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

state: generation 14862 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-24 13:37:19 +00:00
parent 6e4f70b071
commit 63e95f5e38
8 changed files with 1663 additions and 1617 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -3204,7 +3204,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-24T13:31:51.604995+00:00", "generatedAt": "2026-09-24T13:36:52.656597+00:00",
"summary": { "summary": {
"activeBlockCount": 161, "activeBlockCount": 161,
"byGpuFramework": { "byGpuFramework": {

224
.modelhub_state/market_intelligence.json
View File

@@ -396,99 +396,99 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-24T13:35:44.475445+00:00", "generatedAt": "2026-09-24T13:37:15.488969+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1152.3221476510068, "backlogHours": 1183.8620689655172,
"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": 0.9384234278933614, "qualityFactor": 0.951483790913402,
"queueFactor": 0.9146216912074664, "queueFactor": 0.9108877150795957,
"queueWeight": 0.9146216912074664, "queueWeight": 0.9108877150795957,
"recentSuccess": 53, "recentSuccess": 52,
"recentSuccessRate": 0.35570469798657717, "recentSuccessRate": 0.3586206896551724,
"recentTerminal": 149, "recentTerminal": 145,
"recentWilsonLowerBound": 0.2833482425162708, "recentWilsonLowerBound": 0.2851339669748648,
"running": 8, "running": 8,
"selectionWeight": 0.8583024226885341, "selectionWeight": 0.8666948962403804,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.833333333333332, "throughputPerHour": 24.166666666666668,
"waiting": 28616 "waiting": 28610
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 206.74285714285716, "backlogHours": 211.22627737226279,
"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": 0.3171560782273986, "qualityFactor": 0.28270338312158144,
"queueFactor": 1.1834856767466995, "queueFactor": 1.1796354599600463,
"queueWeight": 1.1834856767466995, "queueWeight": 1.1796354599600463,
"recentSuccess": 33, "recentSuccess": 31,
"recentSuccessRate": 0.2357142857142857, "recentSuccessRate": 0.22627737226277372,
"recentTerminal": 140, "recentTerminal": 137,
"recentWilsonLowerBound": 0.17305032975689183, "recentWilsonLowerBound": 0.1642371904152058,
"running": 8, "running": 8,
"selectionWeight": 0.375349675875282, "selectionWeight": 0.3334869353808879,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.333333333333332, "throughputPerHour": 22.833333333333332,
"waiting": 4824 "waiting": 4823
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1420.2461538461537, "backlogHours": 1442.0625,
"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": 0.30570006009394524, "qualityFactor": 0.26744873871975483,
"queueFactor": 0.886386310265614, "queueFactor": 0.8843260089798054,
"queueWeight": 0.886386310265614, "queueWeight": 0.8843260089798054,
"recentSuccess": 17, "recentSuccess": 16,
"recentSuccessRate": 0.26153846153846155, "recentSuccessRate": 0.25,
"recentTerminal": 65, "recentTerminal": 64,
"recentWilsonLowerBound": 0.17018055060319134, "recentWilsonLowerBound": 0.16014791974174092,
"running": 7, "running": 7,
"selectionWeight": 0.27096834831464855, "selectionWeight": 0.23651187571872354,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.833333333333334, "throughputPerHour": 10.666666666666666,
"waiting": 15386 "waiting": 15382
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 544.92, "backlogHours": 544.56,
"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": 0.26118326794349606, "qualityFactor": 0.26118326794349606,
"queueFactor": 1.0233581935064588, "queueFactor": 1.0234182333346336,
"queueWeight": 1.0233581935064588, "queueWeight": 1.0234182333346336,
"recentSuccess": 23, "recentSuccess": 23,
"recentSuccessRate": 0.23, "recentSuccessRate": 0.23,
"recentTerminal": 100, "recentTerminal": 100,
"recentWilsonLowerBound": 0.15843154746876406, "recentWilsonLowerBound": 0.15843154746876406,
"running": 7, "running": 7,
"selectionWeight": 0.2672840372567695, "selectionWeight": 0.26729971865529895,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 16.666666666666668, "throughputPerHour": 16.666666666666668,
"waiting": 9082 "waiting": 9076
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 53.02173913043478, "backlogHours": 52.38709677419355,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -498,19 +498,19 @@
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 12, "recentSuccess": 12,
"recentSuccessRate": 0.043478260869565216, "recentSuccessRate": 0.043010752688172046,
"recentTerminal": 276, "recentTerminal": 279,
