state: generation 22913 (intent)

This commit is contained in:
2026-10-10 08:19:42 +00:00
parent 11c154f1e0
commit 57e1aa3a16
8 changed files with 1635 additions and 1330 deletions

View File

@@ -2944,7 +2944,7 @@
"taskType": "text-generation"
}
},
"generatedAt": "2026-10-10T08:03:33.598263+00:00",
"generatedAt": "2026-10-10T08:15:47.809330+00:00",
"summary": {
"activeBlockCount": 147,
"byGpuFramework": {

View File

@@ -443,121 +443,121 @@
}
},
"frameworkUpdatedAt": null,
"generatedAt": "2026-10-10T08:13:54.584553+00:00",
"generatedAt": "2026-10-10T08:17:34.462615+00:00",
"gpuStats": {
"Ascend_910-b3": {
"available": true,
"backlogHours": 1152.1241379310345,
"backlogHours": 1144.3150684931506,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b3",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.8843699347295599,
"queueFactor": 0.9603571472805361,
"queueWeight": 0.9603571472805361,
"recentSuccess": 47,
"recentSuccessRate": 0.32413793103448274,
"recentTerminal": 145,
"recentWilsonLowerBound": 0.2533452486065094,
"running": 8,
"selectionWeight": 0.8493109876575541,
"qualityFactor": 1.0593084556490235,
"queueFactor": 0.9649161003951285,
"queueWeight": 0.9649161003951285,
"recentSuccess": 50,
"recentSuccessRate": 0.3424657534246575,
"recentTerminal": 146,
"recentWilsonLowerBound": 0.27041584886057934,
"running": 9,
"selectionWeight": 1.0221437841404417,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 24.166666666666668,
"waiting": 27843
"throughputPerHour": 24.333333333333332,
"waiting": 27845
},
"Ascend_910-b4": {
"available": true,
"backlogHours": 1456.095238095238,
"backlogHours": 1433.109375,
"canVerify": true,
"error": null,
"gpu": "Ascend_910-b4",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 2.5,
"queueFactor": 0.9272123273628564,
"queueWeight": 0.9272123273628564,
"queueFactor": 0.9328879749100778,
"queueWeight": 0.9328879749100778,
"recentSuccess": 62,
"recentSuccessRate": 0.49206349206349204,
"recentTerminal": 126,
"recentWilsonLowerBound": 0.4063047244513012,
"running": 8,
"selectionWeight": 2.318030818407141,
"recentSuccessRate": 0.484375,
"recentTerminal": 128,
"recentWilsonLowerBound": 0.3995214745657504,
"running": 10,
"selectionWeight": 2.3322199372751946,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.0,
"waiting": 30578
"throughputPerHour": 21.333333333333332,
"waiting": 30573
},
"Biren_166m": {
"available": true,
"backlogHours": 127.6969696969697,
"backlogHours": 127.14572864321609,
"canVerify": true,
"error": null,
"gpu": "Biren_166m",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.05992149274640102,
"qualityFactor": 0.05427780844442985,
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 22,
"recentSuccessRate": 0.1111111111111111,
"recentTerminal": 198,
"recentWilsonLowerBound": 0.0745290848046365,
"recentSuccess": 21,
"recentSuccessRate": 0.10552763819095477,
"recentTerminal": 199,
"recentWilsonLowerBound": 0.0700626606555105,
"running": 8,
"selectionWeight": 0.07789794057032133,
"selectionWeight": 0.07056115097775881,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 33.0,
"waiting": 4214
"throughputPerHour": 33.166666666666664,
"waiting": 4217
},
"Cambricon_mlu-370-x4": {
"available": true,
"backlogHours": 1313.44,
"backlogHours": 1350.0,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x4",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.5396707453597864,
"queueFactor": 0.9416643488529907,
"queueWeight": 0.9416643488529907,
"recentSuccess": 22,
"recentSuccessRate": 0.29333333333333333,
"recentTerminal": 75,
"recentWilsonLowerBound": 0.20239997218158162,
"qualityFactor": 0.6730269778107485,
