state: generation 6317 (cycle)

This commit is contained in:
2026-09-12 18:08:37 +00:00
parent c18ef8e44c
commit f57ce38470
10 changed files with 2944 additions and 2901 deletions

View File

@@ -1406,7 +1406,7 @@
"taskType": "text-generation" "taskType": "text-generation"
} }
}, },
"generatedAt": "2026-09-12T18:02:44.711062+00:00", "generatedAt": "2026-09-12T18:08:36.272752+00:00",
"summary": { "summary": {
"activeBlockCount": 71, "activeBlockCount": 71,
"byGpuFramework": { "byGpuFramework": {

View File

@@ -59,7 +59,7 @@
"5": { "5": {
"complete": false, "complete": false,
"lastError": "ModelHubAPIError: 系统错误", "lastError": "ModelHubAPIError: 系统错误",
"listingErrors": 455, "listingErrors": 456,
"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": 5, "nextAccountIndex": 6,
"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": "2026-09-12T18:02:44.678252+00:00", "updatedAt": "2026-09-12T18:08:36.247890+00:00",
"version": 1 "version": 1
} }

View File

@@ -416,121 +416,121 @@
} }
}, },
"frameworkUpdatedAt": null, "frameworkUpdatedAt": null,
"generatedAt": "2026-09-12T18:00:52.181954+00:00", "generatedAt": "2026-09-12T18:04:47.488347+00:00",
"gpuStats": { "gpuStats": {
"Ascend_910-b3": { "Ascend_910-b3": {
"available": true, "available": true,
"backlogHours": 946.3378378378378, "backlogHours": 966.0413793103448,
"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": 1.2875972799362438, "qualityFactor": 1.3763740116499368,
"queueFactor": 1.0008944239236461, "queueFactor": 1.0051116731286185,
"queueWeight": 1.0008944239236461, "queueWeight": 1.0051116731286185,
"recentSuccess": 56, "recentSuccess": 57,
"recentSuccessRate": 0.3783783783783784, "recentSuccessRate": 0.3931034482758621,
"recentTerminal": 148, "recentTerminal": 145,
"recentWilsonLowerBound": 0.30425277698958925, "recentWilsonLowerBound": 0.31734377558655397,
"running": 8, "running": 8,
"selectionWeight": 1.2887489377474406, "selectionWeight": 1.3834095857002167,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 24.666666666666668, "throughputPerHour": 24.166666666666668,
"waiting": 23343 "waiting": 23346
}, },
"Ascend_910-b4": { "Ascend_910-b4": {
"available": true, "available": true,
"backlogHours": 1236.0, "backlogHours": 1274.5116279069769,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Ascend_910-b4", "gpu": "Ascend_910-b4",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 8, "maxConcurrentTasks": 8,
"qualityFactor": 1.6495398368121936, "qualityFactor": 1.6473891648646393,
"queueFactor": 0.9615955168637548, "queueFactor": 0.9641888521292241,
"queueWeight": 0.9615955168637548, "queueWeight": 0.9641888521292241,
"recentSuccess": 56, "recentSuccess": 55,
"recentSuccessRate": 0.42105263157894735, "recentSuccessRate": 0.4263565891472868,
"recentTerminal": 133, "recentTerminal": 129,
"recentWilsonLowerBound": 0.3405146523621463, "recentWilsonLowerBound": 0.3443591959416735,
"running": 11, "running": 8,
"selectionWeight": 1.586190111966775, "selectionWeight": 1.5883942678809577,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 22.166666666666668, "throughputPerHour": 21.5,
"waiting": 27398 "waiting": 27402
}, },
"Biren_166m": { "Biren_166m": {
"available": true, "available": true,
"backlogHours": 177.58441558441558, "backlogHours": 176.24516129032259,
"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": 0.37612875524012424, "qualityFactor": 0.3611289726426108,
"queueFactor": 1.2864250045036854, "queueFactor": 1.297316960350093,
"queueWeight": 1.2864250045036854, "queueWeight": 1.297316960350093,
"recentSuccess": 36, "recentSuccess": 36,
"recentSuccessRate": 0.23376623376623376, "recentSuccessRate": 0.23225806451612904,
"recentTerminal": 154, "recentTerminal": 155,
"recentWilsonLowerBound": 0.17390244213855313, "recentWilsonLowerBound": 0.1727449576065253,
"running": 10, "running": 8,
"selectionWeight": 0.4838614356537424, "selectionWeight": 0.4684987410830637,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 25.666666666666668, "throughputPerHour": 25.833333333333332,
"waiting": 4558 "waiting": 4553
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
"available": true, "available": true,
"backlogHours": 1635.9622641509434, "backlogHours": 1548.1071428571427,
"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": 0.33226581702753216, "qualityFactor": 0.4158494808535502,
"queueFactor": 0.9219963637375209, "queueFactor": 0.9364692556843618,
"queueWeight": 0.9219963637375209, "queueWeight": 0.9364692556843618,
"recentSuccess": 14, "recentSuccess": 16,
"recentSuccessRate": 0.2641509433962264, "recentSuccessRate": 0.2857142857142857,
"recentTerminal": 53, "recentTerminal": 56,
