state: generation 31970 (intent)

This commit is contained in:
2026-10-23 17:40:26 +00:00
parent f3e1a28551
commit c2d148a650
7 changed files with 935 additions and 872 deletions

View File

@@ -506,7 +506,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-10-23T16:29:32.701896+00:00", "generatedAt": "2026-10-23T17:40:02.361063+00:00",
"summary": { "summary": {
"activeBlockCount": 25, "activeBlockCount": 25,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -1,5 +1,5 @@
{ {
"communityAttemptedAt": "2026-10-23T16:31:05.905165+00:00", "communityAttemptedAt": "2026-10-23T17:40:02.458484+00:00",
"communityError": "ModelHubAPIError: 分页大小不能超过100", "communityError": "ModelHubAPIError: 分页大小不能超过100",
"communitySample": {}, "communitySample": {},
"communityUpdatedAt": null, "communityUpdatedAt": null,
@@ -452,320 +452,320 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-10-23T16:31:05.905165+00:00", "generatedAt": "2026-10-23T17:40:02.458484+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 1351.3064516129032, "backlogHours": 1297.906976744186,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b3", "gpu": "Ascend_910-b3",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 10, "maxConcurrentTasks": 10,
"qualityFactor": 1.4090539560573094, "qualityFactor": 1.4857820894690112,
"queueFactor": 0.9277010389679453, "queueFactor": 0.9174393501818073,
"queueWeight": 0.9277010389679453, "queueWeight": 0.9174393501818073,
"recentSuccess": 40, "recentSuccess": 40,
"recentSuccessRate": 0.3225806451612903, "recentSuccessRate": 0.31007751937984496,
"recentTerminal": 124, "recentTerminal": 129,
"recentWilsonLowerBound": 0.24670272784213756, "recentWilsonLowerBound": 0.23672366283538512,
"running": 10, "running": 10,
"selectionWeight": 1.3071808189962595, "selectionWeight": 1.3631149546742176,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.666666666666668, "throughputPerHour": 21.5,
"waiting": 27927 "waiting": 27905
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1383.6170212765958, "backlogHours": 1249.8076923076924,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b4", "gpu": "Ascend_910-b4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 10, "maxConcurrentTasks": 10,
"qualityFactor": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.9244187295839714, "queueFactor": 0.9226509212153048,
"queueWeight": 0.9244187295839714, "queueWeight": 0.9226509212153048,
"recentSuccess": 56, "recentSuccess": 58,
"recentSuccessRate": 0.3971631205673759, "recentSuccessRate": 0.3717948717948718,
"recentTerminal": 141, "recentTerminal": 156,
"recentWilsonLowerBound": 0.3201558187006704, "recentWilsonLowerBound": 0.2998900637660186,
"running": 12, "running": 10,
"selectionWeight": 2.3110468239599284, "selectionWeight": 2.306627303038262,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.5, "throughputPerHour": 26.0,
"waiting": 32515 "waiting": 32495
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 179.4437086092715, "backlogHours": 228.5593220338983,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 10, "maxConcurrentTasks": 10,
"qualityFactor": 0.14371488613200342, "qualityFactor": 0.10834279796050629,
"queueFactor": 1.2558329828609094, "queueFactor": 1.1904579450635433,
"queueWeight": 1.2558329828609094, "queueWeight": 1.1904579450635433,
"recentSuccess": 20, "recentSuccess": 14,
"recentSuccessRate": 0.13245033112582782, "recentSuccessRate": 0.11864406779661017,
"recentTerminal": 151, "recentTerminal": 118,
"recentWilsonLowerBound": 0.08740289737091173, "recentWilsonLowerBound": 0.0720033998019242,
"running": 10, "running": 10,
"selectionWeight": 0.1804818941326698, "selectionWeight": 0.12897754462249897,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.166666666666668, "throughputPerHour": 19.666666666666668,
"waiting": 4516 "waiting": 4495
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 996.6055045871559, "backlogHours": 889.9180327868853,
"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": 0.11211282694036205, "qualityFactor": 0.14562597147812992,
"queueFactor": 0.9710523157220752, "queueFactor": 0.9708707066054406,
"queueWeight": 0.9710523157220752, "queueWeight": 0.9708707066054406,
"recentSuccess": 14, "recentSuccess": 16,
"recentSuccessRate": 0.12844036697247707, "recentSuccessRate": 0.13114754098360656,
"recentTerminal": 109, "recentTerminal": 122,
"recentWilsonLowerBound": 0.07807369166475243, "recentWilsonLowerBound": 0.08236340083536885,
"running": 7, "running": 7,
"selectionWeight": 0.10886742022258683, "selectionWeight": 0.14138398982907574,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.166666666666668, "throughputPerHour": 20.333333333333332,
"waiting": 18105 "waiting": 18095
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 411.19708029197085, "backlogHours": 385.1506849315069,
"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": 0.32565944198606095, "qualityFactor": 0.3996343885204463,
"queueFactor": 1.108954218109302, "queueFactor": 1.1008275691787728,
"queueWeight": 1.108954218109302, "queueWeight": 1.1008275691787728,
"recentSuccess": 25, "recentSuccess": 27,
"recentSuccessRate": 0.18248175182481752, "recentSuccessRate": 0.18493150684931506,
"recentTerminal": 137, "recentTerminal": 146,
"recentWilsonLowerBound": 0.12676767353162913, "recentWilsonLowerBound": 0.1303220534783932,
"running": 7, "running": 7,
"selectionWeight": 0.3611414118575638, "selectionWeight": 0.4399285524752082,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.833333333333332, "throughputPerHour": 24.333333333333332,
"waiting": 9389 "waiting": 9372
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 87.15107913669064, "backlogHours": 82.09556313993174,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 24, "maxConcurrentTasks": 24,
"qualityFactor": 0.05346385763399738, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 23, "recentSuccess": 22,
"recentSuccessRate": 0.08273381294964029, "recentSuccessRate": 0.07508532423208192,
"recentTerminal": 278, "recentTerminal": 293,
"recentWilsonLowerBound": 0.05576030804694043, "recentWilsonLowerBound": 0.05010488254217555,
"running": 24, "running": 24,
"selectionWeight": 0.0695030149241966, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 46.333333333333336, "throughputPerHour": 48.833333333333336,
