0.2781539657463732, "selectionWeight": 0.309964316759861,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 13.5, "throughputPerHour": 13.166666666666666,
"waiting": 11040 "waiting": 11041
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 652.5142857142857, "backlogHours": 665.0679611650485,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "MetaX_c-500", "gpu": "MetaX_c-500",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 0.27776932824238054, "qualityFactor": 0.3067531103754004,
"queueFactor": 1.0481106841938441, "queueFactor": 1.0444880236945049,
"queueWeight": 1.0481106841938441, "queueWeight": 1.0444880236945049,
"recentSuccess": 25, "recentSuccess": 25,
"recentSuccessRate": 0.23809523809523808, "recentSuccessRate": 0.24271844660194175,
"recentTerminal": 105, "recentTerminal": 103,
"recentWilsonLowerBound": 0.16678968751856937, "recentWilsonLowerBound": 0.17014922730424603,
"running": 4, "running": 4,
"selectionWeight": 0.29113300067218595, "selectionWeight": 0.32039995001814425,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.5, "throughputPerHour": 17.166666666666668,
"waiting": 11419 "waiting": 11417
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2046.952380952381, "backlogHours": 1924.3880597014927,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Mthreads_s4000", "gpu": "Mthreads_s4000",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 1.9314126343897107, "qualityFactor": 2.0654270553009066,
"queueFactor": 0.8829365410026397, "queueFactor": 0.8906139033639533,
"queueWeight": 0.8829365410026397, "queueWeight": 0.8906139033639533,
"recentSuccess": 33, "recentSuccess": 35,
"recentSuccessRate": 0.5238095238095238, "recentSuccessRate": 0.5223880597014925,
"recentTerminal": 63, "recentTerminal": 67,
"recentWilsonLowerBound": 0.4027014429047192, "recentWilsonLowerBound": 0.4048498852683165,
"running": 4, "running": 4,
"selectionWeight": 1.7053147906568473, "selectionWeight": 1.8394980518350563,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.5, "throughputPerHour": 11.166666666666666,
"waiting": 21493 "waiting": 21489
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 3765.391304347826, "backlogHours": 3936.5454545454545,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Sunrise_pt-200-x1", "gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.36192699594036104, "qualityFactor": 0.42499767388097165,
"queueFactor": 0.8057941951278319, "queueFactor": 0.7999559593509202,
"queueWeight": 0.8057941951278319, "queueWeight": 0.7999559593509202,
"recentSuccess": 8, "recentSuccess": 8,
"recentSuccessRate": 0.34782608695652173, "recentSuccessRate": 0.36363636363636365,
"recentTerminal": 23, "recentTerminal": 22,
"recentWilsonLowerBound": 0.18811054636982238, "recentWilsonLowerBound": 0.19732972772607896,
"running": 2, "running": 2,
"selectionWeight": 0.2916386723887973, "selectionWeight": 0.3399794219313622,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 3.8333333333333335, "throughputPerHour": 3.6666666666666665,
"waiting": 14434 "waiting": 14434
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 967.3432835820896, "backlogHours": 939.3913043478261,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Vastai_va16", "gpu": "Vastai_va16",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 16, "maxConcurrentTasks": 16,
"qualityFactor": 0.27081258308437683, "qualityFactor": 0.2675522272558072,
"queueFactor": 0.9880036719210764, "queueFactor": 0.991759543487484,
"queueWeight": 0.9880036719210764, "queueWeight": 0.991759543487484,
"recentSuccess": 17, "recentSuccess": 17,
"recentSuccessRate": 0.2537313432835821, "recentSuccessRate": 0.2463768115942029,
"recentTerminal": 67, "recentTerminal": 69,
"recentWilsonLowerBound": 0.1648777957769739, "recentWilsonLowerBound": 0.1598964745113261,
"running": 16, "running": 16,
"selectionWeight": 0.2675638264897959, "selectionWeight": 0.2653474747622789,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.166666666666666, "throughputPerHour": 11.5,
"waiting": 10802 "waiting": 10803
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 640.7045454545455, "backlogHours": 655.3255813953488,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "hygon_k100-ai", "gpu": "hygon_k100-ai",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 6, "maxConcurrentTasks": 6,
"qualityFactor": 2.5, "qualityFactor": 2.5,
"queueFactor": 1.0509861211761637, "queueFactor": 1.046802618746375,
"queueWeight": 1.0509861211761637, "queueWeight": 1.046802618746375,
"recentSuccess": 49, "recentSuccess": 47,
"recentSuccessRate": 0.5568181818181818, "recentSuccessRate": 0.5465116279069767,
"recentTerminal": 88, "recentTerminal": 86,
"recentWilsonLowerBound": 0.45281603242067786, "recentWilsonLowerBound": 0.44155981420304113,
"running": 6, "running": 6,
"selectionWeight": 2.6274653029404096, "selectionWeight": 2.6170065468659374,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 14.666666666666666, "throughputPerHour": 14.333333333333334,
"waiting": 9397 "waiting": 9393
} }
}, },
"queueAttemptedAt": "2026-09-12T14:29:34.136598+00:00", "queueAttemptedAt": "2026-09-12T14:41:41.036180+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-12T14:29:34.136598+00:00", "queueUpdatedAt": "2026-09-12T14:41:41.036180+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Iluvatar_mrv-100", "Iluvatar_mrv-100",