"recentWilsonLowerBound": 0.16437206511316813, "recentWilsonLowerBound": 0.18418621391703333,
"running": 7, "running": 7,
"selectionWeight": 0.3063478750936611, "selectionWeight": 0.3894302538116524,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 8.833333333333334, "throughputPerHour": 9.333333333333334,
"waiting": 14451 "waiting": 14449
}, },
"Cambricon_mlu-370-x8": { "Cambricon_mlu-370-x8": {
"available": true, "available": true,
"backlogHours": 477.2972972972973, "backlogHours": 464.63157894736844,
"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": 0.37134319792969267, "qualityFactor": 0.3078695685205719,
"queueFactor": 1.1091157032720729, "queueFactor": 1.1217533306224683,
"queueWeight": 1.1091157032720729, "queueWeight": 1.1217533306224683,
"recentSuccess": 27, "recentSuccess": 26,
"recentSuccessRate": 0.24324324324324326, "recentSuccessRate": 0.22807017543859648,
"recentTerminal": 111, "recentTerminal": 114,
"recentWilsonLowerBound": 0.17289320485810214, "recentWilsonLowerBound": 0.16065986333040763,
"running": 7, "running": 7,
"selectionWeight": 0.41186257212709165, "selectionWeight": 0.34535371388525377,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 18.5, "throughputPerHour": 19.0,
"waiting": 8830 "waiting": 8828
}, },
"Iluvatar_bi-100": { "Iluvatar_bi-100": {
"available": true, "available": true,
"backlogHours": 44.30487804878049, "backlogHours": 45.04643962848297,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Iluvatar_bi-100", "gpu": "Iluvatar_bi-100",
@@ -539,148 +539,148 @@
"qualityFactor": 0.05, "qualityFactor": 0.05,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 18, "recentSuccess": 16,
"recentSuccessRate": 0.054878048780487805, "recentSuccessRate": 0.04953560371517028,
"recentTerminal": 328, "recentTerminal": 323,
"recentWilsonLowerBound": 0.03499126350756856, "recentWilsonLowerBound": 0.030717597856607593,
"running": 26, "running": 24,
"selectionWeight": 0.065, "selectionWeight": 0.065,
"stale": false, "stale": false,
"submissionEligible": false, "submissionEligible": false,
"throughputPerHour": 54.666666666666664, "throughputPerHour": 53.833333333333336,
"waiting": 2422 "waiting": 2425
}, },
"Iluvatar_bi-150": { "Iluvatar_bi-150": {
"available": true, "available": true,
"backlogHours": 97.39024390243902, "backlogHours": 98.16393442622952,
"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": 0.05046170451894635, "qualityFactor": 0.0555368383662588,
"queueFactor": 1.3, "queueFactor": 1.3,
"queueWeight": 1.3, "queueWeight": 1.3,
"recentSuccess": 25, "recentSuccess": 26,
"recentSuccessRate": 0.1016260162601626, "recentSuccessRate": 0.10655737704918032,
"recentTerminal": 246, "recentTerminal": 244,
"recentWilsonLowerBound": 0.06978655540314754, "recentWilsonLowerBound": 0.07376035948922724,
"running": 9, "running": 8,
"selectionWeight": 0.06560021587463026, "selectionWeight": 0.07219788987613644,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 41.0, "throughputPerHour": 40.666666666666664,
"waiting": 3993 "waiting": 3992
}, },
"Iluvatar_mrv-100": { "Iluvatar_mrv-100": {
"available": true, "available": true,
"backlogHours": 2663.4857142857145, "backlogHours": 2452.8947368421054,
"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": 0.7068384396700939, "qualityFactor": 0.703060017625936,
"queueFactor": 0.856993730456916, "queueFactor": 0.8740008188152797,
"queueWeight": 0.856993730456916, "queueWeight": 0.8740008188152797,
"recentSuccess": 13, "recentSuccess": 14,
"recentSuccessRate": 0.37142857142857144, "recentSuccessRate": 0.3684210526315789,
"recentTerminal": 35, "recentTerminal": 38,
"recentWilsonLowerBound": 0.2316560736889106, "recentWilsonLowerBound": 0.23384013155413794,
"running": 3, "running": 2,
"selectionWeight": 0.6057561112432195, "selectionWeight": 0.614475031081353,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 5.833333333333333, "throughputPerHour": 6.333333333333333,
"waiting": 15537 "waiting": 15535
}, },
"Kunlunxin_p-800": { "Kunlunxin_p-800": {
"available": true, "available": true,
"backlogHours": 957.6521739130435, "backlogHours": 1032.84375,
"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": 0.3126868323678068, "qualityFactor": 0.36212971703450114,
"queueFactor": 0.9991116676089515, "queueFactor": 0.995081110904116,
"queueWeight": 0.9991116676089515, "queueWeight": 0.995081110904116,
"recentSuccess": 17, "recentSuccess": 17,
"recentSuccessRate": 0.2463768115942029, "recentSuccessRate": 0.265625,
"recentTerminal": 69, "recentTerminal": 64,
"recentWilsonLowerBound": 0.1598964745113261, "recentWilsonLowerBound": 0.1729623856953776,
"running": 7, "running": 7,