"waiting": 4038 "waiting": 4009
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 330.2896551724138, "backlogHours": 296.74074074074076,
"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": 0.38702368722539005, "qualityFactor": 0.25773575328217496,
"queueFactor": 1.1460059560894293, "queueFactor": 1.1447412226156894,
"queueWeight": 1.1460059560894293, "queueWeight": 1.1447412226156894,
"recentSuccess": 28, "recentSuccess": 25,
"recentSuccessRate": 0.19310344827586207, "recentSuccessRate": 0.15432098765432098,
"recentTerminal": 145, "recentTerminal": 162,
"recentWilsonLowerBound": 0.1371158160661615, "recentWilsonLowerBound": 0.1067658535481554,
"running": 11, "running": 0,
"selectionWeight": 0.4435314507079894, "selectionWeight": 0.29504074132401265,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.166666666666668, "throughputPerHour": 27.0,
"waiting": 7982 "waiting": 8012
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 1969.591836734694, "backlogHours": 2192.318181818182,
"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": 0.19225206610347845, "qualityFactor": 0.5110943215463821,
"queueFactor": 0.8767276131500563, "queueFactor": 0.8480634783983779,
"queueWeight": 0.8767276131500563, "queueWeight": 0.8480634783983779,
"recentSuccess": 9, "recentSuccess": 11,
"recentSuccessRate": 0.1836734693877551, "recentSuccessRate": 0.25,
"recentTerminal": 49, "recentTerminal": 44,
"recentWilsonLowerBound": 0.09976228838458356, "recentWilsonLowerBound": 0.14574066080685744,
"running": 2, "running": 2,
"selectionWeight": 0.1685526950380695, "selectionWeight": 0.4334404281202839,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.166666666666666, "throughputPerHour": 7.333333333333333,
"waiting": 16085 "waiting": 16077
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 370.26206896551724, "backlogHours": 343.38461538461536,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 0.38702368722539005, "qualityFactor": 0.22462089359338647,
"queueFactor": 1.1265351238311918, "queueFactor": 1.1199452023546284,
"queueWeight": 1.1265351238311918, "queueWeight": 1.1199452023546284,
"recentSuccess": 28, "recentSuccess": 23,
"recentSuccessRate": 0.19310344827586207, "recentSuccessRate": 0.14743589743589744,
"recentTerminal": 145, "recentTerminal": 156,
"recentWilsonLowerBound": 0.1371158160661615, "recentWilsonLowerBound": 0.10029628994550262,
"running": 9, "running": 8,
"selectionWeight": 0.4359957774140592, "selectionWeight": 0.2515630921285226,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.166666666666668, "throughputPerHour": 26.0,
"waiting": 8948 "waiting": 8928
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 642.1121495327103, "backlogHours": 571.55,
"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": 0.9277050801812586, "qualityFactor": 0.686470782988538,
"queueFactor": 1.0372405514936127, "queueFactor": 1.0375421868915236,
"queueWeight": 1.0372405514936127, "queueWeight": 1.0375421868915236,
"recentSuccess": 30, "recentSuccess": 28,
"recentSuccessRate": 0.2803738317757009, "recentSuccessRate": 0.23333333333333334,
"recentTerminal": 107, "recentTerminal": 120,
"recentWilsonLowerBound": 0.20401679054167657, "recentWilsonLowerBound": 0.16665469513089648,
"running": 4, "running": 4,
"selectionWeight": 0.9622533289906349, "selectionWeight": 0.7122423974190643,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.833333333333332, "throughputPerHour": 20.0,
"waiting": 11451 "waiting": 11431
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1549.7058823529412, "backlogHours": 1549.235294117647,
"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": 1.442783828816564, "qualityFactor": 2.234131605734595,
"queueFactor": 0.9088322472083833, "queueFactor": 0.8934007060224293,
"queueWeight": 0.9088322472083833, "queueWeight": 0.8934007060224293,
"recentSuccess": 34, "recentSuccess": 38,
"recentSuccessRate": 0.3333333333333333, "recentSuccessRate": 0.37254901960784315,
"recentTerminal": 102, "recentTerminal": 102,
"recentWilsonLowerBound": 0.2493697609902782, "recentWilsonLowerBound": 0.28494828732820177,
"running": 4, "running": 4,
"selectionWeight": 1.3112484693792732, "selectionWeight": 1.9959747539103108,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.0, "throughputPerHour": 17.0,
"waiting": 26345 "waiting": 26337
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 3397.818181818182, "backlogHours": 2950.421052631579,
"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": 0.13906701305560298, "qualityFactor": 0.05,
"queueFactor": 0.8078692914282477, "queueFactor": 0.8111128821616749,
"queueWeight": 0.8078692914282477, "queueWeight": 0.8111128821616749,
"recentSuccess": 6, "recentSuccess": 4,
"recentSuccessRate": 0.18181818181818182, "recentSuccessRate": 0.10526315789473684,
"recentTerminal": 33, "recentTerminal": 38,
"recentWilsonLowerBound": 0.08610651225698264, "recentWilsonLowerBound": 0.04170189793266581,
"running": 2, "running": 2,
"selectionWeight": 0.11234796929827286, "selectionWeight": 0.040555644108083745,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": false,
"throughputPerHour": 5.5, "throughputPerHour": 6.333333333333333,
"waiting": 18688 "waiting": 18686
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 535.064039408867, "backlogHours": 562.0103626943005,
"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": 0.5527736184714995, "qualityFactor": 0.8505587754620192,
"queueFactor": 1.066007489474953, "queueFactor": 1.040165033195255,
"queueWeight": 1.066007489474953, "queueWeight": 1.040165033195255,
"recentSuccess": 43, "recentSuccess": 46,
"recentSuccessRate": 0.21182266009852216, "recentSuccessRate": 0.23834196891191708,
"recentTerminal": 203, "recentTerminal": 193,
"recentWilsonLowerBound": 0.16123362795295199, "recentWilsonLowerBound": 0.1837078341451914,
"running": 18, "running": 16,
"selectionWeight": 0.5892608172747887, "selectionWeight": 0.8847214969129666,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 33.833333333333336, "throughputPerHour": 32.166666666666664,
"waiting": 18103 "waiting": 18078