2407
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

104
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-12T14:12:46.471291+00:00", "generatedAt": "2026-09-12T14:41:33.654436+00:00",
"lastSyncTime": "2026-09-12T14:12:46.256625+00:00", "lastSyncTime": "2026-09-12T14:41:33.434355+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -69,17 +69,17 @@
"architectureSignature": "model_type:qwen3_5", "architectureSignature": "model_type:qwen3_5",
"architectures": [], "architectures": [],
"evidenceCount": 1, "evidenceCount": 1,
"expiresAt": "2026-10-05T18:17:21+00:00", "expiresAt": "2026-10-12T14:35:21+00:00",
"framework": "vllm", "framework": "vllm",
"latestFailureAt": "2026-09-05T18:17:21+00:00", "latestFailureAt": "2026-09-12T14:35:21+00:00",
"latestSuccessfulAt": null, "latestSuccessfulAt": null,
"matchType": "model_type", "matchType": "model_type",
"modelType": "qwen3_5", "modelType": "qwen3_5",
"sourceModelIds": [ "sourceModelIds": [
"Youssofal/Qwen3.8-27B-MTPLX-Optimized-Speed-FP16" "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8"
], ],
"sourceTaskIds": [ "sourceTaskIds": [
"4332826" "4543632"
], ],
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation" "taskType": "text-generation"
@@ -1451,17 +1451,17 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Ascend_910-b3|vllm|text-generation": { "Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 27, "attributableFailureCount": 28,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 27, "decisionTotal": 28,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 28, "ambiguous_runtime": 28,
"framework_architecture_unsupported": 25, "framework_architecture_unsupported": 26,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 1 "tokenizer_compatibility": 1
}, },
"failureCount": 55, "failureCount": 56,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -1471,7 +1471,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 55, "total": 56,
"unresolvedFailureCount": 28 "unresolvedFailureCount": 28
}, },
"Ascend_910-b4|llamacpp|text-generation": { "Ascend_910-b4|llamacpp|text-generation": {
@@ -2417,14 +2417,14 @@
"unresolvedFailureCount": 866 "unresolvedFailureCount": 866
}, },
"vllm": { "vllm": {
"attributableFailureCount": 273, "attributableFailureCount": 274,
"decisionFailureRate": 0.9891, "decisionFailureRate": 0.9892,
"decisionSuccessRate": 0.0109, "decisionSuccessRate": 0.0108,
"decisionTotal": 276, "decisionTotal": 277,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 200, "ambiguous_runtime": 200,
"backend_operator": 34, "backend_operator": 34,
"framework_architecture_unsupported": 187, "framework_architecture_unsupported": 188,
"memory_capacity": 6, "memory_capacity": 6,
"model_load": 26, "model_load": 26,
"platform_infrastructure": 1, "platform_infrastructure": 1,
@@ -2433,14 +2433,14 @@
"tokenizer_compatibility": 6, "tokenizer_compatibility": 6,
"参数/模板问题": 24 "参数/模板问题": 24
}, },
"failureCount": 498, "failureCount": 499,
"failureRate": 0.994, "failureRate": 0.994,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 3, "successCount": 3,
"successRate": 0.006, "successRate": 0.006,
"total": 501, "total": 502,
"unresolvedFailureCount": 224 "unresolvedFailureCount": 224
}, },
"vllm-mlu": { "vllm-mlu": {
@@ -2545,29 +2545,29 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-12T14:12:46.465723+00:00", "generatedAt": "2026-09-12T14:41:33.648453+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 27, "attributableFailureCount": 28,
"decisionFailureRate": 0.9643, "decisionFailureRate": 0.9655,
"decisionSuccessRate": 0.0357, "decisionSuccessRate": 0.0345,
"decisionTotal": 28, "decisionTotal": 29,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 28, "ambiguous_runtime": 28,
"framework_architecture_unsupported": 25, "framework_architecture_unsupported": 26,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 8, "参数/模板问题": 8,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 90, "failureCount": 91,