"queueFactor": 0.9412854167657568,
"queueWeight": 0.9412854167657568,
"recentSuccess": 23,
"recentSuccessRate": 0.3150684931506849,
"recentTerminal": 73,
"recentWilsonLowerBound": 0.22003473675403795,
"running": 7,
"selectionWeight": 0.5081887010242314,
"selectionWeight": 0.6335104793031882,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 12.5,
"waiting": 16418
"throughputPerHour": 12.166666666666666,
"waiting": 16425
},
"Cambricon_mlu-370-x8": {
"available": true,
"backlogHours": 392.97777777777776,
"backlogHours": 390.0441176470588,
"canVerify": true,
"error": null,
"gpu": "Cambricon_mlu-370-x8",
"healthFactor": 1.0,
"maxConcurrentTasks": 7,
"qualityFactor": 0.3523797080856194,
"queueFactor": 1.1285023436378065,
"queueWeight": 1.1285023436378065,
"recentSuccess": 31,
"recentSuccessRate": 0.22962962962962963,
"recentTerminal": 135,
"recentWilsonLowerBound": 0.16675002584299897,
"qualityFactor": 0.4238000807597553,
"queueFactor": 1.133977234013559,
"queueWeight": 1.133977234013559,
"recentSuccess": 33,
"recentSuccessRate": 0.2426470588235294,
"recentTerminal": 136,
"recentWilsonLowerBound": 0.17831424909262023,
"running": 7,
"selectionWeight": 0.39766132642502766,
"selectionWeight": 0.48057964335467024,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 22.5,
"waiting": 8842
"throughputPerHour": 22.666666666666668,
"waiting": 8841
},
"Iluvatar_bi-100": {
"available": true,
"backlogHours": 50.86753246753246,
"backlogHours": 55.55113636363637,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-100",
@@ -567,196 +567,196 @@
"queueFactor": 1.3,
"queueWeight": 1.3,
"recentSuccess": 1,
"recentSuccessRate": 0.0025974025974025974,
"recentTerminal": 385,
"recentWilsonLowerBound": 0.0004586407760462704,
"running": 24,
"recentSuccessRate": 0.002840909090909091,
"recentTerminal": 352,
"recentWilsonLowerBound": 0.0005016534566580937,
"running": 25,
"selectionWeight": 0.065,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 64.16666666666667,
"waiting": 3264
"throughputPerHour": 58.666666666666664,
"waiting": 3259
},
"Iluvatar_bi-150": {
"available": true,
"backlogHours": 163.79757085020245,
"backlogHours": 191.7440758293839,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_bi-150",
"healthFactor": 1.0,
"maxConcurrentTasks": 50,
"qualityFactor": 0.21034549463392244,
"queueFactor": 1.286801462113525,
"queueWeight": 1.286801462113525,
"qualityFactor": 0.31121268406041724,
"queueFactor": 1.2614298458244937,
"queueWeight": 1.2614298458244937,
"recentSuccess": 43,
"recentSuccessRate": 0.17408906882591094,
"recentTerminal": 247,
"recentWilsonLowerBound": 0.13189016764972245,
"running": 6,
"selectionWeight": 0.27067289004392403,
"recentSuccessRate": 0.2037914691943128,
"recentTerminal": 211,
"recentWilsonLowerBound": 0.15496363704958327,
"running": 3,
"selectionWeight": 0.392572968072959,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 41.166666666666664,
"submissionEligible": true,
"throughputPerHour": 35.166666666666664,
"waiting": 6743
},
"Iluvatar_mrv-100": {
"available": true,
"backlogHours": 1972.595744680851,
"backlogHours": 1931.375,
"canVerify": true,
"error": null,
"gpu": "Iluvatar_mrv-100",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.5488170551586449,
"queueFactor": 0.8859351857150429,
"queueWeight": 0.8859351857150429,
"qualityFactor": 0.5422644719757561,
"queueFactor": 0.8920545335467827,
"queueWeight": 0.8920545335467827,
"recentSuccess": 15,
"recentSuccessRate": 0.3191489361702128,
"recentTerminal": 47,
"recentWilsonLowerBound": 0.2039520381739899,
"running": 2,
"selectionWeight": 0.486216339685557,
"recentSuccessRate": 0.3125,