"selectionWeight": 0.31240906252636014, "selectionWeight": 0.36034844111808456,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.5, "throughputPerHour": 10.666666666666666,
"waiting": 11013 "waiting": 11017
}, },
"MetaX_c-500": { "MetaX_c-500": {
"available": true, "available": true,
"backlogHours": 886.8311688311688, "backlogHours": 853.05,
"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": 0.24330334953441313, "qualityFactor": 0.2953044843422508,
"queueFactor": 1.0106925355333871, "queueFactor": 1.0240413727412203,
"queueWeight": 1.0106925355333871, "queueWeight": 1.0240413727412203,
"recentSuccess": 17, "recentSuccess": 19,
"recentSuccessRate": 0.22077922077922077, "recentSuccessRate": 0.2375,
"recentTerminal": 77, "recentTerminal": 80,
"recentWilsonLowerBound": 0.14266286171984086, "recentWilsonLowerBound": 0.15764551183088746,
"running": 6, "running": 4,
"selectionWeight": 0.24590487924470195, "selectionWeight": 0.3024040095224767,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 12.833333333333334, "throughputPerHour": 13.333333333333334,
"waiting": 11381 "waiting": 11374
}, },
"Mthreads_s4000": { "Mthreads_s4000": {
"available": true, "available": true,
"backlogHours": 1866.0869565217392, "backlogHours": 1839.1714285714286,
"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": 1.481918774529861, "qualityFactor": 1.3956016026928462,
"queueFactor": 0.9039729163803113, "queueFactor": 0.9125787347760691,
"queueWeight": 0.9039729163803113, "queueWeight": 0.9125787347760691,
"recentSuccess": 30, "recentSuccess": 30,
"recentSuccessRate": 0.43478260869565216, "recentSuccessRate": 0.42857142857142855,
"recentTerminal": 69, "recentTerminal": 70,
"recentWilsonLowerBound": 0.3243261617876528, "recentWilsonLowerBound": 0.31935124886212546,
"running": 4, "running": 4,
"selectionWeight": 1.3396144364504954, "selectionWeight": 1.2735963448368919,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 11.5, "throughputPerHour": 11.666666666666666,
"waiting": 21460 "waiting": 21457
}, },
"Sunrise_pt-200-x1": { "Sunrise_pt-200-x1": {
"available": true, "available": true,
"backlogHours": 3330.692307692308, "backlogHours": 3463.4399999999996,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "Sunrise_pt-200-x1", "gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 2, "maxConcurrentTasks": 2,
"qualityFactor": 0.6582919713554916, "qualityFactor": 0.5121474050445495,
"queueFactor": 0.8287337455319523, "queueFactor": 0.8299224752745554,
"queueWeight": 0.8287337455319523, "queueWeight": 0.8299224752745554,
"recentSuccess": 10, "recentSuccess": 9,
"recentSuccessRate": 0.38461538461538464, "recentSuccessRate": 0.36,
"recentTerminal": 26, "recentTerminal": 25,
"recentWilsonLowerBound": 0.22428359511834425, "recentWilsonLowerBound": 0.20247656431735636,
"running": 2, "running": 2,
"selectionWeight": 0.5455487710750492, "selectionWeight": 0.42504264210001286,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 4.333333333333333, "throughputPerHour": 4.166666666666667,
"waiting": 14433 "waiting": 14431
}, },
"Vastai_va16": { "Vastai_va16": {
"available": true, "available": true,
@@ -690,15 +690,15 @@
"gpu": "Vastai_va16", "gpu": "Vastai_va16",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 16, "maxConcurrentTasks": 16,
"qualityFactor": 0.12546296435644544, "qualityFactor": 0.12224243827160902,
"queueFactor": 0.9817733799605276, "queueFactor": 0.9889622812809149,
"queueWeight": 0.9817733799605276, "queueWeight": 0.9889622812809149,
"recentSuccess": 11, "recentSuccess": 11,
"recentSuccessRate": 0.18333333333333332, "recentSuccessRate": 0.18333333333333332,
"recentTerminal": 60, "recentTerminal": 60,
"recentWilsonLowerBound": 0.10557689037136128, "recentWilsonLowerBound": 0.10557689037136128,
"running": 16, "running": 16,
"selectionWeight": 0.12317619857609464, "selectionWeight": 0.12089316062243188,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 10.0, "throughputPerHour": 10.0,
@@ -706,30 +706,30 @@
}, },
"hygon_k100-ai": { "hygon_k100-ai": {
"available": true, "available": true,
"backlogHours": 692.6666666666666, "backlogHours": 719.3076923076923,
"canVerify": true, "canVerify": true,
"error": null, "error": null,
"gpu": "hygon_k100-ai", "gpu": "hygon_k100-ai",
"healthFactor": 1.0, "healthFactor": 1.0,
"maxConcurrentTasks": 6, "maxConcurrentTasks": 6,
"qualityFactor": 2.5, "qualityFactor": 2.5,
"queueFactor": 1.0488576671382484, "queueFactor": 1.0505735693881624,
"queueWeight": 1.0488576671382484, "queueWeight": 1.0505735693881624,
"recentSuccess": 42, "recentSuccess": 41,
"recentSuccessRate": 0.5185185185185185, "recentSuccessRate": 0.5256410256410257,
"recentTerminal": 81, "recentTerminal": 78,