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 1387.7383177570093, "backlogHours": 1440.8155339805824,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "hygon_k100-ai", "gpu": "hygon_k100-ai",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 6, "maxConcurrentTasks": 6,
"qualityFactor": 0.40441688376565504, "qualityFactor": 0.7185374342360767,
"queueFactor": 0.9240064089371199, "queueFactor": 0.9031765256696916,
"queueWeight": 0.9240064089371199, "queueWeight": 0.9031765256696916,
"recentSuccess": 22, "recentSuccess": 25,
"recentSuccessRate": 0.205607476635514, "recentSuccessRate": 0.24271844660194175,
"recentTerminal": 107, "recentTerminal": 103,
"recentWilsonLowerBound": 0.13988321742546095, "recentWilsonLowerBound": 0.17014922730424603,
"running": 6, "running": 6,
"selectionWeight": 0.3736837924818436, "selectionWeight": 0.6489661434169544,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.833333333333332, "throughputPerHour": 17.166666666666668,
"waiting": 24748 "waiting": 24734
} }
}, },
"queueAttemptedAt": "2026-10-23T16:31:05.905165+00:00", "queueAttemptedAt": "2026-10-23T17:40:02.458484+00:00",
"queueError": "ModelHubAPIError: Network request failed for https://modelhub.org.cn/api/computility/power/machine/list/machine-info", "queueError": null,
"queueUpdatedAt": "2026-10-23T16:15:30.154515+00:00", "queueUpdatedAt": "2026-10-23T17:40:02.458484+00:00",
"supportedGpus": [ "supportedGpus": [
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",
"Vastai_va16", "Vastai_va16",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-10-23T14:45:02.435401+00:00", "generatedAt": "2026-10-23T17:40:02.270959+00:00",
"lastSyncTime": "2026-10-23T14:45:02.363525+00:00", "lastSyncTime": "2026-10-23T17:40:01.945857+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -71,27 +71,6 @@
"targetGpu": "Ascend_910-b3", "targetGpu": "Ascend_910-b3",
"taskType": "text-generation" "taskType": "text-generation"
}, },
"ascend_910-b4|vllm_tokenizer_patch|text-generation|architectures:spark2_5forcausallm": {
"architectureSignature": "architectures:spark2_5forcausallm",
"architectures": [
"spark2_5forcausallm"
],
"evidenceCount": 1,
"expiresAt": "2026-10-23T15:05:50.784052+00:00",
"framework": "vllm_tokenizer_patch",
"latestFailureAt": "2026-09-23T15:05:50.784052+00:00",
"latestSuccessfulAt": null,
"matchType": "architectures",
"modelType": null,
"sourceModelIds": [
"cyankiwi/Spark-X2.5-4B-AWQ-INT4"
],
"sourceTaskIds": [
"5042147"
],
"targetGpu": "Ascend_910-b4",
"taskType": "text-generation"
},
"ascend_910-b4|vllm|text-generation|model_type:gemma4": { "ascend_910-b4|vllm|text-generation|model_type:gemma4": {
"architectureSignature": "model_type:gemma4", "architectureSignature": "model_type:gemma4",
"architectures": [], "architectures": [],
@@ -532,12 +511,11 @@
} }
}, },
"architectureCompatibilitySummary": { "architectureCompatibilitySummary": {
"activeBlockCount": 26, "activeBlockCount": 25,
"byGpuFramework": { "byGpuFramework": {
"Ascend_910-b3|vllm": 1, "Ascend_910-b3|vllm": 1,
"Ascend_910-b3|vllm_tokenizer_patch": 2, "Ascend_910-b3|vllm_tokenizer_patch": 2,
"Ascend_910-b4|vllm": 1, "Ascend_910-b4|vllm": 1,
"Ascend_910-b4|vllm_tokenizer_patch": 1,
"Cambricon_mlu-370-x4|vllm-customized": 1, "Cambricon_mlu-370-x4|vllm-customized": 1,
"Cambricon_mlu-370-x8|vllm-mlu": 2, "Cambricon_mlu-370-x8|vllm-mlu": 2,
"Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 2, "Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0": 2,
@@ -1103,29 +1081,29 @@
"unresolvedFailureCount": 11 "unresolvedFailureCount": 11
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation": { "Cambricon_mlu-370-x4|vllm-mlu|text-generation": {
"attributableFailureCount": 36, "attributableFailureCount": 37,
"decisionFailureRate": 0.8, "decisionFailureRate": 0.8043,
"decisionSuccessRate": 0.2, "decisionSuccessRate": 0.1957,
"decisionTotal": 45, "decisionTotal": 46,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 55, "ambiguous_runtime": 55,
"framework_architecture_unsupported": 32, "framework_architecture_unsupported": 33,
"model_load": 4, "model_load": 4,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"参数/模板问题": 5, "参数/模板问题": 5,
"验证失败": 3 "验证失败": 3
}, },
"failureCount": 100, "failureCount": 101,
"failureRate": 0.9174, "failureRate": 0.9182,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 9, "successCount": 9,
"successRate": 0.0826, "successRate": 0.0818,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 109, "total": 110,
"unresolvedFailureCount": 63 "unresolvedFailureCount": 63
}, },
"Cambricon_mlu-370-x4|vllm|text-generation": { "Cambricon_mlu-370-x4|vllm|text-generation": {
@@ -3306,27 +3284,27 @@
"unresolvedFailureCount": 58 "unresolvedFailureCount": 58
}, },
"vllm-mlu": { "vllm-mlu": {
"attributableFailureCount": 62, "attributableFailureCount": 63,
"decisionFailureRate": 0.7381, "decisionFailureRate": 0.7412,
"decisionSuccessRate": 0.2619, "decisionSuccessRate": 0.2588,
"decisionTotal": 84, "decisionTotal": 85,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 114, "ambiguous_runtime": 114,
"framework_architecture_unsupported": 54, "framework_architecture_unsupported": 55,
"model_load": 7, "model_load": 7,
"platform_infrastructure": 1, "platform_infrastructure": 1,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 47, "参数/模板问题": 47,
"验证失败": 3 "验证失败": 3
}, },
"failureCount": 227, "failureCount": 228,
"failureRate": 0.9116, "failureRate": 0.912,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 22, "successCount": 22,
"successRate": 0.0884, "successRate": 0.088,
"total": 249, "total": 250,
"unresolvedFailureCount": 164 "unresolvedFailureCount": 164
}, },
"vllm-patch-tokenizer": { "vllm-patch-tokenizer": {
@@ -3430,7 +3408,7 @@
"unresolvedFailureCount": 341 "unresolvedFailureCount": 341
} }
}, },
"generatedAt": "2026-10-23T14:45:02.419752+00:00", "generatedAt": "2026-10-23T17:40:02.252614+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 133, "attributableFailureCount": 133,
@@ -3519,15 +3497,15 @@
"unresolvedFailureCount": 608 "unresolvedFailureCount": 608
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"attributableFailureCount": 770, "attributableFailureCount": 771,
"decisionFailureRate": 0.9123, "decisionFailureRate": 0.9124,
"decisionSuccessRate": 0.0877, "decisionSuccessRate": 0.0876,
"decisionTotal": 844, "decisionTotal": 845,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 520, "ambiguous_runtime": 520,