"recentWilsonLowerBound": 0.02504337022584559, "recentWilsonLowerBound": 0.024772233291548575,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 46.0, "throughputPerHour": 46.5,
"waiting": 2439 "waiting": 2436
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 100.68243243243242, "backlogHours": 102.47422680412372,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-150", "gpu": "Iluvatar_bi-150",
@@ -519,104 +519,104 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 30, "recentSuccess": 29,
"recentSuccessRate": 0.10135135135135136, "recentSuccessRate": 0.09965635738831616,
"recentTerminal": 296, "recentTerminal": 291,
"recentWilsonLowerBound": 0.07191899900443502, "recentWilsonLowerBound": 0.07028546464040038,
"running": 8, "running": 5,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 49.333333333333336, "throughputPerHour": 48.5,
"waiting": 4967 "waiting": 4970
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 3702.0000000000005, "backlogHours": 4184.347826086956,
"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": 1.2314663769527514, "qualityFactor": 1.6689592169541345,
"queueFactor": 0.767736380919533, "queueFactor": 0.7537300739505735,
"queueWeight": 0.767736380919533, "queueWeight": 0.7537300739505735,
"recentSuccess": 13, "recentSuccess": 13,
"recentSuccessRate": 0.5, "recentSuccessRate": 0.5652173913043478,
"recentTerminal": 26, "recentTerminal": 23,
"recentWilsonLowerBound": 0.3206030631500208, "recentWilsonLowerBound": 0.36811049305016963,
"running": 2, "running": 2,
"selectionWeight": 0.9454415394657948, "selectionWeight": 1.257944754015331,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 4.333333333333333, "throughputPerHour": 3.8333333333333335,
"waiting": 16042 "waiting": 16040
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 568.373831775701, "backlogHours": 553.0363636363637,
"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": 0.496961390016157, "qualityFactor": 0.5502380275326447,
"queueFactor": 1.0169098923184685, "queueFactor": 1.021049877466962,
"queueWeight": 1.0169098923184685, "queueWeight": 1.021049877466962,
"recentSuccess": 31, "recentSuccess": 33,
"recentSuccessRate": 0.2897196261682243, "recentSuccessRate": 0.3,
"recentTerminal": 107, "recentTerminal": 110,
"recentWilsonLowerBound": 0.21224200748413424, "recentWilsonLowerBound": 0.22229769508028016,
"running": 8, "running": 8,
"selectionWeight": 0.5053649536077667, "selectionWeight": 0.5618204705898698,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.833333333333332, "throughputPerHour": 18.333333333333332,
"waiting": 10136 "waiting": 10139
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 635.6, "backlogHours": 635.4285714285714,
"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": 0.47572336165355805, "qualityFactor": 0.5645126985819736,
"queueFactor": 1.0, "queueFactor": 1.0,
"queueWeight": 1.0, "queueWeight": 1.0,
"recentSuccess": 30, "recentSuccess": 32,
"recentSuccessRate": 0.2857142857142857, "recentSuccessRate": 0.3047619047619048,
"recentTerminal": 105, "recentTerminal": 105,
"recentWilsonLowerBound": 0.20806999151103064, "recentWilsonLowerBound": 0.22490075875702692,
"running": 4, "running": 4,
"selectionWeight": 0.47572336165355805, "selectionWeight": 0.5645126985819736,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.5, "throughputPerHour": 17.5,
"waiting": 11123 "waiting": 11120
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2499.72, "backlogHours": 2499.6,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Mthreads_s4000", "gpu": "Mthreads_s4000",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 4, "maxConcurrentTasks": 4,
"qualityFactor": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.8143177071630086, "queueFactor": 0.8142906224384582,
"queueWeight": 0.8143177071630086, "queueWeight": 0.8142906224384582,
"recentSuccess": 29, "recentSuccess": 29,
"recentSuccessRate": 0.58, "recentSuccessRate": 0.58,
"recentTerminal": 50, "recentTerminal": 50,
"recentWilsonLowerBound": 0.4423319668777783, "recentWilsonLowerBound": 0.4423319668777783,
"running": 4, "running": 4,
"selectionWeight": 2.035794267907521, "selectionWeight": 2.0357265560961455,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.333333333333334, "throughputPerHour": 8.333333333333334,
"waiting": 20831 "waiting": 20830
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
@@ -627,14 +627,14 @@
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.8667295268164948, "qualityFactor": 0.8667295268164948,
"queueFactor": 0.731681191925064, "queueFactor": 0.7316515871166086,