"recentWilsonLowerBound": 0.4113545922111773, "recentWilsonLowerBound": 0.4162457167544664,
"running": 8, "running": 6,
"selectionWeight": 2.622144167845621, "selectionWeight": 2.626433923470406,
"stale": false, "stale": false,
"submissionEligible": true, "submissionEligible": true,
"throughputPerHour": 13.5, "throughputPerHour": 13.0,
"waiting": 9351 "waiting": 9351
} }
}, },
"queueAttemptedAt": "2026-09-12T17:51:13.539911+00:00", "queueAttemptedAt": "2026-09-12T18:04:47.488347+00:00",
"queueError": null, "queueError": null,
"queueUpdatedAt": "2026-09-12T17:51:13.539911+00:00", "queueUpdatedAt": "2026-09-12T18:04:47.488347+00:00",
"supportedGpus": [ "supportedGpus": [
"Vastai_va16", "Vastai_va16",
"Iluvatar_mrv-100", "Iluvatar_mrv-100",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{ {
"generatedAt": "2026-09-12T17:16:50.134307+00:00", "generatedAt": "2026-09-12T18:04:41.740562+00:00",
"lastSyncTime": "2026-09-12T17:16:49.913530+00:00", "lastSyncTime": "2026-09-12T18:04:41.532609+00:00",
"recentLimit": 300, "recentLimit": 300,
"report": { "report": {
"architectureCompatibilityBlocks": { "architectureCompatibilityBlocks": {
@@ -1614,15 +1614,15 @@
"unresolvedFailureCount": 53 "unresolvedFailureCount": 53
}, },
"Biren_166m|vllm|text-generation": { "Biren_166m|vllm|text-generation": {
"attributableFailureCount": 2, "attributableFailureCount": 3,
"decisionFailureRate": 1.0, "decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0, "decisionSuccessRate": 0.0,
"decisionTotal": 2, "decisionTotal": 3,
"failureBreakdown": { "failureBreakdown": {
"framework_architecture_unsupported": 1, "framework_architecture_unsupported": 2,
"model_load": 1 "model_load": 1
}, },
"failureCount": 2, "failureCount": 3,
"failureRate": 1.0, "failureRate": 1.0,
"framework": "vllm", "framework": "vllm",
"pendingCount": 0, "pendingCount": 0,
@@ -1632,7 +1632,7 @@
"successRate": 0.0, "successRate": 0.0,
"targetGpu": "Biren_166m", "targetGpu": "Biren_166m",
"taskType": "text-generation", "taskType": "text-generation",
"total": 2, "total": 3,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Cambricon_mlu-370-x4|unknown|text-generation": { "Cambricon_mlu-370-x4|unknown|text-generation": {
@@ -2440,14 +2440,14 @@
"unresolvedFailureCount": 866 "unresolvedFailureCount": 866
}, },
"vllm": { "vllm": {
"attributableFailureCount": 279, "attributableFailureCount": 280,
"decisionFailureRate": 0.9894, "decisionFailureRate": 0.9894,
"decisionSuccessRate": 0.0106, "decisionSuccessRate": 0.0106,
"decisionTotal": 282, "decisionTotal": 283,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 200, "ambiguous_runtime": 200,
"backend_operator": 34, "backend_operator": 34,
"framework_architecture_unsupported": 193, "framework_architecture_unsupported": 194,
"memory_capacity": 6, "memory_capacity": 6,
"model_load": 26, "model_load": 26,
"platform_infrastructure": 1, "platform_infrastructure": 1,
@@ -2456,14 +2456,14 @@
"tokenizer_compatibility": 6, "tokenizer_compatibility": 6,
"参数/模板问题": 24 "参数/模板问题": 24
}, },
"failureCount": 504, "failureCount": 505,
"failureRate": 0.9941, "failureRate": 0.9941,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 1, "platformFailureCount": 1,
"successCount": 3, "successCount": 3,
"successRate": 0.0059, "successRate": 0.0059,
"total": 507, "total": 508,
"unresolvedFailureCount": 224 "unresolvedFailureCount": 224
}, },
"vllm-mlu": { "vllm-mlu": {
@@ -2568,7 +2568,7 @@
"unresolvedFailureCount": 1 "unresolvedFailureCount": 1
} }
}, },
"generatedAt": "2026-09-12T17:16:50.130271+00:00", "generatedAt": "2026-09-12T18:04:41.736777+00:00",
"gpuSummaries": { "gpuSummaries": {
"Ascend_910-b3": { "Ascend_910-b3": {
"attributableFailureCount": 28, "attributableFailureCount": 28,
@@ -2619,27 +2619,27 @@
"unresolvedFailureCount": 223 "unresolvedFailureCount": 223
}, },
"Biren_166m": { "Biren_166m": {
"attributableFailureCount": 30, "attributableFailureCount": 31,
"decisionFailureRate": 0.9677, "decisionFailureRate": 0.9688,
"decisionSuccessRate": 0.0323, "decisionSuccessRate": 0.0312,
"decisionTotal": 31, "decisionTotal": 32,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 26, "ambiguous_runtime": 26,
"backend_operator": 4, "backend_operator": 4,
"framework_architecture_unsupported": 21, "framework_architecture_unsupported": 22,
"memory_capacity": 1, "memory_capacity": 1,
"model_load": 3, "model_load": 3,
"tokenizer_compatibility": 1, "tokenizer_compatibility": 1,
"验证失败": 27 "验证失败": 27
}, },
"failureCount": 83, "failureCount": 84,
"failureRate": 0.9881, "failureRate": 0.9882,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 0, "platformFailureCount": 0,
"successCount": 1, "successCount": 1,