"architecture_compatibility": 53, "architecture_compatibility": 53,
"context_length": 48, "context_length": 48,
"framework_architecture_unsupported": 322, "framework_architecture_unsupported": 323,
"memory_capacity": 219, "memory_capacity": 219,
"model_load": 8, "model_load": 8,
"platform_infrastructure": 16, "platform_infrastructure": 16,
@@ -3537,14 +3515,14 @@
"日志缺失": 13, "日志缺失": 13,
"验证失败": 42 "验证失败": 42
}, },
"failureCount": 1676, "failureCount": 1677,
"failureRate": 0.9577, "failureRate": 0.9577,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 16, "platformFailureCount": 16,
"successCount": 74, "successCount": 74,
"successRate": 0.0423, "successRate": 0.0423,
"total": 1750, "total": 1751,
"unresolvedFailureCount": 890 "unresolvedFailureCount": 890
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
@@ -9903,16 +9881,16 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none": { "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none": {
"attributableFailureCount": 9, "attributableFailureCount": 10,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 9, "decisionTotal": 10,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 9, "framework_architecture_unsupported": 10,
"参数/模板问题": 1, "参数/模板问题": 1,
"验证失败": 1 "验证失败": 1
}, },
"failureCount": 11, "failureCount": 12,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"modelType": "qwen3_5", "modelType": "qwen3_5",
@@ -9924,7 +9902,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 11, "total": 12,
"unresolvedFailureCount": 2 "unresolvedFailureCount": 2
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_vl|none": { "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_vl|none": {
@@ -37769,15 +37747,15 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|33": { "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|33": {
"attributableFailureCount": 4, "attributableFailureCount": 5,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 4, "decisionTotal": 5,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 4, "framework_architecture_unsupported": 5,
"验证失败": 1 "验证失败": 1
}, },
"failureCount": 5, "failureCount": 6,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"loadSizeLog2Bucket": 33, "loadSizeLog2Bucket": 33,
@@ -37790,7 +37768,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 5, "total": 6,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|34": { "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5|none|34": {
@@ -61150,20 +61128,20 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 17994, "terminalRecords": 17995,
"totalRecords": 18538, "totalRecords": 18539,
"totals": { "totals": {
"attributableFailureCount": 6370, "attributableFailureCount": 6371,
"decisionFailureRate": 0.866, "decisionFailureRate": 0.866,
"decisionSuccessRate": 0.134, "decisionSuccessRate": 0.134,
"decisionTotal": 7356, "decisionTotal": 7357,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4672, "ambiguous_runtime": 4672,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 137, "backend_operator": 137,
"context_length": 328, "context_length": 328,
"framework_architecture_unsupported": 2365, "framework_architecture_unsupported": 2366,
"memory_capacity": 1207, "memory_capacity": 1207,
"model_load": 577, "model_load": 577,
"platform_infrastructure": 972, "platform_infrastructure": 972,
@@ -61174,14 +61152,14 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 17008, "failureCount": 17009,
"failureRate": 0.9452, "failureRate": 0.9452,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 972, "platformFailureCount": 972,
"successCount": 986, "successCount": 986,
"successRate": 0.0548, "successRate": 0.0548,
"total": 17994, "total": 17995,
"unresolvedFailureCount": 9666 "unresolvedFailureCount": 9666
}, },
"warnings": [ "warnings": [
@@ -61237,14 +61215,14 @@
"组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Biren_166m|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_mrv-100|unknown|visual-multi-modal 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|llamacpp|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|llamacpp|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Kunlunxin_p-800|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 Kunlunxin_p-800|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
"组合 Cambricon_mlu-370-x4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。"
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 18538, "summarizedRecords": 18539,
"version": 1 "version": 1
} }

View File

@@ -3733,6 +3733,18 @@
{"batchId": "4ba40262d41d4141871a82e2c8ef7e3d", "completedAt": "2026-10-23T09:25:25.190554+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T09:25:22.571790+00:00", "framework": "vllm_tokenizer_patch", "intentId": "16d775d2d9e84b2c9f96cd48661d178c", "lastModified": "2026-10-21T19:08:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-23T17:38:29.916960+00:00", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5735872", "taskType": "text-generation"} {"batchId": "4ba40262d41d4141871a82e2c8ef7e3d", "completedAt": "2026-10-23T09:25:25.190554+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T09:25:22.571790+00:00", "framework": "vllm_tokenizer_patch", "intentId": "16d775d2d9e84b2c9f96cd48661d178c", "lastModified": "2026-10-21T19:08:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "reason": null, "reconciledAt": "2026-10-23T17:38:29.916960+00:00", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5735872", "taskType": "text-generation"}
{"batchId": "3240b9dc6ea34cfa957079f469e9ae4b", "completedAt": "2026-10-23T11:15:29.377844+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T11:15:26.821111+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3d111b54d33a4ad6a01ce40afe6240df", "lastModified": "2026-10-22T01:37:07+00:00", "modelAddress": "https://modelscope.cn/models/RecursiveSI/flint-int4", "reason": null, "reconciledAt": "2026-10-23T17:38:29.916107+00:00", "repoId": "RecursiveSI/flint-int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5737151", "taskType": "text-generation"} {"batchId": "3240b9dc6ea34cfa957079f469e9ae4b", "completedAt": "2026-10-23T11:15:29.377844+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T11:15:26.821111+00:00", "framework": "vllm_tokenizer_patch", "intentId": "3d111b54d33a4ad6a01ce40afe6240df", "lastModified": "2026-10-22T01:37:07+00:00", "modelAddress": "https://modelscope.cn/models/RecursiveSI/flint-int4", "reason": null, "reconciledAt": "2026-10-23T17:38:29.916107+00:00", "repoId": "RecursiveSI/flint-int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5737151", "taskType": "text-generation"}
