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

state: generation 7493 (cycle)

Browse Source
This commit is contained in:
CoolBoy
2026-09-15 02:53:05 +00:00
parent aa16510d6e
commit efb577cb05
10 changed files with 2243 additions and 2200 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.modelhub_state/architecture_compatibility_blacklist.json
View File

@@ -1558,7 +1558,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-15T02:49:57.982227+00:00", "generatedAt": "2026-09-15T02:53:04.585123+00:00",
"summary": { "summary": {
"activeBlockCount": 77, "activeBlockCount": 77,
"byGpuFramework": { "byGpuFramework": {

6
.modelhub_state/architecture_history_backfill.json
View File

@@ -27,7 +27,7 @@
"11": { "11": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 543, "listingErrors": 544,
"nextPage": 1, "nextPage": 1,
"recordsScanned": 0, "recordsScanned": 0,
"uniqueRecords": 0 "uniqueRecords": 0
@@ -102,12 +102,12 @@
"cutoffAt": "2026-09-04T03:55:51.365685+00:00", "cutoffAt": "2026-09-04T03:55:51.365685+00:00",
"failureLogsInspected": 0, "failureLogsInspected": 0,
"mode": "incremental_decision_only", "mode": "incremental_decision_only",
"nextAccountIndex": 11, "nextAccountIndex": 0,
"recordsScanned": 0, "recordsScanned": 0,
"seenTaskIds": [], "seenTaskIds": [],
"startedAt": "2026-09-04T03:55:51.365685+00:00", "startedAt": "2026-09-04T03:55:51.365685+00:00",
"terminalRecords": 0, "terminalRecords": 0,
"uniqueRecords": 0, "uniqueRecords": 0,
"updatedAt": "2026-09-15T02:49:57.955502+00:00", "updatedAt": "2026-09-15T02:53:04.516540+00:00",
"version": 1 "version": 1
} }