"successRate": 0.0119, "successRate": 0.0118,
"total": 84, "total": 85,
"unresolvedFailureCount": 53 "unresolvedFailureCount": 53
}, },
"Cambricon_mlu-370-x4": { "Cambricon_mlu-370-x4": {
@@ -2985,6 +2985,29 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|rwkv7|none": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma2|compressed-tensors": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma2|compressed-tensors": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -5171,6 +5194,30 @@
"total": 1, "total": 1,
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
}, },
"Biren_166m|vllm|text-generation|rwkv7|none|32": {
"attributableFailureCount": 1,
"decisionFailureRate": 1.0,
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"framework_architecture_unsupported": 1
},
"failureCount": 1,
"failureRate": 1.0,
"framework": "vllm",
"loadSizeLog2Bucket": 32,
"modelType": "rwkv7",
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 0,
"quantizationMethod": "none",
"successCount": 0,
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 1,
"unresolvedFailureCount": 0
},
"Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma2|compressed-tensors|31": { "Cambricon_mlu-370-x8|vllm-mlu|text-generation|gemma2|compressed-tensors|31": {
"attributableFailureCount": 0, "attributableFailureCount": 0,
"decisionFailureRate": 0.0, "decisionFailureRate": 0.0,
@@ -7254,17 +7301,17 @@
"unresolvedFailureCount": 0 "unresolvedFailureCount": 0
} }
}, },
"terminalRecords": 1731, "terminalRecords": 1732,
"totalRecords": 1818, "totalRecords": 1819,
"totals": { "totals": {
"attributableFailureCount": 491, "attributableFailureCount": 492,
"decisionFailureRate": 0.896, "decisionFailureRate": 0.8962,
"decisionSuccessRate": 0.104, "decisionSuccessRate": 0.1038,
"decisionTotal": 548, "decisionTotal": 549,
"failureBreakdown": { "failureBreakdown": {
"ambiguous_runtime": 405, "ambiguous_runtime": 405,
"backend_operator": 42, "backend_operator": 42,
"framework_architecture_unsupported": 304, "framework_architecture_unsupported": 305,
"memory_capacity": 11, "memory_capacity": 11,
"model_load": 72, "model_load": 72,
"platform_infrastructure": 4, "platform_infrastructure": 4,
@@ -7274,21 +7321,20 @@
"参数/模板问题": 101, "参数/模板问题": 101,
"验证失败": 673 "验证失败": 673
}, },
"failureCount": 1674, "failureCount": 1675,
"failureRate": 0.9671, "failureRate": 0.9671,
"pendingCount": 0, "pendingCount": 0,
"pendingRate": 0.0, "pendingRate": 0.0,
"platformFailureCount": 4, "platformFailureCount": 4,
"successCount": 57, "successCount": 57,
"successRate": 0.0329, "successRate": 0.0329,
"total": 1731, "total": 1732,
"unresolvedFailureCount": 1179 "unresolvedFailureCount": 1179
}, },
"warnings": [ "warnings": [
"GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。", "GPU Ascend_910-b4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。", "GPU Mthreads_s4000 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。", "GPU Cambricon_mlu-370-x4 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。", "GPU Iluvatar_mrv-100 本地统计失败率偏高≥50%),建议重点关注。",
@@ -7297,6 +7343,7 @@
"GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。", "GPU MetaX_c-500 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。", "GPU Biren_166m 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。", "GPU Iluvatar_bi-150 本地统计失败率偏高≥50%),建议重点关注。",
"GPU Sunrise_pt-200-x1 本地统计失败率偏高≥50%),建议重点关注。",
"组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm-patch-tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 hygon_k100-ai|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Ascend_910-b4|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7307,6 +7354,7 @@
"组合 Cambricon_mlu-370-x8|vllm-mlu|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Cambricon_mlu-370-x8|vllm-mlu|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Cambricon_mlu-370-x8|unknown|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-x8|unknown|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-x8|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-x8|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Biren_166m|vllm|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Vastai_va16|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 Vastai_va16|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 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
"组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。", "组合 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中,建议降低该 GPU+框架的提交优先级。",
@@ -7318,6 +7366,6 @@
] ]
}, },
"storageMode": "decision_state_only", "storageMode": "decision_state_only",
"summarizedRecords": 1818, "summarizedRecords": 1819,
"version": 1 "version": 1
} }