"recentTerminal": 48,
"recentWilsonLowerBound": 0.19945512167731494,
"running": 3,
"selectionWeight": 0.4837294806073255,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 7.833333333333333,
"waiting": 15452
"throughputPerHour": 8.0,
"waiting": 15451
},
"Kunlunxin_p-800": {
"available": true,
"backlogHours": 449.22413793103453,
"backlogHours": 456.63157894736844,
"canVerify": true,
"error": null,
"gpu": "Kunlunxin_p-800",
"healthFactor": 1.0,
"maxConcurrentTasks": 8,
"qualityFactor": 0.38018541327705213,
"queueFactor": 1.106084233073432,
"queueWeight": 1.106084233073432,
"recentSuccess": 28,
"recentSuccessRate": 0.2413793103448276,
"recentTerminal": 116,
"recentWilsonLowerBound": 0.17260719345282605,
"running": 8,
"selectionWeight": 0.420517091270254,
"qualityFactor": 0.372618373246395,
"queueFactor": 1.1074815610080329,
"queueWeight": 1.1074815610080329,
"recentSuccess": 27,
"recentSuccessRate": 0.23684210526315788,
"recentTerminal": 114,
"recentWilsonLowerBound": 0.16818157933444355,
"running": 9,
"selectionWeight": 0.41266797766319135,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 19.333333333333332,
"waiting": 8685
"throughputPerHour": 19.0,
"waiting": 8676
},
"MetaX_c-500": {
"available": true,
"backlogHours": 513.1935483870967,
"backlogHours": 504.95238095238096,
"canVerify": true,
"error": null,
"gpu": "MetaX_c-500",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 0.3266447554384373,
"queueFactor": 1.0842151862573284,
"queueWeight": 1.0842151862573284,
"recentSuccess": 28,
"recentSuccessRate": 0.22580645161290322,
"recentTerminal": 124,
"recentWilsonLowerBound": 0.16109993441103604,
"running": 4,
"selectionWeight": 0.3541532043576648,
"qualityFactor": 0.39235689334401347,
"queueFactor": 1.0908972121415499,
"queueWeight": 1.0908972121415499,
"recentSuccess": 30,
"recentSuccessRate": 0.23809523809523808,
"recentTerminal": 126,
"recentWilsonLowerBound": 0.17217416354451306,
"running": 5,
"selectionWeight": 0.4280210411135037,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 20.666666666666668,
"waiting": 10606
"throughputPerHour": 21.0,
"waiting": 10604
},
"Mthreads_s4000": {
"available": true,
"backlogHours": 2819.5,
"backlogHours": 2941.9565217391305,
"canVerify": true,
"error": null,
"gpu": "Mthreads_s4000",
"healthFactor": 1.0,
"maxConcurrentTasks": 4,
"qualityFactor": 1.7412732408808431,
"queueFactor": 0.839714880562812,
"queueWeight": 0.839714880562812,
"qualityFactor": 2.0024533841218877,
"queueFactor": 0.8374829188664105,
"queueWeight": 0.8374829188664105,
"recentSuccess": 23,
"recentSuccessRate": 0.4791666666666667,
"recentTerminal": 48,
"recentWilsonLowerBound": 0.34471090015787464,
"running": 4,
"selectionWeight": 1.4621730514934776,
"recentSuccessRate": 0.5,
"recentTerminal": 46,
"recentWilsonLowerBound": 0.3611870167007237,
"running": 5,
"selectionWeight": 1.67702050502832,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 8.0,
"waiting": 22556
"throughputPerHour": 7.666666666666667,
"waiting": 22555
},
"Sunrise_pt-200-x1": {
"available": true,
"backlogHours": 2488.5714285714284,
"backlogHours": 2488.714285714286,
"canVerify": true,
"error": null,
"gpu": "Sunrise_pt-200-x1",
"healthFactor": 1.0,
"maxConcurrentTasks": 2,
"qualityFactor": 0.22072007190317733,
"queueFactor": 0.8555889118324543,
"queueWeight": 0.8555889118324543,
"qualityFactor": 0.22904861313915192,
"queueFactor": 0.858766588814977,
"queueWeight": 0.858766588814977,
"recentSuccess": 10,
"recentSuccessRate": 0.23809523809523808,
"recentTerminal": 42,
"recentWilsonLowerBound": 0.13480820811018185,
"running": 2,
"selectionWeight": 0.18884564613922056,