276
.modelhub_state/market_intelligence.json
View File

@@ -416,99 +416,99 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-15T02:48:02.992677+00:00", "generatedAt": "2026-09-15T02:51:09.235899+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 987.0833333333334, "backlogHours": 987.125,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b3", "gpu": "Ascend_910-b3",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 1.2155908398588848, "qualityFactor": 1.1673751242232802,
"queueFactor": 0.9946711564949742, "queueFactor": 0.9965562962719667,
"queueWeight": 0.9946711564949742, "queueWeight": 0.9965562962719667,
"recentSuccess": 49, "recentSuccess": 50,
"recentSuccessRate": 0.3402777777777778, "recentSuccessRate": 0.3472222222222222,
"recentTerminal": 144, "recentTerminal": 144,
"recentWilsonLowerBound": 0.267939727271058, "recentWilsonLowerBound": 0.2743455215337146,
"running": 8, "running": 9,
"selectionWeight": 1.2091131465071339, "selectionWeight": 1.1633550301559792,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.0, "throughputPerHour": 24.0,
"waiting": 23690 "waiting": 23691
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1400.65, "backlogHours": 1400.6,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b4", "gpu": "Ascend_910-b4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 2.5, "qualityFactor": 2.5,
"queueFactor": 0.9438069116998786, "queueFactor": 0.9456067022433745,
"queueWeight": 0.9438069116998786, "queueWeight": 0.9456067022433745,
"recentSuccess": 55, "recentSuccess": 57,
"recentSuccessRate": 0.4583333333333333, "recentSuccessRate": 0.475,
"recentTerminal": 120, "recentTerminal": 120,
"recentWilsonLowerBound": 0.371859770816446, "recentWilsonLowerBound": 0.3878193727928457,
"running": 10, "running": 8,
"selectionWeight": 2.3595172792496966, "selectionWeight": 2.364016755608436,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 20.0, "throughputPerHour": 20.0,
"waiting": 28013 "waiting": 28012
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 780.0, "backlogHours": 799.6923076923077,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Biren_166m", "gpu": "Biren_166m",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.06465823557768155, "qualityFactor": 0.062424140439282155,
"queueFactor": 1.030429792659889, "queueFactor": 1.0285353490136604,
"queueWeight": 1.030429792659889, "queueWeight": 1.0285353490136604,
"recentSuccess": 6, "recentSuccess": 6,
"recentSuccessRate": 0.15, "recentSuccessRate": 0.15384615384615385,
"recentTerminal": 40, "recentTerminal": 39,
"recentWilsonLowerBound": 0.07061091708507436, "recentWilsonLowerBound": 0.07247373845051468,
"running": 2, "running": 3,
"selectionWeight": 0.06662577228006467, "selectionWeight": 0.06420543507359483,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.666666666666667, "throughputPerHour": 6.5,
"waiting": 5200 "waiting": 5198
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1229.04, "backlogHours": 1280.0833333333333,
"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": 0.7403259465888222, "qualityFactor": 0.7418496536639053,
"queueFactor": 0.9624932548556293, "queueFactor": 0.9584554330873829,
"queueWeight": 0.9624932548556293, "queueWeight": 0.9584554330873829,
"recentSuccess": 23, "recentSuccess": 23,
"recentSuccessRate": 0.30666666666666664, "recentSuccessRate": 0.3194444444444444,
"recentTerminal": 75, "recentTerminal": 72,
"recentWilsonLowerBound": 0.21386719822895708, "recentWilsonLowerBound": 0.2232545704855647,
"running": 7, "running": 7,
"selectionWeight": 0.7125587299863503, "selectionWeight": 0.7110298310881634,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.5, "throughputPerHour": 12.0,
"waiting": 15363 "waiting": 15361
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 148.36507936507937, "backlogHours": 146.03125,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Cambricon_mlu-370-x8", "gpu": "Cambricon_mlu-370-x8",
@@ -517,20 +517,20 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 23, "recentSuccess": 24,
"recentSuccessRate": 0.06084656084656084, "recentSuccessRate": 0.0625,
"recentTerminal": 378, "recentTerminal": 384,
"recentWilsonLowerBound": 0.0408837698852248, "recentWilsonLowerBound": 0.04235583891458391,
"running": 7, "running": 7,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 63.0, "throughputPerHour": 64.0,
"waiting": 9347 "waiting": 9346
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 50.154798761609904, "backlogHours": 52.76872964169382,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -539,126 +539,126 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 11, "recentSuccess": 10,
"recentSuccessRate": 0.034055727554179564, "recentSuccessRate": 0.03257328990228013,
"recentTerminal": 323, "recentTerminal": 307,
"recentWilsonLowerBound": 0.019120489612725677, "recentWilsonLowerBound": 0.017787438641174505,
"running": 24, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 53.833333333333336, "throughputPerHour": 51.166666666666664,
"waiting": 2700 "waiting": 2700
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 170.36129032258066, "backlogHours": 172.4313725490196,
"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": 0.3130821521600364, "qualityFactor": 0.2696756395856187,
"queueFactor": 1.2945742345953062, "queueFactor": 1.2946882818705234,
"queueWeight": 1.2945742345953062, "queueWeight": 1.2946882818705234,
"recentSuccess": 31, "recentSuccess": 30,
"recentSuccessRate": 0.2, "recentSuccessRate": 0.19607843137254902,
"recentTerminal": 155, "recentTerminal": 153,
"recentWilsonLowerBound": 0.1446275910955794, "recentWilsonLowerBound": 0.14094165512787288,
"running": 4, "running": 8,
"selectionWeight": 0.40530808749803027, "selectionWeight": 0.34914589047743916,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.833333333333332, "throughputPerHour": 25.5,
"waiting": 4401 "waiting": 4397
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2456.4615384615386, "backlogHours": 2520.947368421053,
"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": 0.6841198246175211, "qualityFactor": 0.6628947516310328,
"queueFactor": 0.8675331960273489, "queueFactor": 0.8658109881684902,