File diff suppressed because it is too large Load Diff

File diff suppressed because it is too large Load Diff

View File

@@ -34,7 +34,6 @@
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "modelId": "Youssofal/Qwen3.8-27B-MTPLX-Optimized-Quality-FP16", "submitTime": "2026-09-04T07:12:30.054811+00:00", "targetGpu": "Biren_166m", "taskId": "4621809", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-biren-166m"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T07:40:37.506061+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4622172", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T07:40:37.506061+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4622172", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b4"}
{"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T07:56:50.952206+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4622417", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"} {"framework": "vllm_tokenizer_patch", "modelAddress": "https://modelscope.cn/models/Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "modelId": "Mia-AiLab/Qwen3.8-27B-EXL3-3.5bpw", "submitTime": "2026-09-04T07:56:50.952206+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4622417", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-tokenizer-patch-ascend-910-b3"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-4B", "modelId": "XHToken/Spark-X2.5-4B", "submitTime": "2026-09-04T08:10:58.161686+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622625", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "modelId": "XHToken/Spark-X2.5-1.7B", "submitTime": "2026-09-04T08:10:58.162821+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622620", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/XHToken/Spark-X2.5-1.7B", "modelId": "XHToken/Spark-X2.5-1.7B", "submitTime": "2026-09-04T08:10:58.162821+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622620", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-04T08:10:58.185038+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622623", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-v0.4-AWQ", "submitTime": "2026-09-04T08:10:58.185038+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622623", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}
{"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T08:10:58.159820+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622624", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"} {"framework": "vllm", "modelAddress": "https://modelscope.cn/models/solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "submitTime": "2026-09-04T08:10:58.159820+00:00", "targetGpu": "MetaX_c-500", "taskId": "4622624", "taskType": "text-generation", "templateId": "modelhub-live-text-generation-vllm-metax-c-500"}