{"batchId": "3d8c0e91978f43e09b0ff79b372b0077", "completedAt": "2026-10-23T13:28:14.742077+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-23T13:27:58.482566+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2bbf1c38663f4f2a91f1f3c5a47eb79f", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-23T17:38:29.916459+00:00", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5738981", "taskType": "text-generation"} {"batchId": "3d8c0e91978f43e09b0ff79b372b0077", "completedAt": "2026-10-23T13:28:14.742077+00:00", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-23T13:27:58.482566+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2bbf1c38663f4f2a91f1f3c5a47eb79f", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-23T17:38:29.916459+00:00", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "MetaX_c-500", "taskId": "5738981", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.574645+00:00", "framework": "vllm_tokenizer_patch", "intentId": "5d292602ee4d4b47b6be26ca9de1dbf6", "lastModified": "2026-10-22T01:37:07+00:00", "modelAddress": "https://modelscope.cn/models/RecursiveSI/flint-int4", "repoId": "RecursiveSI/flint-int4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.574751+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e396811cf14c49c5b196a26a53c9eaf1", "lastModified": "2026-10-21T19:08:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.574800+00:00", "framework": "vllm_tokenizer_patch", "intentId": "1836fafdc2d44225b7af529ed665920a", "lastModified": "2026-10-21T17:08:03+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-8bit", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-8bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "MetaX_c-500", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "705b8b3614c86a1ac722c97f43e177e84ca20282e9799fffb1b890510d641728", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.574845+00:00", "framework": "llamacpp", "intentId": "537eba6d0ad4477089b19fca74cdef50", "lastModified": "2026-10-21T18:16:46+00:00", "modelAddress": "https://modelscope.cn/models/AtomicChat/Qwen3.5-9B-DFlash-GGUF", "repoId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.574901+00:00", "framework": "vllm_tokenizer_patch", "intentId": "339e9017a6394a289030d5e055d9f579", "lastModified": "2026-10-21T16:58:14+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/KAT-Dev-AWQ-4bit", "repoId": "cyankiwi/KAT-Dev-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.574955+00:00", "framework": "vllm_tokenizer_patch", "intentId": "73bb008fedcd40a186adeb038f83b7db", "lastModified": "2026-10-21T16:41:10+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.575006+00:00", "framework": "vllm_tokenizer_patch", "intentId": "440cf101317341e9b1d6b053352abfe6", "lastModified": "2026-10-21T16:33:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "repoId": "cyankiwi/Qwen3-4B-Instruct-2507-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.575045+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2e5aeb3607fc4f4786ed0a9942cf67f6", "lastModified": "2026-10-21T16:31:51+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.575083+00:00", "framework": "vllm_tokenizer_patch", "intentId": "15602e80081d4b9c8dc16488056640bf", "lastModified": "2026-10-23T13:17:05+00:00", "modelAddress": "https://modelscope.cn/models/ukisai/Swift-1.5-4bit-MLX", "repoId": "ukisai/Swift-1.5-4bit-MLX", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.575121+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d0129ecf523d44bea44c5bbb5efa4741", "lastModified": "2026-10-21T17:21:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "repoId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT8", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.575159+00:00", "framework": "vllm_tokenizer_patch", "intentId": "4a4ff8622da042ed9ad33cd094857507", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "c3d21430f5d849ca9dbcc7af7ccc9435", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:40:26.575205+00:00", "framework": "vllm_tokenizer_patch", "intentId": "f043429abd9b40a68cb4e32c45ed3562", "lastModified": "2026-10-21T16:19:52+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "repoId": "cyankiwi/IQuest-Coder-V1-40B-Loop-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Ascend_910-b3", "taskType": "text-generation"}
{"batchId": "09e4bbe7fcce4d2fa47a6bfa8717a3e3", "completedAt": "2026-10-23T17:38:22.196368+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:38:18.904899+00:00", "framework": "vllm_tokenizer_patch", "intentId": "44001346bd334d2b8fa5c65b506ac8dc", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"} {"batchId": "09e4bbe7fcce4d2fa47a6bfa8717a3e3", "completedAt": "2026-10-23T17:38:22.196368+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:38:18.904899+00:00", "framework": "vllm_tokenizer_patch", "intentId": "44001346bd334d2b8fa5c65b506ac8dc", "repoId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b3", "taskId": null, "taskType": "text-generation"}
{"batchId": "09e4bbe7fcce4d2fa47a6bfa8717a3e3", "completedAt": "2026-10-23T17:38:22.196366+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:38:18.904845+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2b30253c4c464e6293a05d850727bb74", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "09e4bbe7fcce4d2fa47a6bfa8717a3e3", "completedAt": "2026-10-23T17:38:22.196366+00:00", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:38:18.904845+00:00", "framework": "vllm_tokenizer_patch", "intentId": "2b30253c4c464e6293a05d850727bb74", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "09e4bbe7fcce4d2fa47a6bfa8717a3e3", "completedAt": "2026-10-23T17:38:22.196362+00:00", "configFingerprint": "705b8b3614c86a1ac722c97f43e177e84ca20282e9799fffb1b890510d641728", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:38:18.904791+00:00", "framework": "llamacpp", "intentId": "9f88ee49e4504fcba974d01854d76bd1", "repoId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"} {"batchId": "09e4bbe7fcce4d2fa47a6bfa8717a3e3", "completedAt": "2026-10-23T17:38:22.196362+00:00", "configFingerprint": "705b8b3614c86a1ac722c97f43e177e84ca20282e9799fffb1b890510d641728", "configSource": "modelhub_live", "createdAt": "2026-10-23T17:38:18.904791+00:00", "framework": "llamacpp", "intentId": "9f88ee49e4504fcba974d01854d76bd1", "repoId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "capacity_deferred", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}