"failureRate": 0.989, "failureRate": 0.9891,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.011, "successRate": 0.0109,
"total": 91, "total": 92,
"unresolvedFailureCount": 63 "unresolvedFailureCount": 63
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
@@ -4274,21 +4274,21 @@
}, },
"recentCombinationStats": { "recentCombinationStats": {
"Ascend_910-b3|vllm|text-generation": { "Ascend_910-b3|vllm|text-generation": {
"attributableFailureCount": 1, "attributableFailureCount": 2,
"consecutiveFailures": 1, "consecutiveFailures": 2,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 1, "decisionTotal": 2,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 19, "ambiguous_runtime": 18,
"framework_architecture_unsupported": 1 "framework_architecture_unsupported": 2
}, },
"failureCount": 20, "failureCount": 20,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
"lastTerminalAt": "2026-09-12T13:37:49.606306+00:00", "lastTerminalAt": "2026-09-12T14:41:33.434355+00:00",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
@@ -4297,7 +4297,7 @@
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation", "taskType": "text-generation",
"total": 20, "total": 20,
"unresolvedFailureCount": 19 "unresolvedFailureCount": 18
}, },
"Ascend_910-b4|unknown|text-generation": { "Ascend_910-b4|unknown|text-generation": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -4585,19 +4585,19 @@
"unresolvedFailureCount": 19 "unresolvedFailureCount": 19
}, },
"MetaX_c-500|vllm|text-generation": { "MetaX_c-500|vllm|text-generation": {
"attributableFailureCount": 6, "attributableFailureCount": 5,
"consecutiveFailures": 6, "consecutiveFailures": 5,
"consecutivePlatformFailures": 0, "consecutivePlatformFailures": 0,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 6, "decisionTotal": 5,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 1, "ambiguous_runtime": 1,
"framework_architecture_unsupported": 2, "framework_architecture_unsupported": 1,
"model_load": 3, "model_load": 3,
"repository_structure": 1 "repository_structure": 1
}, },
"failureCount": 7, "failureCount": 6,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"lastPlatformFailureAt": null, "lastPlatformFailureAt": null,
@@ -4609,7 +4609,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "MetaX_c-500", "targetGpu": "MetaX_c-500",
"taskType": "text-generation", "taskType": "text-generation",
"total": 7, "total": 6,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Mthreads_s4000|llamacpp|text-generation": { "Mthreads_s4000|llamacpp|text-generation": {
@@ -7256,17 +7256,17 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1722, "terminalRecords": 1723,
"totalRecords": 1809, "totalRecords": 1810,
"totals": { "totals": {
"attributableFailureCount": 483, "attributableFailureCount": 484,
"decisionFailureRate": 0.8944, "decisionFailureRate": 0.8946,
"decisionSuccessRate": 0.1056, "decisionSuccessRate": 0.1054,
"decisionTotal": 540, "decisionTotal": 541,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 404, "ambiguous_runtime": 404,
"backend_operator": 42, "backend_operator": 42,
"framework_architecture_unsupported": 296, "framework_architecture_unsupported": 297,
"memory_capacity": 11, "memory_capacity": 11,
"model_load": 72, "model_load": 72,
"platform_infrastructure": 4, "platform_infrastructure": 4,
@@ -7276,21 +7276,20 @@
"参数/模板问题": 101, "参数/模板问题": 101,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1665, "failureCount": 1666,
"failureRate": 0.9669, "failureRate": 0.9669,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 4, "platformFailureCount": 4,
"successCount": 57, "successCount": 57,
"successRate": 0.0331, "successRate": 0.0331,
"total": 1722, "total": 1723,
"unresolvedFailureCount": 1178 "unresolvedFailureCount": 1178
}, },
"warnings": [ "warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。",
@@ -7299,6 +7298,7 @@
"GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。",
@@ -7320,6 +7320,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1809, "summarizedRecords": 1810,
"version": 1 "version": 1
} }