"queueWeight": 0.8675331960273489, "queueWeight": 0.8658109881684902,
"recentSuccess": 13, "recentSuccess": 13,
"recentSuccessRate": 0.3333333333333333, "recentSuccessRate": 0.34210526315789475,
"recentTerminal": 39, "recentTerminal": 38,
"recentWilsonLowerBound": 0.2063276610691516, "recentWilsonLowerBound": 0.21212220026458956,
"running": 2, "running": 2,
"selectionWeight": 0.5934966579161075, "selectionWeight": 0.5739415599613704,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 6.5, "throughputPerHour": 6.333333333333333,
"waiting": 15967 "waiting": 15966
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 734.5531914893618, "backlogHours": 758.6373626373627,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Kunlunxin_p-800", "gpu": "Kunlunxin_p-800",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 7, "maxConcurrentTasks": 7,
"qualityFactor": 0.3906768400619053, "qualityFactor": 0.3380132998161403,
"queueFactor": 1.03975043274518, "queueFactor": 1.0366986329891255,
"queueWeight": 1.03975043274518, "queueWeight": 1.0366986329891255,
"recentSuccess": 22, "recentSuccess": 21,
"recentSuccessRate": 0.23404255319148937, "recentSuccessRate": 0.23076923076923078,
"recentTerminal": 94, "recentTerminal": 91,
"recentWilsonLowerBound": 0.1599410529376495, "recentWilsonLowerBound": 0.15618045094358188,
"running": 7, "running": 7,
"selectionWeight": 0.4062064135178855, "selectionWeight": 0.3504179258515361,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 15.666666666666666, "throughputPerHour": 15.166666666666666,
"waiting": 11508 "waiting": 11506
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 918.0, "backlogHours": 942.24,
"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": 1.0759730358873818, "qualityFactor": 0.8466941872344714,
"queueFactor": 1.0055558457767442, "queueFactor": 1.0035370926695926,
"queueWeight": 1.0055558457767442, "queueWeight": 1.0035370926695926,
"recentSuccess": 27, "recentSuccess": 25,
"recentSuccessRate": 0.35064935064935066, "recentSuccessRate": 0.3333333333333333,
"recentTerminal": 77, "recentTerminal": 75,
"recentWilsonLowerBound": 0.253485167224312, "recentWilsonLowerBound": 0.23708065705320358,
"running": 4, "running": 5,
"selectionWeight": 1.0819509761347073, "selectionWeight": 0.8496890230375251,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.833333333333334, "throughputPerHour": 12.5,
"waiting": 11781 "waiting": 11778
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 2371.423728813559, "backlogHours": 2498.035714285714,
"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": 1.8151155950993079, "qualityFactor": 1.6817305946133239,
"queueFactor": 0.872129994522462, "queueFactor": 0.8669975366743552,
"queueWeight": 0.872129994522462, "queueWeight": 0.8669975366743552,
"recentSuccess": 26, "recentSuccess": 25,
"recentSuccessRate": 0.4406779661016949, "recentSuccessRate": 0.44642857142857145,
"recentTerminal": 59, "recentTerminal": 56,
"recentWilsonLowerBound": 0.3215001223396273, "recentWilsonLowerBound": 0.3238651625129941,
"running": 5, "running": 5,
"selectionWeight": 1.5830167540115947, "selectionWeight": 1.4580562828796504,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 9.833333333333334, "throughputPerHour": 9.333333333333334,
"waiting": 23319 "waiting": 23315
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
@@ -668,15 +668,15 @@
"gpu": "Sunrise_pt-200-x1", "gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.3519966032389718, "qualityFactor": 0.21357049899308206,
"queueFactor": 0.8317254211772703, "queueFactor": 0.8333070160008342,
"queueWeight": 0.8317254211772703, "queueWeight": 0.8333070160008342,
"recentSuccess": 8, "recentSuccess": 7,
"recentSuccessRate": 0.2857142857142857, "recentSuccessRate": 0.25,
"recentTerminal": 28, "recentTerminal": 28,
"recentWilsonLowerBound": 0.15253815848329966, "recentWilsonLowerBound": 0.12676334942200781,
"running": 2, "running": 2,
"selectionWeight": 0.2927645230819023, "selectionWeight": 0.1779697952217344,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 4.666666666666667, "throughputPerHour": 4.666666666666667,
@@ -690,15 +690,15 @@
"gpu": "Vastai_va16", "gpu": "Vastai_va16",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 16, "maxConcurrentTasks": 16,
"qualityFactor": 0.14023381443941396, "qualityFactor": 0.09704774548195431,
"queueFactor": 0.9627051012687367, "queueFactor": 0.9645357648098726,
"queueWeight": 0.9627051012687367, "queueWeight": 0.9645357648098726,
"recentSuccess": 11, "recentSuccess": 10,
"recentSuccessRate": 0.1746031746031746, "recentSuccessRate": 0.15873015873015872,
"recentTerminal": 63, "recentTerminal": 63,
"recentWilsonLowerBound": 0.10039293923176863, "recentWilsonLowerBound": 0.08856997432352591,
"running": 17, "running": 16,
"selectionWeight": 0.13500380853119726, "selectionWeight": 0.09360602141151066,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.5, "throughputPerHour": 10.5,
@@ -706,30 +706,30 @@
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 718.766355140187, "backlogHours": 699.0545454545455,
"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": 0.8589664967196196, "qualityFactor": 0.7348725422964986,
"queueFactor": 1.043144412870296, "queueFactor": 1.0494965141529355,
"queueWeight": 1.043144412870296, "queueWeight": 1.0494965141529355,
"recentSuccess": 33, "recentSuccess": 33,
"recentSuccessRate": 0.308411214953271, "recentSuccessRate": 0.3,
"recentTerminal": 107, "recentTerminal": 110,
"recentWilsonLowerBound": 0.2288160943036506, "recentWilsonLowerBound": 0.22229769508028016,
"running": 8, "running": 7,
"selectionWeight": 0.8960261018958426, "selectionWeight": 0.7712461714868809,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 17.833333333333332, "throughputPerHour": 18.333333333333332,
"waiting": 12818 "waiting": 12816
} }
}, },
"queueAttemptedAt": "2026-09-15T02:40:52.662910+00:00", "queueAttemptedAt": "2026-09-15T02:51:09.235899+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-15T02:40:52.662910+00:00", "queueUpdatedAt": "2026-09-15T02:51:09.235899+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Iluvatar_mrv-100", "Iluvatar_mrv-100",