"queueWeight": 0.731681191925064, "queueWeight": 0.7316515871166086,
"recentSuccess": 9, "recentSuccess": 9,
"recentSuccessRate": 0.47368421052631576, "recentSuccessRate": 0.47368421052631576,
"recentTerminal": 19, "recentTerminal": 19,
"recentWilsonLowerBound": 0.2732950548744854, "recentWilsonLowerBound": 0.2732950548744854,
"running": 2, "running": 2,
"selectionWeight": 0.6341696932577396, "selectionWeight": 0.6341440338961156,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 3.1666666666666665, "throughputPerHour": 3.1666666666666665,
@@ -642,52 +642,52 @@
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
"backlogHours": 603.986013986014, "backlogHours": 591.5342465753425,
"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": 0.8432142496213593, "qualityFactor": 0.8039000579371001,
"queueFactor": 1.0076821160966638, "queueFactor": 1.0107948647055496,
"queueWeight": 1.0076821160966638, "queueWeight": 1.0107948647055496,
"recentSuccess": 49, "recentSuccess": 49,
"recentSuccessRate": 0.34265734265734266, "recentSuccessRate": 0.3356164383561644,
"recentTerminal": 143, "recentTerminal": 146,
"recentWilsonLowerBound": 0.2698994070063999, "recentWilsonLowerBound": 0.2641049442736961,
"running": 16, "running": 16,
"selectionWeight": 0.8496919193813118, "selectionWeight": 0.8125780502993145,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 23.833333333333332, "throughputPerHour": 24.333333333333332,
"waiting": 14395 "waiting": 14394
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 754.781954887218, "backlogHours": 749.1492537313434,
"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": 0.2536017524512272, "qualityFactor": 0.22722168855526817,
"queueFactor": 0.9745505187309582, "queueFactor": 0.9756066638794528,
"queueWeight": 0.9745505187309582, "queueWeight": 0.9756066638794528,
"recentSuccess": 29, "recentSuccess": 28,
"recentSuccessRate": 0.21804511278195488, "recentSuccessRate": 0.208955223880597,
"recentTerminal": 133, "recentTerminal": 134,
"recentWilsonLowerBound": 0.15632434518405217, "recentWilsonLowerBound": 0.14871120011463207,
"running": 6, "running": 6,
"selectionWeight": 0.2471477194024235, "selectionWeight": 0.22167899353246123,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": false,
"throughputPerHour": 22.166666666666668, "throughputPerHour": 22.333333333333332,
"waiting": 16731 "waiting": 16731
} }
}, },
"queueAttemptedAt": "2026-09-24T13:27:02.197783+00:00", "queueAttemptedAt": "2026-09-24T13:37:15.488969+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-24T13:27:02.197783+00:00", "queueUpdatedAt": "2026-09-24T13:37:15.488969+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Cambricon_mlu-370-x4", "Cambricon_mlu-370-x4",

6
.modelhub_state/official_capabilities.json
View File

@@ -1,5 +1,5 @@
{ {
"catalogUpdatedAt": "2026-09-24T13:35:44.475445+00:00", "catalogUpdatedAt": "2026-09-24T13:37:15.488969+00:00",
"configuredTaskTypes": [ "configuredTaskTypes": [
"text-generation" "text-generation"
], ],
@@ -56,7 +56,7 @@
"time-series-forecasting" "time-series-forecasting"
], ],
"errors": [], "errors": [],
"generatedAt": "2026-09-24T13:35:44.475445+00:00", "generatedAt": "2026-09-24T13:37:15.488969+00:00",
"gpuCatalog": { "gpuCatalog": {
"Ascend_910-b3": { "Ascend_910-b3": {
"canVerify": true, "canVerify": true,
@@ -6206,6 +6206,6 @@
"updateTime": "2025-12-22 08:59:53" "updateTime": "2025-12-22 08:59:53"
} }
], ],
"taskTreeUpdatedAt": "2026-09-24T13:35:44.475445+00:00", "taskTreeUpdatedAt": "2026-09-24T13:37:15.488969+00:00",
"version": 1 "version": 1
} }

103
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-24T13:31:51.521367+00:00", "generatedAt": "2026-09-24T13:36:52.571887+00:00",
"lastSyncTime": "2026-09-24T13:31:51.262642+00:00", "lastSyncTime": "2026-09-24T13:36:52.257909+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -3787,23 +3787,23 @@
"decisionSuccessRate": 0.3636, "decisionSuccessRate": 0.3636,
"decisionTotal": 22, "decisionTotal": 22,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 27, "ambiguous_runtime": 28,
"framework_architecture_unsupported": 11, "framework_architecture_unsupported": 11,
"model_load": 3, "model_load": 3,
"验证失败": 3 "验证失败": 3
}, },
"failureCount": 44, "failureCount": 45,
"failureRate": 0.8462, "failureRate": 0.8491,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 8, "successCount": 8,
"successRate": 0.1538, "successRate": 0.1509,
"targetGpu": "Cambricon_mlu-370-x4", "targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation", "taskType": "text-generation",
"total": 52, "total": 53,