2
.modelhub_state/recent_outcomes.jsonl
View File

@@ -1,3 +1,4 @@
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm", "lastSyncTime": "2026-09-12T14:41:33.434355+00:00", "modelId": "primitive-ai/Qwen3.8-27B-mixed-NVFP4-FP8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T14:35:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4543632", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T14:12:46.256625+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T14:11:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4543480", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T14:12:46.256625+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T14:11:21+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4543480", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T13:37:49.606306+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T13:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4546528", "taskType": "text-generation", "verifyResult": -1} {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["nemotron_h"], "framework": "vllm", "lastSyncTime": "2026-09-12T13:37:49.606306+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T13:37:21+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4546528", "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": "", "lastSyncTime": "2026-09-12T13:02:08.318677+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T12:55:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560063", "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": "", "lastSyncTime": "2026-09-12T13:02:08.318677+00:00", "modelId": "primitive-ai/Nemotron-3.5-Lightning-30B-A3B-mixed-INT4-INT8", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-12T12:55:21+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4560063", "taskType": "text-generation", "verifyResult": -1}
@@ -297,4 +298,3 @@
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-09T11:33:22.442275+00:00", "modelId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090490505, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T02:37:59.437448+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9090490505}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:45.784701+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729501", "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": "2026-09-09T11:33:22.442275+00:00", "modelId": "nm-testing/Meta-llama3-8b-Instruct-SmoothQuant-Fp8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090490505, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T02:37:59.437448+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9090490505}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:45.784701+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729501", "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": "2026-09-09T14:42:07.646504+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090490459, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T02:37:59.437448+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9090490459}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:45.697968+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729508", "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": "2026-09-09T14:42:07.646504+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test-bos", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9081287016, "estimatedRequiredGiB": 10.159, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9090490459, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T02:37:59.437448+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 9090490459}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:45.697968+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729508", "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": "2026-09-10T08:02:07.004675+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5700679600, "estimatedRequiredGiB": 6.381, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5709884743, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T02:37:59.437448+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 5709884743}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:45.685300+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729504", "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": "2026-09-10T08:02:07.004675+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5700679600, "estimatedRequiredGiB": 6.381, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5709884743, "modelscopeLicense": null, "modelscopeParams": 8030261248, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-07T02:37:59.437448+00:00", "modelType": "llama", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 5709884743}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T23:02:45.685300+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4729504", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "framework": "vllm", "lastSyncTime": "2026-09-08T22:32:41.015088+00:00", "modelId": "amd/Qwen3-4B-awq-quant-onnx-hybrid", "modelProfile": {}, "outcome": "failed", "status": "success", "submitTime": "2026-09-08T22:31:21+00:00", "targetGpu": "MetaX_c-500", "taskId": "4079127", "taskType": "text-generation", "verifyResult": -1}

1208
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1254
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

22
manifest.json
View File

@@ -1,24 +1,24 @@
{ {
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "013735751b7b985fa3e9f418efea1a1ba3eda421181e16b68c48dde20dcb0fce", ".modelhub_state/architecture_compatibility_blacklist.json": "81f121f1be14a8fc41b0a79aeb7fe2b9c87a2289c33a26de0e1ad3cf36e8c103",
".modelhub_state/architecture_history_backfill.json": "8c8ec249a0f46450e351444cfc7ae69e683ab10718193c92592ae910180ccdaf", ".modelhub_state/architecture_history_backfill.json": "dea37564dab7cd9352c5942412a407b9533524365a47298dfa3e655eb3f4151a",
".modelhub_state/market_intelligence.json": "b2e6b7f2fc62dcb136aa64c8225d420d8ad20d07665ca642ea39501a64e0f8f6", ".modelhub_state/market_intelligence.json": "17792a900791c3c287b15f327fae6a93fb144d34adcd89d28fe16e43e0db9080",
".modelhub_state/official_capabilities.json": "ca6d0315832ebb9982b437edfb640ccaf8383edb3382c3123adb4acfc3d76f2b", ".modelhub_state/official_capabilities.json": "cbe994f3e4684449db8886a23bb106ebe091f4680d916a5e06bbe48ea42c4581",
".modelhub_state/outcome_checkpoint.json": "15fbb258182e612a2d14dbb0be89f50e33ec43ff1a9960d19678a0c3e3029249", ".modelhub_state/outcome_checkpoint.json": "1456f673633f7b2e5db24836f5bb76ebf089a4bbf7005bd88499fea67b27c196",
".modelhub_state/queue_cleanup_latest.json": "ecc68d43eaa771f35cd07fa219bd853d351a804602ed91e977e807e91d62ae63", ".modelhub_state/queue_cleanup_latest.json": "ecc68d43eaa771f35cd07fa219bd853d351a804602ed91e977e807e91d62ae63",
".modelhub_state/recent_outcomes.jsonl": "d10a4edece0a93cf3452fbc872013bd8dc99add3eb27ddb56f13ae26a619952c", ".modelhub_state/recent_outcomes.jsonl": "d89360d9b1497793a7c0c0386ee9383eebd3c5264e9768b2c52a599dc109c7cb",
".modelhub_state/recovery_active_tasks.jsonl": "6721bfc12d9bacfff483f751d3c6a1d40686acd4ef329400d2eeac24842dffaf", ".modelhub_state/recovery_active_tasks.jsonl": "cdbfb785baf7356dd7f8ac93661dcae267d030d1b490a490cdd03a67027eabdb",
".modelhub_state/recovery_intents.jsonl": "417547f30dee5635cc6c2a7bf1cca47b7cdc0db59b67dbe3ec31185117583a6b", ".modelhub_state/recovery_intents.jsonl": "f090ec6eb6c8eda20331c47bc205ff9c0514a4f3b4ac8b49ea5c43f840362946",
".modelhub_state/routing_intelligence.json": "1fd08052d188703295b385ad2baefdf48051a8712c8c95922bacea9b34745263", ".modelhub_state/routing_intelligence.json": "1fd08052d188703295b385ad2baefdf48051a8712c8c95922bacea9b34745263",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220", ".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162", ".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "ca0794aeab385493f756235c9dd69be4eff4d8f005bdf57f93adf86b21bd571a", "ledger/submissions.jsonl": "ca0794aeab385493f756235c9dd69be4eff4d8f005bdf57f93adf86b21bd571a",
"outcomes/submissions.jsonl": "b630bbdd954d9d2fc754b89e3ba0a7e412a1b33406ac48351f50a2ca59ff7527" "outcomes/submissions.jsonl": "cc1c7f4e84da44fa007c4dbf2a318d553e807a3daf9acae97f0aface85d44538"
}, },
"generation": 6240, "generation": 6241,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-12T14:40:32.776068+00:00", "updatedAt": "2026-09-12T14:43:21.214696+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2" "writerId": "e5dd59a4c84a4f21926bad61448789e2"
} }