1506
.modelhub_state/official_capabilities.json
View File

File diff suppressed because it is too large Load Diff

95
.modelhub_state/outcome_checkpoint.json
View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-15T01:43:45.065697+00:00", "generatedAt": "2026-09-15T02:50:59.210186+00:00",
"lastSyncTime": "2026-09-15T01:43:44.814965+00:00", "lastSyncTime": "2026-09-15T02:50:58.954226+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1846,12 +1846,12 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 8, "decisionTotal": 8,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 22, "ambiguous_runtime": 23,
"framework_architecture_unsupported": 7, "framework_architecture_unsupported": 7,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 3 "参数/模板问题": 3
}, },
"failureCount": 33, "failureCount": 34,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm-mlu", "framework": "vllm-mlu",
"pendingCount": 0, "pendingCount": 0,
@@ -1861,8 +1861,8 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8", "targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation", "taskType": "text-generation",
"total": 33, "total": 34,
"unresolvedFailureCount": 25 "unresolvedFailureCount": 26
}, },
"Cambricon_mlu-370-x8|vllm|text-generation": { "Cambricon_mlu-370-x8|vllm|text-generation": {
"attributableFailureCount": 3, "attributableFailureCount": 3,
@@ -2633,20 +2633,20 @@
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 8, "decisionTotal": 8,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 22, "ambiguous_runtime": 23,
"framework_architecture_unsupported": 7, "framework_architecture_unsupported": 7,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"参数/模板问题": 3 "参数/模板问题": 3
}, },
"failureCount": 33, "failureCount": 34,
"failureRate": 1.0, "failureRate": 1.0,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 0, "successCount": 0,
"successRate": 0.0, "successRate": 0.0,
"total": 33, "total": 34,
"unresolvedFailureCount": 25 "unresolvedFailureCount": 26
}, },
"vllm-patch-tokenizer": { "vllm-patch-tokenizer": {
"attributableFailureCount": 5, "attributableFailureCount": 5,
@@ -2733,7 +2733,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-15T01:43:45.057311+00:00", "generatedAt": "2026-09-15T02:50:59.204743+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 39, "attributableFailureCount": 39,
@@ -2837,22 +2837,22 @@
"decisionSuccessRate": 0.0952, "decisionSuccessRate": 0.0952,
"decisionTotal": 21, "decisionTotal": 21,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 42, "ambiguous_runtime": 43,
"framework_architecture_unsupported": 16, "framework_architecture_unsupported": 16,
"memory_capacity": 1, "memory_capacity": 1,
"tokenizer_compatibility": 2, "tokenizer_compatibility": 2,
"参数/模板问题": 18, "参数/模板问题": 18,
"验证失败": 22 "验证失败": 22
}, },
"failureCount": 101, "failureCount": 102,
"failureRate": 0.9806, "failureRate": 0.9808,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 2, "successCount": 2,
"successRate": 0.0194, "successRate": 0.0192,
"total": 103, "total": 104,
"unresolvedFailureCount": 82 "unresolvedFailureCount": 83
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
@@ -3247,6 +3247,29 @@
"total": 5, "total": 5,
"unresolvedFailureCount": 5 "unresolvedFailureCount": 5
}, },
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|compressed-tensors": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -6114,6 +6137,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
}, },
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|awq|32": {
"attributableFailureCount": 0,
"decisionFailureRate": 0.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm-mlu",
"loadSizeLog2Bucket": 32,
"modelType": "llama",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "awq",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Cambricon_mlu-370-x8",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 1
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|compressed-tensors|30": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation|llama|compressed-tensors|30": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -9129,15 +9176,15 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1890, "terminalRecords": 1891,
"totalRecords": 1983, "totalRecords": 1984,
"totals": { "totals": {
"attributableFailureCount": 575, "attributableFailureCount": 575,
"decisionFailureRate": 0.8984, "decisionFailureRate": 0.8984,
"decisionSuccessRate": 0.1016, "decisionSuccessRate": 0.1016,
"decisionTotal": 640, "decisionTotal": 640,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 455, "ambiguous_runtime": 456,
"backend_operator": 44, "backend_operator": 44,
"framework_architecture_unsupported": 369, "framework_architecture_unsupported": 369,
"memory_capacity": 12, "memory_capacity": 12,
@@ -9149,15 +9196,15 @@
"参数/模板问题": 116, "参数/模板问题": 116,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1825, "failureCount": 1826,
"failureRate": 0.9656, "failureRate": 0.9656,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 6, "platformFailureCount": 6,
"successCount": 65, "successCount": 65,
"successRate": 0.0344, "successRate": 0.0344,
"total": 1890, "total": 1891,
"unresolvedFailureCount": 1244 "unresolvedFailureCount": 1245
}, },
"warnings": [ "warnings": [
"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。",
@@ -9195,6 +9242,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1983, "summarizedRecords": 1984,
"version": 1 "version": 1
} }