View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "a50f6212902095ce17f32e150e8bf29f3763261172cf16a74d16164eabba1783", ".modelhub_state/account_capacity.json": "a50f6212902095ce17f32e150e8bf29f3763261172cf16a74d16164eabba1783",
".modelhub_state/architecture_compatibility_blacklist.json": "826b43377cd010ec4ea185d6f4934160789c4543392b2a8d8eb8f255cf87be2d", ".modelhub_state/architecture_compatibility_blacklist.json": "7e9b10d8063d273bd27d971034df85b2f8f8f6c153571f8ee07d2e23c89860a2",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "3fd2377448d957d79182973daaeaf79dd867eded1dc5f9e20b3c403215c161d7", ".modelhub_state/market_intelligence.json": "54e2bf1f9b19714b69429e82625a17aacc75d33c185e100c4e899732843c1672",
".modelhub_state/official_capabilities.json": "45f743ef90fcdb577500264af6744e534f3932b1b996346760fcf62f25b37258", ".modelhub_state/official_capabilities.json": "b6e53f627e78ccc8ffeb7fb5b1013d5aa2e5777721d2a858404f294e286599b7",
".modelhub_state/outcome_checkpoint.json": "a6057cb4be70fe7cc840e42c01c7087921ed93a043d54f3b7b3c1cabcda914f7", ".modelhub_state/outcome_checkpoint.json": "6a597d64f5a648058094005b3713925133d81daccbb2dcd583ba6fc2a008dc60",
".modelhub_state/queue_cleanup_latest.json": "b9f4ab6b802f11fba1eac4aab36681bb1c55ca9ec453f998ff165c36b204bca4", ".modelhub_state/queue_cleanup_latest.json": "b9f4ab6b802f11fba1eac4aab36681bb1c55ca9ec453f998ff165c36b204bca4",
".modelhub_state/recent_outcomes.jsonl": "4e9ea96530129301fd28fce2a2553a0c3ac736a88199c5f646c5d1f197302806", ".modelhub_state/recent_outcomes.jsonl": "4e9ea96530129301fd28fce2a2553a0c3ac736a88199c5f646c5d1f197302806",
".modelhub_state/recovery_active_tasks.jsonl": "1c32494d4639b199a79d8461f5a8d22f32dd6922d3f6e49b467a43b078f96fc4", ".modelhub_state/recovery_active_tasks.jsonl": "1c32494d4639b199a79d8461f5a8d22f32dd6922d3f6e49b467a43b078f96fc4",
".modelhub_state/recovery_intents.jsonl": "4d42275d3435e42d9e36ca2c03d8c99ce3e9eea7372415a79595d7fdd7b3a2ff", ".modelhub_state/recovery_intents.jsonl": "79a4a2ee952f3853e492a6899612676442918ae8b735db8b4a4783b59a592e65",
".modelhub_state/routing_intelligence.json": "7e7cfac499fefb395f5d1bb9d616d3110adb91be6f6e5cb4cf8c767f02a3747e", ".modelhub_state/routing_intelligence.json": "7e7cfac499fefb395f5d1bb9d616d3110adb91be6f6e5cb4cf8c767f02a3747e",
".modelhub_state/submission_exclusions.jsonl": "3bb99a0a703cee6767cdaeed2e3d26480ebf6d1cb44552f40bf65c94d9ed58b1", ".modelhub_state/submission_exclusions.jsonl": "3bb99a0a703cee6767cdaeed2e3d26480ebf6d1cb44552f40bf65c94d9ed58b1",
".modelhub_state/worker_crashes.jsonl": "0e675b1c3ea5c2ab436cf083668db8830733f3e9d03420e10a8563a589acb517", ".modelhub_state/worker_crashes.jsonl": "0e675b1c3ea5c2ab436cf083668db8830733f3e9d03420e10a8563a589acb517",
"ledger/submissions.jsonl": "3d8aa5d757abc53e8fdef68f6355847de0058d65dbfcb8917138cabc8e4b65b5", "ledger/submissions.jsonl": "3d8aa5d757abc53e8fdef68f6355847de0058d65dbfcb8917138cabc8e4b65b5",
"outcomes/submissions.jsonl": "2a969e2be7d5739c7bf82fcd953f2e7681bfda512741566eb737dab68962642c" "outcomes/submissions.jsonl": "1bc79810308a1a1c27ef80d3c617fe394a7c5218885a700210057e15022a6874"
}, },
"generation": 31969, "generation": 31970,
"phase": "cycle", "phase": "intent",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-10-23T17:38:30.122891+00:00", "updatedAt": "2026-10-23T17:40:26.901156+00:00",
"writerId": "6cd7cbd5a7014f838149942b3e5927f7" "writerId": "6cd7cbd5a7014f838149942b3e5927f7"
} }

View File

@@ -172,7 +172,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-24T03:34:38.852704+00:00", "modelId": "IFM/K2-Horizon-7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "a015ad361c8b35c70c85648256a591979967ef38682323a28f85efdfa8060bd0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9573964160, "estimatedRequiredGiB": 59.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 53374659671, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53374659671}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-23T19:33:16.585033+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5046043", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-24T03:34:38.852704+00:00", "modelId": "IFM/K2-Horizon-7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "a015ad361c8b35c70c85648256a591979967ef38682323a28f85efdfa8060bd0", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9573964160, "estimatedRequiredGiB": 59.651, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 53374659671, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 53374659671}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-23T19:33:16.585033+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5046043", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T03:51:15.462063+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3320832164, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790145}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-23T19:47:42.048287+00:00", "targetGpu": "Vastai_va16", "taskId": "5046271", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T03:51:15.462063+00:00", "modelId": "IFM/K2-Horizon-32B-NVFP4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "cbe5569cdb6c42553436b837dd5b8f0cfa03334642a56f4ff0137f952f8eb84b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 23253718728, "estimatedRequiredGiB": 26.013, "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": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3320832164, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:32b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 