"selectionWeight": 0.19669929617831083,
"stale": false,
"submissionEligible": false,
"throughputPerHour": 7.0,
"waiting": 17420
"waiting": 17421
},
"Vastai_va16": {
"available": true,
"backlogHours": 714.6461538461538,
"backlogHours": 720.046511627907,
"canVerify": true,
"error": null,
"gpu": "Vastai_va16",
"healthFactor": 1.0,
"maxConcurrentTasks": 16,
"qualityFactor": 0.3219725024470605,
"queueFactor": 1.031677609389423,
"queueWeight": 1.031677609389423,
"recentSuccess": 29,
"recentSuccessRate": 0.2230769230769231,
"recentTerminal": 130,
"recentWilsonLowerBound": 0.16004839200095863,
"running": 16,
"selectionWeight": 0.33217182161371356,
"qualityFactor": 0.30986115543135284,
"queueFactor": 1.0343495097130189,
"queueWeight": 1.0343495097130189,
"recentSuccess": 28,
"recentSuccessRate": 0.21705426356589147,
"recentTerminal": 129,
"recentWilsonLowerBound": 0.154657377030721,
"running": 17,
"selectionWeight": 0.32050473419952935,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 21.666666666666668,
"waiting": 15484
"throughputPerHour": 21.5,
"waiting": 15481
},
"hygon_k100-ai": {
"available": true,
"backlogHours": 1044.9557522123894,
"backlogHours": 1083.6880733944954,
"canVerify": true,
"error": null,
"gpu": "hygon_k100-ai",
"healthFactor": 1.0,
"maxConcurrentTasks": 6,
"qualityFactor": 0.44303087199610236,
"queueFactor": 0.97452498717122,
"queueWeight": 0.97452498717122,
"recentSuccess": 29,
"recentSuccessRate": 0.25663716814159293,
"recentTerminal": 113,
"recentWilsonLowerBound": 0.18503685046249974,
"qualityFactor": 0.4547437947996742,
"queueFactor": 0.9728273044182972,
"queueWeight": 0.9728273044182972,
"recentSuccess": 28,
"recentSuccessRate": 0.25688073394495414,
"recentTerminal": 109,
"recentWilsonLowerBound": 0.18411863732206865,
"running": 6,
"selectionWeight": 0.4317446548484561,
"selectionWeight": 0.4423871800959143,
"stale": false,
"submissionEligible": true,
"throughputPerHour": 18.833333333333332,
"waiting": 19680
"throughputPerHour": 18.166666666666668,
"waiting": 19687
}
},
"queueAttemptedAt": "2026-10-10T08:04:59.190479+00:00",
"queueAttemptedAt": "2026-10-10T08:17:34.462615+00:00",
"queueError": null,
"queueUpdatedAt": "2026-10-10T08:04:59.190479+00:00",
"queueUpdatedAt": "2026-10-10T08:17:34.462615+00:00",
"supportedGpus": [
"Cambricon_mlu-370-x4",
"Vastai_va16",

File diff suppressed because it is too large Load Diff

View File

@@ -1,6 +1,6 @@
{
"generatedAt": "2026-10-10T08:03:33.502996+00:00",
"lastSyncTime": "2026-10-10T08:03:32.765493+00:00",
"generatedAt": "2026-10-10T08:15:47.719711+00:00",
"lastSyncTime": "2026-10-10T08:15:47.453341+00:00",
"recentLimit": 300,
"report": {
"architectureCompatibilityBlocks": {
@@ -3387,11 +3387,11 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 1,
"failureBreakdown": {
"ambiguous_runtime": 147,
"ambiguous_runtime": 149,
"memory_capacity": 1,
"参数/模板问题": 1
},
"failureCount": 149,
"failureCount": 151,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"pendingCount": 0,
@@ -3401,8 +3401,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 149,
"unresolvedFailureCount": 148
"total": 151,
"unresolvedFailureCount": 150
},
"Biren_166m|vllm|text-generation": {
"attributableFailureCount": 50,
@@ -5805,7 +5805,7 @@
"decisionSuccessRate": 0.0269,
"decisionTotal": 186,
"failureBreakdown": {
"ambiguous_runtime": 411,
"ambiguous_runtime": 413,
"backend_operator": 10,
"framework_architecture_unsupported": 52,
"memory_capacity": 10,
@@ -5814,15 +5814,15 @@
"tokenizer_compatibility": 96,
"参数/模板问题": 16
},
"failureCount": 635,
"failureCount": 637,