1246
.modelhub_state/recovery_active_tasks.jsonl
View File

File diff suppressed because it is too large Load Diff

1288
.modelhub_state/recovery_intents.jsonl
View File

File diff suppressed because it is too large Load Diff

1
ledger/submissions.jsonl
View File

@@ -74,7 +74,6 @@
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-2B-Distill-GGUF", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "submitTime": "2026-09-05T04:38:07.789820+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641229", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"} {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-2B-Distill-GGUF", "modelId": "empero-ai/Qwen3.8-2B-Distill-GGUF", "submitTime": "2026-09-05T04:38:07.789820+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641229", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill-GGUF", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "submitTime": "2026-09-05T04:56:19.745119+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"} {"framework": "llamacpp", "modelAddress": "https://modelscope.cn/models/empero-ai/Qwen3.8-4B-Distill-GGUF", "modelId": "empero-ai/Qwen3.8-4B-Distill-GGUF", "submitTime": "2026-09-05T04:56:19.745119+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4641463", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-llamacpp-iluvatar-bi-150"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-05T05:03:01.097550+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641563", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "submitTime": "2026-09-05T05:03:01.097550+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641563", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "submitTime": "2026-09-05T05:03:09.008584+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641565", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "submitTime": "2026-09-05T05:03:09.000926+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641564", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "modelId": "FlagRelease/DeepSeek-R1-Distill-Qwen-1.5B-mthreads-FlagOS", "submitTime": "2026-09-05T05:03:09.000926+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4641564", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-mthreads-s4000"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LLM-Research/Phi-3.5-mini-instruct-bnb-4bit", "modelId": "LLM-Research/Phi-3.5-mini-instruct-bnb-4bit", "submitTime": "2026-09-05T05:03:09.034612+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4641566", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/LLM-Research/Phi-3.5-mini-instruct-bnb-4bit", "modelId": "LLM-Research/Phi-3.5-mini-instruct-bnb-4bit", "submitTime": "2026-09-05T05:03:09.034612+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4641566", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-sunrise-pt-200-x1"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "submitTime": "2026-09-05T05:17:16.436989+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641789", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/ornith-ai/Ornith-1.5-9B-MLX-8bit", "modelId": "ornith-ai/Ornith-1.5-9B-MLX-8bit", "submitTime": "2026-09-05T05:17:16.436989+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4641789", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-iluvatar-mrv-100"}