View File

@@ -1,24 +1,24 @@
{ {
"agentVersion": "2026.09.04.4", "agentVersion": "2026.09.04.4",
"checksums": { "checksums": {
".modelhub_state/architecture_compatibility_blacklist.json": "f4ef811dca22320bb028c39750499a4a273093b56e502f2dce7b8ba11a059b61", ".modelhub_state/architecture_compatibility_blacklist.json": "7864eec3a5ab0f66b8e3c852b723bbfa779a775f2b76ff063cea1228da66eaaf",
".modelhub_state/architecture_history_backfill.json": "cfce90fbca96632a4c54e02513f08f2e69e332fe9ce59d2fa83a28ba333dbc3f", ".modelhub_state/architecture_history_backfill.json": "34bb7b4cb806209c2f5dc447f494f2f32b8b5c9787b7c9e01b1e4931aeb9ae0a",
".modelhub_state/market_intelligence.json": "99a3173a7184b3509ce24a6e18dd00d5ea8a07b4a645889b7e67a3e7a208e5a1", ".modelhub_state/market_intelligence.json": "e1daf2d52d7508e3c77463e69450f7a6c3a3a9de4a1ff2ff318ad5348652defa",
".modelhub_state/official_capabilities.json": "5b14d59a0ebfcc32bedaf564b6382216334cf211e104bb33a3a2d4d7bdfb21ce", ".modelhub_state/official_capabilities.json": "b0dc099c5e8a0795729e403ef706b2f0dac7830a0dc9435efef8f48fb5c6158e",
".modelhub_state/outcome_checkpoint.json": "a4852d701c5ca6d8d89b39d651be30a5427dd955423a030226fc820c2e6a5a6a", ".modelhub_state/outcome_checkpoint.json": "e547a713bc00489e0b22ce7e24a2e53985ab8d5a85689084dfcf58344f108692",
".modelhub_state/queue_cleanup_latest.json": "ccebc58971e155e7d5987315af83d23359f4ad65134945945f168235fb97bc19", ".modelhub_state/queue_cleanup_latest.json": "ccebc58971e155e7d5987315af83d23359f4ad65134945945f168235fb97bc19",
".modelhub_state/recent_outcomes.jsonl": "f0143b6f492637a597d7027271b2d3cfa24058051c2bd6a684fca345a8b23463", ".modelhub_state/recent_outcomes.jsonl": "f0143b6f492637a597d7027271b2d3cfa24058051c2bd6a684fca345a8b23463",
".modelhub_state/recovery_active_tasks.jsonl": "1c60ef43af9ca22600df3dcc619dabf2f7de70e9be1f59f612d34aa332a0642f", ".modelhub_state/recovery_active_tasks.jsonl": "5d2ac7c2fad142ac86861b05821eea5cafdec5e7ad07316997735d1ee6ae4399",
".modelhub_state/recovery_intents.jsonl": "e672866267fe678679cc20879fb742486b1cbbb6dc7d40b14b1293fa3c00e80c", ".modelhub_state/recovery_intents.jsonl": "a29dc0676aaeeb9ebd016a393e1aef0bde892737f36d2f9283fcd4f8c40f9110",
".modelhub_state/routing_intelligence.json": "cdd3341d66484775862c4a1f5c766a7fc0200b1a3a204a76975162502e1d3457", ".modelhub_state/routing_intelligence.json": "cdd3341d66484775862c4a1f5c766a7fc0200b1a3a204a76975162502e1d3457",
".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220", ".modelhub_state/submission_exclusions.jsonl": "14480c58228be6b76e21e98008960b815d20d16132dcab7a11e5b449c5e2d220",
".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162", ".modelhub_state/worker_crashes.jsonl": "9693a31a13cc18a3136ff5373f9569dc2fecaa274aaf91d3b1c8a67f31fe0162",
"ledger/submissions.jsonl": "c20248468f30aaf04889e8782572ece890ec83cf99b928d235c84bdde86120b7", "ledger/submissions.jsonl": "7b7679c8bfcb6d92cbe8602b18b73e9560697c9e1a5bafff3b6f69ac07abe96b",
"outcomes/submissions.jsonl": "745160cb9cc5d215ce529ddd2680a88c801407156ad8692ddd55d6d6fcb35128" "outcomes/submissions.jsonl": "f2c15b1eceed1adfa384c4f3f5aadc118c8e5815bb7998e1aa8d52abcf2043b2"
}, },
"generation": 6316, "generation": 6317,
"phase": "cycle", "phase": "cycle",
"schemaVersion": 1, "schemaVersion": 1,
"updatedAt": "2026-09-12T18:02:44.810513+00:00", "updatedAt": "2026-09-12T18:08:37.005479+00:00",
"writerId": "e5dd59a4c84a4f21926bad61448789e2" "writerId": "e5dd59a4c84a4f21926bad61448789e2"
} }