"failureRate": 0.9922,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 27,
"successCount": 5,
"successRate": 0.0078,
"total": 640,
"unresolvedFailureCount": 427
"total": 642,
"unresolvedFailureCount": 429
},
"vllm_tokenizer_patch": {
"attributableFailureCount": 169,
@@ -5853,7 +5853,7 @@
"unresolvedFailureCount": 307
}
},
"generatedAt": "2026-10-10T08:03:33.489946+00:00",
"generatedAt": "2026-10-10T08:15:47.706960+00:00",
"gpuSummaries": {
"Ascend_910-b3": {
"attributableFailureCount": 130,
@@ -5916,7 +5916,7 @@
"decisionSuccessRate": 0.1147,
"decisionTotal": 218,
"failureBreakdown": {
"ambiguous_runtime": 291,
"ambiguous_runtime": 293,
"backend_operator": 4,
"context_length": 10,
"framework_architecture_unsupported": 125,
@@ -5930,15 +5930,15 @@
"日志缺失": 62,
"验证失败": 27
},
"failureCount": 790,
"failureRate": 0.9693,
"failureCount": 792,
"failureRate": 0.9694,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 2,
"successCount": 25,
"successRate": 0.0307,
"total": 815,
"unresolvedFailureCount": 595
"successRate": 0.0306,
"total": 817,
"unresolvedFailureCount": 597
},
"Cambricon_mlu-370-x4": {
"attributableFailureCount": 765,
@@ -9496,9 +9496,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 15
"ambiguous_runtime": 17
},
"failureCount": 15,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"modelType": "mini_k3",
@@ -9510,8 +9510,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 15,
"unresolvedFailureCount": 15
"total": 17,
"unresolvedFailureCount": 17
},
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none": {
"attributableFailureCount": 0,
@@ -26385,9 +26385,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 6
"ambiguous_runtime": 7
},
"failureCount": 6,
"failureCount": 7,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastPlatformFailureAt": null,
@@ -26399,8 +26399,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 6,
"unresolvedFailureCount": 6
"total": 7,
"unresolvedFailureCount": 7
},
"Cambricon_mlu-370-x4|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -26490,9 +26490,9 @@
"failureBreakdown": {
"ambiguous_runtime": 2,
"framework_architecture_unsupported": 1,
"参数/模板问题": 14
"参数/模板问题": 13
},
"failureCount": 17,
"failureCount": 16,
"failureRate": 1.0,
"framework": "vllm_0_17_0_corex_4_4_0",
"lastPlatformFailureAt": null,
@@ -26504,8 +26504,8 @@
"successRate": 0.0,
"targetGpu": "Iluvatar_bi-150",
"taskType": "text-generation",
"total": 17,
"unresolvedFailureCount": 16
"total": 16,
"unresolvedFailureCount": 15
},
"Iluvatar_mrv-100|unknown|text-generation": {
"attributableFailureCount": 0,
@@ -27127,9 +27127,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 2
"ambiguous_runtime": 3
},
"failureCount": 2,
"failureCount": 3,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"lastTerminalAt": "2026-10-10T00:08:25.360789+00:00",
@@ -27142,8 +27142,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 2,
"unresolvedFailureCount": 2
"total": 3,
"unresolvedFailureCount": 3
},
"Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5_moe|none": {
"attributableFailureCount": 0,
@@ -33390,9 +33390,9 @@
"decisionSuccessRate": 0.0,
"decisionTotal": 0,
"failureBreakdown": {
"ambiguous_runtime": 15
"ambiguous_runtime": 17
},
"failureCount": 15,
"failureCount": 17,
"failureRate": 1.0,
"framework": "vllm_fix_tokenizer",
"loadSizeLog2Bucket": 30,
@@ -33405,8 +33405,8 @@
"successRate": 0.0,
"targetGpu": "Biren_166m",
"taskType": "text-generation",
"total": 15,
"unresolvedFailureCount": 15
"total": 17,
"unresolvedFailureCount": 17
},
"Biren_166m|vllm_fix_tokenizer|text-generation|mistral3|none|34": {
"attributableFailureCount": 0,
@@ -58545,15 +58545,15 @@