"unresolvedFailureCount": 30 "unresolvedFailureCount": 31
}, },
"Cambricon_mlu-370-x4|vllm|text-generation": { "Cambricon_mlu-370-x4|vllm|text-generation": {
"attributableFailureCount": 18, "attributableFailureCount": 18,
@@ -5955,22 +5955,22 @@
"decisionSuccessRate": 0.4167, "decisionSuccessRate": 0.4167,
"decisionTotal": 48, "decisionTotal": 48,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 73, "ambiguous_runtime": 74,
"framework_architecture_unsupported": 22, "framework_architecture_unsupported": 22,
"model_load": 5, "model_load": 5,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 3, "参数/模板问题": 3,
"验证失败": 3 "验证失败": 3
}, },
"failureCount": 107, "failureCount": 108,
"failureRate": 0.8425, "failureRate": 0.8438,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 20, "successCount": 20,
"successRate": 0.1575, "successRate": 0.1562,
"total": 127, "total": 128,
"unresolvedFailureCount": 79 "unresolvedFailureCount": 80
}, },
"vllm-patch-tokenizer": { "vllm-patch-tokenizer": {
"attributableFailureCount": 55, "attributableFailureCount": 55,
@@ -6073,7 +6073,7 @@
"unresolvedFailureCount": 195 "unresolvedFailureCount": 195
} }
}, },
"generatedAt": "2026-09-24T13:31:51.508599+00:00", "generatedAt": "2026-09-24T13:36:52.509287+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 102, "attributableFailureCount": 102,
@@ -6165,7 +6165,7 @@
"decisionSuccessRate": 0.09, "decisionSuccessRate": 0.09,
"decisionTotal": 811, "decisionTotal": 811,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 458, "ambiguous_runtime": 459,
"architecture_compatibility": 53, "architecture_compatibility": 53,
"context_length": 48, "context_length": 48,
"framework_architecture_unsupported": 291, "framework_architecture_unsupported": 291,
@@ -6178,15 +6178,15 @@
"日志缺失": 13, "日志缺失": 13,
"验证失败": 42 "验证失败": 42
}, },
"failureCount": 1552, "failureCount": 1553,
"failureRate": 0.9551, "failureRate": 0.9551,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 15, "platformFailureCount": 15,
"successCount": 73, "successCount": 73,
"successRate": 0.0449, "successRate": 0.0449,
"total": 1625, "total": 1626,
"unresolvedFailureCount": 799 "unresolvedFailureCount": 800
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"attributableFailureCount": 60, "attributableFailureCount": 60,
@@ -10768,6 +10768,29 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen2|compressed-tensors": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none": { "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none": {
"attributableFailureCount": 2, "attributableFailureCount": 2,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -32859,6 +32882,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen2|compressed-tensors|33": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 33,
"modelType": "qwen2",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "compressed-tensors",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x4",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none|32": { "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_5_text|none|32": {
"attributableFailureCount": 1, "attributableFailureCount": 1,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
@@ -50002,15 +50049,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 16988, "terminalRecords": 16989,
"totalRecords": 17208, "totalRecords": 17209,
"totals": { "totals": {
"attributableFailureCount": 6098, "attributableFailureCount": 6098,
"decisionFailureRate": 0.8635, "decisionFailureRate": 0.8635,
"decisionSuccessRate": 0.1365, "decisionSuccessRate": 0.1365,
"decisionTotal": 7062, "decisionTotal": 7062,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 4370, "ambiguous_runtime": 4371,
"architecture_compatibility": 212, "architecture_compatibility": 212,
"attention_backend": 3, "attention_backend": 3,
"backend_operator": 127, "backend_operator": 127,
@@ -50026,15 +50073,15 @@
"日志缺失": 719, "日志缺失": 719,
"验证失败": 676 "验证失败": 676
}, },
"failureCount": 16024, "failureCount": 16025,
"failureRate": 0.9433, "failureRate": 0.9433,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 934, "platformFailureCount": 934,
"successCount": 964, "successCount": 964,
"successRate": 0.0567, "successRate": 0.0567,
"total": 16988, "total": 16989,
"unresolvedFailureCount": 8992 "unresolvedFailureCount": 8993
}, },
"warnings": [ "warnings": [
"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。",
@@ -50045,11 +50092,11 @@
"GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU 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 Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 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 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 Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。",