2
outcomes/submissions.jsonl
View File

@@ -623,7 +623,7 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T13:02:08.318710+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T04:52:57.116897+00:00", "targetGpu": "Biren_166m", "taskId": "4794241", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T13:02:08.318710+00:00", "modelId": "CohereLabs/tiny-aya-base-32K", "modelProfile": {"architectures": ["Cohere2ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6700539432, "estimatedRequiredGiB": 7.522, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cohere2", "modelscopeFileSize": 6730839322, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": 3350243328, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:cohere2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:aya", "custom_tag:multilingual", "custom_tag:long-context", "custom_tag:tiny-aya"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 6730839322}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T04:52:57.116897+00:00", "targetGpu": "Biren_166m", "taskId": "4794241", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T13:02:08.318700+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T04:52:57.114996+00:00", "targetGpu": "Biren_166m", "taskId": "4794242", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-12T13:02:08.318700+00:00", "modelId": "ddalcu/Qwen3.8-27B-MLX-Serve-iQ-MLX-3.8bpw", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12999919368, "estimatedRequiredGiB": 14.555, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 13023155398, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3544073216, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:mlx-serve", "custom_tag:qwen3_5", "custom_tag:apple-silicon", "custom_tag:imatrix", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13023155398}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T04:52:57.114996+00:00", "targetGpu": "Biren_166m", "taskId": "4794242", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-12T14:23:18.821537+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "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": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T06:19:56.330927+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4795478", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-12T14:23:18.821537+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "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": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T06:19:56.330927+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4795478", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "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": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-12T06:36:56.396629+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4795634", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-12T14:41:33.434314+00:00", "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "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": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T06:36:56.396629+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4795634", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-12T06:53:56.898337+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4795839", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-12T06:53:56.898337+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4795839", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:00:25.508497+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-12T10:58:56.807180+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800525", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "mlx-community/Ornith-1.5-35B-A3B-8bit", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37721402856, "estimatedRequiredGiB": 42.187, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 37748367893, "modelscopeLicense": "mit", "modelscopeParams": 10195701616, "modelscopeTags": ["license:mit", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 2}, "failureCount": 2, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-09T14:00:25.508497+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 2, "unresolvedFailureCount": 2}, "repositoryOnDiskBytes": 37748367893}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-12T10:58:56.807180+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800525", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65827374264, "estimatedRequiredGiB": 73.588, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 65845719365, "modelscopeLicense": "other", "modelscopeParams": 32913266240, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 65845719365}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-12T10:58:56.798553+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800526", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": null, "modelId": "unsloth/NVIDIA-Nemotron-3.5-Lightning-30B-A3B", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 65827374264, "estimatedRequiredGiB": 73.588, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 65845719365, "modelscopeLicense": "other", "modelscopeParams": 32913266240, "modelscopeTags": ["license:other", "model_type:nemotron_h", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch", "custom_tag:nemotron-3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 65845719365}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-12T10:58:56.798553+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4800526", "taskType": "text-generation", "verifyResult": null}