22
manifest.json
View File

@@ -1,24 +1,24 @@
{ {
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "1711a5850494ce5c9a42c3f14231b1d7c840cead6113d251d3cec3bf3c6f035e", ".modelhub_state/architecture_compatibility_blacklist.json": "c99ea6187f43e076e5fca8a7ccd7637c9214f2c78c5f843accd8f4dc86dd7bb4",
".modelhub_state/architecture_history_backfill.json": "b8367312b654d6895cf0da21940725e77597ec97b9ce4b02c89b4b71afee2917", ".modelhub_state/architecture_history_backfill.json": "1c6bb1f398c0b8423a13913a0a1ac36a003ddef67e15d7555f3f0dfb22c8c4dc",
".modelhub_state/market_intelligence.json": "65465b04777b6e57dee5fc8197794b92950db540cd73ad6ba646ffb9a7376939", ".modelhub_state/market_intelligence.json": "0b1cad39f430f71ddcb66bc64d8511fd39de856d07a044c258c0ae6b09cf4d40",
".modelhub_state/official_capabilities.json": "801ff0d91c0b4dc9a7192bde4bfc8e496e580f2813df012112852a7d3f1a6f73", ".modelhub_state/official_capabilities.json": "fd719c5c7fec4e6dd1466bc0b416110a6b47cc3de50df88ce9b966ee6d5617d7",
".modelhub_state/outcome_checkpoint.json": "ec4e586c10fa496e08fbff57d0ca5f83cdfe9762dcde21093c4efac62fed69b4", ".modelhub_state/outcome_checkpoint.json": "e24601dd9d6491479d06b4b4a1271bbe56f485ff575af3a7cce84d0515cc3ee4",
".modelhub_state/queue_cleanup_latest.json": "01e08fd4618eb925c85708b1e84308d8914f762fc7ce784e5b71b8af21bef866", ".modelhub_state/queue_cleanup_latest.json": "01e08fd4618eb925c85708b1e84308d8914f762fc7ce784e5b71b8af21bef866",
".modelhub_state/recent_outcomes.jsonl": "5c3c8d910da2a1d1d4d1b0a9903e8c1048e4bd8112041ea9e351233dc26184fd", ".modelhub_state/recent_outcomes.jsonl": "5c3c8d910da2a1d1d4d1b0a9903e8c1048e4bd8112041ea9e351233dc26184fd",
".modelhub_state/recovery_active_tasks.jsonl": "2dfff8a09bbc4eab40b13e6cecf48d977bc873fc9f993a828fdec9380a58ac4f", ".modelhub_state/recovery_active_tasks.jsonl": "b4e76eb4f03cee76a344ba08c216351b5b13e9e0e225a06fc5cfad9f0cd2b3cc",
".modelhub_state/recovery_intents.jsonl": "f230f893fcb248b7b8ae98940688bb15f4de7b9be1a2bcc89b709ae3885cd783", ".modelhub_state/recovery_intents.jsonl": "c6695639d767d8c4288de7353b7c387aa69cbef5535f5d8a59f58f7f2955149e",
".modelhub_state/routing_intelligence.json": "5f7939a4bcc0cd3361fb3c8b9e46d01882b7482b42018a697367e830f28b1f09", ".modelhub_state/routing_intelligence.json": "5f7939a4bcc0cd3361fb3c8b9e46d01882b7482b42018a697367e830f28b1f09",
".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552", ".modelhub_state/submission_exclusions.jsonl": "632739c6cd6a2dd2237572ba18e6a390c5aa37ce56a18a2c1341d78569421552",
".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983", ".modelhub_state/worker_crashes.jsonl": "b41d1dda7bab11bedd96de40fecd2d416e47396901b3283f48a56de5d6348983",
"ledger/submissions.jsonl": "b8563512d893ae2a4f8a4d65881d0eab34d0b8d937550ac1fd54cdbaddb9db2b", "ledger/submissions.jsonl": "bc4265db15e741217b95bea4cfa61a7b0db9a1c1d021ad7ec05c2269031a5569",
"outcomes/submissions.jsonl": "5299e707c920d77fb00dc5c6b61ce2213c163b805502a44820ad42f628cd2a2e" "outcomes/submissions.jsonl": "21f61e212567d10de47d3dc8795764b5d3e0a57a71f4b3b7987a31cdfa4372f7"
}, },
"generation": 7492, "generation": 7493,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-15T02:49:58.078653+00:00", "updatedAt": "2026-09-15T02:53:05.848516+00:00",
"writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c" "writerId": "07a76ec4a8bc45bc8c08d7549ca0fd6c"
} }