"GPU hygon_k100-ai 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 Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。",
"组合 Iluvatar_bi-150|transformers|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|transformers|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 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。",
@@ -50092,6 +50139,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 17208, "summarizedRecords": 17209,
"version": 1 "version": 1
} }

1260
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1664
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

18
manifest.json
View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.22.1", "agentVersion": "2026.09.22.1",
"checksums": { "checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "5a0149cd25aafac73c5d9911492258ef6dfd447512f239cb185ca2a226cdf072", ".modelhub_state/architecture_compatibility_blacklist.json": "668b4f964a12125b0d0b4ceb35e50144dc43a757cfba0d4281b42f6c562b2e60",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "6628e6c468b157e31b490879aaa0af8d8a3297239fb089224da1264e97db9f9e", ".modelhub_state/market_intelligence.json": "8e250150e5884af9d83634d2d320aea86dc661c3ae5a1a6d807fb1c0aa7f1964",
".modelhub_state/official_capabilities.json": "b730b3ccc112c101e32645d1903868c9eab047cffb2b727320d635fdb1a4a82b", ".modelhub_state/official_capabilities.json": "904ab7b5a8080eed76976efda6cf7ca7dd00761b2e5630ab177d97cd681287c4",
".modelhub_state/outcome_checkpoint.json": "0dc282a027720629f1df2c9df8fb8c3c4db77173b86165b3ce163b9100c0551f", ".modelhub_state/outcome_checkpoint.json": "1a9fdc289eaeb3c1d3b54d1b97f390a780402d884df41d2916391fb75c11a71a",
".modelhub_state/queue_cleanup_latest.json": "e12e3dc9b5a620b18a5eb919e6b78ad98b404a8ec3048f55dfadc06b4e7a28ba", ".modelhub_state/queue_cleanup_latest.json": "e12e3dc9b5a620b18a5eb919e6b78ad98b404a8ec3048f55dfadc06b4e7a28ba",
".modelhub_state/recent_outcomes.jsonl": "dcd1b8324c516e746e323a5ab28151cf4e04ac06f17572f85985669e45a0c2fd", ".modelhub_state/recent_outcomes.jsonl": "dcd1b8324c516e746e323a5ab28151cf4e04ac06f17572f85985669e45a0c2fd",
".modelhub_state/recovery_active_tasks.jsonl": "161570949cca6ed3d025c9956dccb0bd9fedcc597911ea90585f6829b6fa02a0", ".modelhub_state/recovery_active_tasks.jsonl": "16d57ab8d888362c3c5b4cca3590651126c1c4c41194a39b13a1a3addf77d9b4",
".modelhub_state/recovery_intents.jsonl": "adaf603375017b5d25ce938d6159b18276784729663c33fd47126bd89a32f5af", ".modelhub_state/recovery_intents.jsonl": "3b8141e795e00669d8ebae76341eef2f3cb7f297e76ec06e436b361ad2fcbedf",
".modelhub_state/routing_intelligence.json": "d4090084256dc1779714504a751450489f70fd0bf535915e0a359f0296eb7dc9", ".modelhub_state/routing_intelligence.json": "d4090084256dc1779714504a751450489f70fd0bf535915e0a359f0296eb7dc9",
".modelhub_state/submission_exclusions.jsonl": "02c89260955c401737ae26ffb5b4cc542d98dc0cc7e31967a9c71b6b9597ba74", ".modelhub_state/submission_exclusions.jsonl": "02c89260955c401737ae26ffb5b4cc542d98dc0cc7e31967a9c71b6b9597ba74",
".modelhub_state/worker_crashes.jsonl": "091381072c6fcac41b6a5fb5ab44ba0c1464d03b7ad63c09eaa3defdb195e9d3", ".modelhub_state/worker_crashes.jsonl": "091381072c6fcac41b6a5fb5ab44ba0c1464d03b7ad63c09eaa3defdb195e9d3",
"ledger/submissions.jsonl": "88579b45a779d3b15e3a622ba47226f0ce25472451da2198d770e79be937aaab", "ledger/submissions.jsonl": "88579b45a779d3b15e3a622ba47226f0ce25472451da2198d770e79be937aaab",
"outcomes/submissions.jsonl": "83adf7424ef0553aa9893fc03e22bc4e43bed599b50e45c807127269c3561b9f" "outcomes/submissions.jsonl": "915474d52456a6550746e229a7a092a5e68315f91b761ae9273cf85eeaa94b67"
}, },
"generation": 14861, "generation": 14862,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-24T13:35:51.548911+00:00", "updatedAt": "2026-09-24T13:37:19.588119+00:00",
"writerId": "43e8b6eb13264ac59b8ccb41b795b9e4" "writerId": "43e8b6eb13264ac59b8ccb41b795b9e4"
} }

3
outcomes/submissions.jsonl
View File