View File

@@ -28,7 +28,6 @@
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T13:09:06.405170+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "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": "2026-09-04T05:06:37.162640+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611646", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T13:09:06.405170+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-DPO-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "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": "2026-09-04T05:06:37.162640+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611646", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T13:09:06.405177+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "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": "2026-09-04T05:06:37.165709+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611648", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T13:09:06.405177+00:00", "modelId": "solidrust/Llama-3-11B-Instruct-v0.1-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7541230432, "estimatedRequiredGiB": 8.438, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "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": "2026-09-04T05:06:37.165709+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611648", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T13:09:06.405152+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "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": "2026-09-04T05:06:37.161333+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611647", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T13:09:06.405152+00:00", "modelId": "solidrust/Llama-3-8B-Instruct-v0.5-AWQ", "modelProfile": {"architectures": ["LlamaForCausalLM"], "configFingerprint": "a494b1667fab53609b94cc853db1a12c8d3b9fcf98795ecbab3dd5eb3a3c77f6", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5727954960, "estimatedRequiredGiB": 6.412, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "manufacturer_spec", "sourceUrl": "https://docs.mthreads.com/s4000/s4000-doc-online/product_specifications/"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "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": "2026-09-04T05:06:37.161333+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4611647", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T14:45:22.924563+00:00", "modelId": "RWKV/RWKV7-2.9B-20260805", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896238160, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898265436, "modelscopeLicense": "apache-2.0", "modelscopeParams": 2948065280, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898265436}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T06:44:20.184828+00:00", "targetGpu": "Biren_166m", "taskId": "4621451", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T14:58:13.792120+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T06:55:47.742909+00:00", "targetGpu": "Biren_166m", "taskId": "4621594", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T14:58:13.792120+00:00", "modelId": "Jackrong/DeepSeek-V4-Pro-Qwen3.5-9B", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19306310880, "estimatedRequiredGiB": 21.599, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19326449341, "modelscopeLicense": "apache-2.0", "modelscopeParams": 9653104368, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:text-generation-inference", "custom_tag:transformers", "custom_tag:unsloth", "custom_tag:qwen3_5", "custom_tag:reasoning", "custom_tag:distillation", "custom_tag:deepseek", "custom_tag:sft", "custom_tag:rl", "custom_tag:gspo", "custom_tag:math", "custom_tag:stem", "custom_tag:tool-use", "custom_tag:function-calling", "custom_tag:mtp"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19326449341}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T06:55:47.742909+00:00", "targetGpu": "Biren_166m", "taskId": "4621594", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T14:58:13.792154+00:00", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31228126952, "estimatedRequiredGiB": 34.934, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 31258377392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:w8a8", "custom_tag:int8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 31258377392}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T06:55:47.759663+00:00", "targetGpu": "Biren_166m", "taskId": "4621595", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T14:58:13.792154+00:00", "modelId": "VerStella/Qwen3.8-27B-heretic-ara-W8A8-DCU", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 31228126952, "estimatedRequiredGiB": 34.934, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 31258377392, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27781427952, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:qwen", "custom_tag:qwen3.8", "custom_tag:w8a8", "custom_tag:int8", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 31258377392}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T06:55:47.759663+00:00", "targetGpu": "Biren_166m", "taskId": "4621595", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T15:07:35.511841+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:04:25.458550+00:00", "targetGpu": "Biren_166m", "taskId": "4621698", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-04T15:07:35.511841+00:00", "modelId": "nanbeige/Nanbeige4.2-3B-GPTQ-Int8", "modelProfile": {"architectures": ["NanbeigeForCausalLM"], "configFingerprint": "d341b8002cf39d3299fd429479e8c8e954583e49d4fec5a640ddc0f8f0cbd054", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5192364968, "estimatedRequiredGiB": 5.827, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "manufacturer_spec", "sourceUrl": "https://www.birentech.com/news/id6rz98v3obczy77cmxzfgk3/"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanbeige", "modelscopeFileSize": 5214325469, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4169800704, "modelscopeTags": ["license:apache-2.0", "model_type:nanbeige", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:llm", "custom_tag:nanbeige"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 5214325469}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-04T07:04:25.458550+00:00", "targetGpu": "Biren_166m", "taskId": "4621698", "taskType": "text-generation", "verifyResult": null}