23275790145}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-23T19:47:42.048287+00:00", "targetGpu": "Vastai_va16", "taskId": "5046271", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T14:06:39.057071+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": null, "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": "2026-09-24T06:05:15.403300+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5054597", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T14:06:39.057071+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": null, "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": "2026-09-24T06:05:15.403300+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5054597", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T14:06:39.057047+00:00", "modelId": "Youssofal/MiMo-V2.6-Qwen-9B-MTPLX-Optimized-Speed", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8674987255, "estimatedRequiredGiB": 9.718, "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": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "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:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:local-llm", "custom_tag:llm", "custom_tag:coding", "custom_tag:agentic", "custom_tag:mimo", "custom_tag:xiaomi", "custom_tag:qwen3.5", "custom_tag:qwen3-5", "custom_tag:9b", "custom_tag:6-bit", "custom_tag:m5", "custom_tag:m5-max", "custom_tag:m4", "custom_tag:m3", "custom_tag:macbook-air", "custom_tag:macbook-pro", "custom_tag:mac-mini", "custom_tag:opencode", "custom_tag:claude-code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8695114401}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T06:05:15.443994+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054596", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T14:24:00.455827+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "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": "2026-09-24T06:21:33.668586+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054819", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T14:24:00.455827+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "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": "2026-09-24T06:21:33.668586+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054819", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T19:28:25.557808+00:00", "modelId": "primitive-ai/DeepSeek-V4-Flash-Vision-Exp-REAP-145B", "modelProfile": {"architectures": ["DeepseekV4ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 83322353204, "estimatedRequiredGiB": 93.133, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4", "modelscopeFileSize": 83334245282, "modelscopeLicense": "mit", "modelscopeParams": 145799322711, "modelscopeTags": ["license:mit", "model_type:deepseek_v4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:deepseek_v4", "custom_tag:reap", "custom_tag:expert-pruning", "custom_tag:mxfp4", "custom_tag:vllm", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 83334245282}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T11:26:47.190154+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5060689", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T19:28:25.557808+00:00", "modelId": "primitive-ai/DeepSeek-V4-Flash-Vision-Exp-REAP-145B", "modelProfile": {"architectures": ["DeepseekV4ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 83322353204, "estimatedRequiredGiB": 93.133, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4", "modelscopeFileSize": 83334245282, "modelscopeLicense": "mit", "modelscopeParams": 145799322711, "modelscopeTags": ["license:mit", "model_type:deepseek_v4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:deepseek_v4", "custom_tag:reap", "custom_tag:expert-pruning", "custom_tag:mxfp4", "custom_tag:vllm", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 83334245282}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T11:26:47.190154+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5060689", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T20:02:26.569106+00:00", "modelId": "juspay/xor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70214495944, "estimatedRequiredGiB": 78.493, "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": 70234635423, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-23T21:42:41.557218+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": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 70234635423}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T12:00:45.395392+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5061116", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T20:02:26.569106+00:00", "modelId": "juspay/xor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70214495944, "estimatedRequiredGiB": 78.493, "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": 70234635423, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-23T21:42:41.557218+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": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 70234635423}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T12:00:45.395392+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5061116", "taskType": "text-generation", "verifyResult": null}
@@ -1088,6 +1087,6 @@
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-23T13:29:07.557889+00:00", "modelId": "InternScience/Sage-A1.5-Q8_0-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "91915287b76ea7e05cad914ff86bc370079e1da493390c06596dc5d6300af314", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37802150112, "estimatedRequiredGiB": 43.253, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 38701690304, "modelscopeLicense": "apache-2.0", "modelscopeParams": 446571248, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic", "custom_tag:code", "custom_tag:tool-use", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38701690304}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T05:27:06.829874+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5732271", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-23T13:29:07.557889+00:00", "modelId": "InternScience/Sage-A1.5-Q8_0-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "91915287b76ea7e05cad914ff86bc370079e1da493390c06596dc5d6300af314", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 37802150112, "estimatedRequiredGiB": 43.253, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 