@@ -356,7 +356,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599794+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663548868}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.658577+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969673", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599794+00:00", "modelId": "LiquidAI/LFM2.5-1.2B-Instruct-MLX-4bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 658540250, "estimatedRequiredGiB": 0.742, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 663548868, "modelscopeLicense": "other", "modelscopeParams": 182975232, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 663548868}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:25:32.658577+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969673", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599773+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.763321+00:00", "targetGpu": "MetaX_c-500", "taskId": "4969808", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T11:30:54.599773+00:00", "modelId": "aisingapore/Gemma-SEA-LION-v4-27B-IT", "modelProfile": {"architectures": ["Gemma3ForConditionalGeneration"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54864980000, "estimatedRequiredGiB": 61.361, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma3", "modelscopeFileSize": 54904930780, "modelscopeLicense": "gemma", "modelscopeParams": 27432406640, "modelscopeTags": ["license:gemma", "model_type:gemma3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 54904930780}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:30:23.763321+00:00", "targetGpu": "MetaX_c-500", "taskId": "4969808", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:01:00.671231+00:00", "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325202, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325202}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.351352+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969964", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:01:00.671231+00:00", "modelId": "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9084013360, "estimatedRequiredGiB": 10.163, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 9093325202, "modelscopeLicense": "llama3", "modelscopeParams": 8030261248, "modelscopeTags": ["license:llama3", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 9093325202}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.351352+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969964", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-20T12:01:00.670537+00:00", "modelId": "neuralmagic/Qwen2-7B-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["Qwen2ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8708787584, "estimatedRequiredGiB": 9.746, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen2", "modelscopeFileSize": 8720442075, "modelscopeLicense": "apache-2.0", "modelscopeParams": 7615616512, "modelscopeTags": ["license:apache-2.0", "model_type:qwen2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8720442075}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.293456+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969956", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670531+00:00", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236742}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.349301+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969958", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-20T12:01:00.670531+00:00", "modelId": "neuralmagic/SmolLM-135M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "26bfee231695e882b96dee0191bc1dfec25bcad132af96a7ee5f0e26f3cb9fdc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 219850592, "estimatedRequiredGiB": 0.249, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 223236742, "modelscopeLicense": "apache-2.0", "modelscopeParams": 162826560, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 223236742}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:37.349301+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4969958", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.670706+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:44.501444+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969969", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.670706+00:00", "modelId": "RedHatAI/starcoder2-15b-quantized.w8a16", "modelProfile": {"architectures": ["Starcoder2ForCausalLM"], "configFingerprint": "ef4c08c913d3f64cae22550f0c4a189795901d4b11e26d8e640e07e857659fb9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17785269848, "estimatedRequiredGiB": 19.88, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "starcoder2", "modelscopeFileSize": 17788663591, "modelscopeLicense": "bigcode-openrail-m", "modelscopeParams": 15957889024, "modelscopeTags": ["license:bigcode-openrail-m", "model_type:starcoder2", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:code"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 