1
outcomes/submissions.jsonl
View File

@@ -65,7 +65,6 @@
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-05T07:14:11.020202+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:12:12.056590+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4636059", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-05T07:14:11.020202+00:00", "modelId": "inferencerlabs/DeepSeek-V4-Flash-MTP-DSpark-MLX", "modelProfile": {"architectures": [], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 12994906286, "estimatedRequiredGiB": 14.53, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4_dspark", "modelscopeFileSize": 13001289422, "modelscopeLicense": null, "modelscopeParams": 4276397927, "modelscopeTags": ["model_type:deepseek_v4_dspark", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 13001289422}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:12:12.056590+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4636059", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T07:14:11.020212+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "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": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:12:18.663255+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4636060", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T07:14:11.020212+00:00", "modelId": "neuralmagic/SmolLM-360M-Instruct-quantized.w8a8", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "ac9457423139c55bd60f70bc9092d1d9dddd724b01ac0d5cac27be6ed145e50e", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 504052632, "estimatedRequiredGiB": 0.567, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 507443106, "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": 507443106}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:12:18.663255+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4636060", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T07:14:11.020096+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5705684944, "estimatedRequiredGiB": 6.387, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5714910031, "modelscopeLicense": null, "modelscopeParams": 8031506432, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5714910031}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:12:29.786627+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4636099", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-05T07:14:11.020096+00:00", "modelId": "nm-testing/Meta-Llama-3-8B-Instruct-W4A16-ACTORDER-compressed-tensors-test", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5705684944, "estimatedRequiredGiB": 6.387, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "modelhub_preflight_oom:36"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5714910031, "modelscopeLicense": null, "modelscopeParams": 8031506432, "modelscopeTags": ["model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5714910031}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:12:29.786627+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "4636099", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823946+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727938576, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737300809, "modelscopeLicense": "other", "modelscopeParams": 8030261248, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737300809}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:29:59.915927+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636369", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823927+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:29:59.925332+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636370", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823927+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737317601, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737317601}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:29:59.925332+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636370", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823920+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:29:59.918683+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636372", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823920+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 7550622334, "modelscopeLicense": "other", "modelscopeParams": 11520053248, "modelscopeTags": ["license:other", "model_type:llama", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:mergekit", "custom_tag:merge", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 7550622334}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:29:59.918683+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636372", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823934+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:30:00.029529+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636376", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-05T07:32:32.823934+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "1566bbd6c69427ad32f7f86aeba4e39850a1a7af5c6f4ef3c9ca82f0e882f3c5", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://cambricon.com/index.php?a=lists&c=index&catid=406&m=content"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "llama", "modelscopeFileSize": 5737318602, "modelscopeLicense": "other", "modelscopeParams": 8030269440, "modelscopeTags": ["license:other", "model_type:llama", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:4-bit", "custom_tag:AWQ", "custom_tag:text-generation", "custom_tag:autotrain_compatible", "custom_tag:endpoints_compatible", "custom_tag:axolotl", "custom_tag:finetune", "custom_tag:facebook", "custom_tag:meta", "custom_tag:pytorch", "custom_tag:llama", "custom_tag:llama-3"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "awq", "repositoryOnDiskBytes": 5737318602}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T23:30:00.029529+00:00", "targetGpu": "Cambricon_mlu-370-x8", "taskId": "4636376", "taskType": "text-generation", "verifyResult": null}