38701690304, "modelscopeLicense": "apache-2.0", "modelscopeParams": 446571248, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:moe", "custom_tag:vlm", "custom_tag:vision", "custom_tag:agentic", "custom_tag:code", "custom_tag:tool-use", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 38701690304}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T05:27:06.829874+00:00", "targetGpu": "Mthreads_s4000", "taskId": "5732271", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-23T14:46:53.252391+00:00", "modelId": "XHToken/Spark-X2.6-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "57aceff29ff69c4fb34602873529ff182196395d82e08b39e53f9350ca14eca7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021824, "estimatedRequiredGiB": 18.048, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 16148689583, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16148689583}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T06:45:26.931962+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5733467", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-10-23T14:46:53.252391+00:00", "modelId": "XHToken/Spark-X2.6-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "57aceff29ff69c4fb34602873529ff182196395d82e08b39e53f9350ca14eca7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4375021824, "estimatedRequiredGiB": 18.048, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 16148689583, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:transformer", "library:gguf", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16148689583}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T06:45:26.931962+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5733467", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-23T14:46:53.252365+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.786, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125281593, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "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_tokenizer_patch", "lastTerminalAt": "2026-10-22T11:48:09.066588+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 14125281593}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T06:45:26.950299+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5733468", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-23T14:46:53.252365+00:00", "modelId": "cyankiwi/Nemotron-Cascade-8B-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9869921096, "estimatedRequiredGiB": 15.786, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 14125281593, "modelscopeLicense": "other", "modelscopeParams": 8190735360, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:Nemotron-Cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "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_tokenizer_patch", "lastTerminalAt": "2026-10-22T11:48:09.066588+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 14125281593}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T06:45:26.950299+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5733468", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["KimiLinearForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54087705936, "estimatedRequiredGiB": 60.459, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kimi_linear", "modelscopeFileSize": 54097373275, "modelscopeLicense": "mit", "modelscopeParams": 49122681728, "modelscopeTags": ["license:mit", "model_type:kimi_linear", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 54097373275}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-23T09:25:23.728480+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5735872", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-23T17:40:01.945822+00:00", "modelId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["KimiLinearForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54087705936, "estimatedRequiredGiB": 60.459, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kimi_linear", "modelscopeFileSize": 54097373275, "modelscopeLicense": "mit", "modelscopeParams": 49122681728, "modelscopeTags": ["license:mit", "model_type:kimi_linear", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 54097373275}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T09:25:23.728480+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5735872", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RecursiveSI/flint-int4", "modelProfile": {"architectures": ["FlintForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22568912600, "estimatedRequiredGiB": 25.235, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "flint", "modelscopeFileSize": 22580274594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3572482016, "modelscopeTags": ["license:apache-2.0", "model_type:flint", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:int4", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22580274594}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-23T11:15:27.958590+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5737151", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RecursiveSI/flint-int4", "modelProfile": {"architectures": ["FlintForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22568912600, "estimatedRequiredGiB": 25.235, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "flint", "modelscopeFileSize": 22580274594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3572482016, "modelscopeTags": ["license:apache-2.0", "model_type:flint", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:int4", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22580274594}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-23T11:15:27.958590+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5737151", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292651057, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14292651057}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-23T13:28:00.360187+00:00", "targetGpu": "MetaX_c-500", "taskId": "5738981", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292651057, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14292651057}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-23T13:28:00.360187+00:00", "targetGpu": "MetaX_c-500", "taskId": "5738981", "taskType": "text-generation", "verifyResult": null}