17788663591}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:44.501444+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969969", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671081+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443052, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443052}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:44.505215+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969967", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-20T12:01:00.671081+00:00", "modelId": "RedHatAI/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "f49713b9fe8e3e7683ab2722544c85a44993bcd72b9421c1599f634e68b3a2f7", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443052, "modelscopeLicense": "apache-2.0", "modelscopeParams": 409007040, "modelscopeTags": ["license:apache-2.0", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:int8", "custom_tag:vllm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 507443052}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-20T03:40:44.505215+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "4969967", "taskType": "text-generation", "verifyResult": null}
@@ -827,7 +826,7 @@
{"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": "2026-09-24T11:46:07.057446+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T03:45:51.286900+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5052223", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T11:46:07.057446+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T03:45:51.286900+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5052223", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T12:05:54.650656+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T04:02:05.852553+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5052428", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T12:05:54.650656+00:00", "modelId": "hcnote/SparkMuse-4B-INT4", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2938633112, "estimatedRequiredGiB": 3.296, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 2948792004, "modelscopeLicense": "apache-2.0", "modelscopeParams": 935831040, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:creative-writing", "custom_tag:novel-generation", "custom_tag:roleplay", "custom_tag:nsfw", "custom_tag:quantized", "custom_tag:torchao", "custom_tag:int4", "custom_tag:long-context", "custom_tag:spark"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "torchao", "repositoryOnDiskBytes": 2948792004}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T04:02:05.852553+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5052428", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-24T05:35:37.047196+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5054057", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T13:36:52.257884+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T05:35:37.047196+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5054057", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-24T05:50:51.434730+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054354", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "togethercomputer/Tev1-4B-experimental", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 9319828096, "estimatedRequiredGiB": 10.441, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:together-ai", "custom_tag:qwen3.5", "custom_tag:decision-model", "custom_tag:experimental"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 9342812725}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-24T05:50:51.434730+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054354", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "b3ef6bcf57e6bb4fc9ede989e67a765b0e40b19fbd407f1f8452833c12bd5c38", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-24T05:51:00.445370+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054361", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": null, "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "b3ef6bcf57e6bb4fc9ede989e67a765b0e40b19fbd407f1f8452833c12bd5c38", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "pending", "status": "pending", "submitTime": "2026-09-24T05:51:00.445370+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054361", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "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": "pending", "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": null, "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": "pending", "submitTime": "2026-09-24T06:05:15.403300+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5054597", "taskType": "text-generation", "verifyResult": null}