"unresolvedFailureCount": 0
}
},
"terminalRecords": 17776,
"totalRecords": 18290,
"terminalRecords": 17778,
"totalRecords": 18292,
"totals": {
"attributableFailureCount": 6315,
"decisionFailureRate": 0.8655,
"decisionSuccessRate": 0.1345,
"decisionTotal": 7296,
"failureBreakdown": {
"ambiguous_runtime": 4624,
"ambiguous_runtime": 4626,
"architecture_compatibility": 212,
"attention_backend": 3,
"backend_operator": 131,
@@ -58569,15 +58569,15 @@
"日志缺失": 719,
"验证失败": 676
},
"failureCount": 16795,
"failureCount": 16797,
"failureRate": 0.9448,
"pendingCount": 0,
"pendingRate": 0.0,
"platformFailureCount": 956,
"successCount": 981,
"successRate": 0.0552,
"total": 17776,
"unresolvedFailureCount": 9524
"total": 17778,
"unresolvedFailureCount": 9526
},
"warnings": [
"GPU MetaX_c-500 本地统计失败率偏高(≥50%),建议重点关注。",
@@ -58639,6 +58639,6 @@
]
},
"storageMode": "decision_state_only",
"summarizedRecords": 18290,
"summarizedRecords": 18292,
"version": 1
}

View File

@@ -295,6 +295,6 @@
{"failReason": "参数/模板问题", "framework": "", "lastSyncTime": "2026-09-22T10:15:00.769035+00:00", "modelId": "mlx-community/Qwen3.5-122B-A10B-OptiQ-2bit-REAP-63B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T10:13:22+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4979107", "taskType": "text-generation", "verifyResult": null}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-08T21:09:25.152964+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T06:26:57.052647+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5013724", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T11:35:31.353790+00:00", "modelId": "Panyuqi/SpikingBrain-2.0-base-8k", "modelProfile": {"architectures": ["SSESWAMoBAForCausalLM"], "configFingerprint": "1cc16a7df03cf7b1485e2fda7e5c05e286a546d04e80bdd595c015004b3852a8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11110611058, "estimatedRequiredGiB": 12.435, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "sse_swa_moba", "modelscopeFileSize": 11126702266, "modelscopeLicense": "Apache License 2.0", "modelscopeParams": null, "modelscopeTags": ["license:Apache License 2.0", "model_type:sse_swa_moba", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11126702266}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T06:15:24.089191+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5013573", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-10T08:15:47.453315+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030769952, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039132310}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:59:41.753031+00:00", "targetGpu": "Biren_166m", "taskId": "5013417", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-10T08:15:47.453341+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:59:41.751599+00:00", "targetGpu": "Biren_166m", "taskId": "5013416", "taskType": "text-generation", "verifyResult": -1}
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557099+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T05:54:51.552227+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5013340", "taskType": "text-generation", "verifyResult": null}
{"failReason": "参数/模板问题", "framework": "vllm_0_17_0_corex_4_4_0", "lastSyncTime": "2026-10-08T06:08:00.557020+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-09-22T05:54:51.550868+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "5013339", "taskType": "text-generation", "verifyResult": null}
{"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "execute_empty_result", "failureCode": "EXECUTE_EMPTY_RESULT", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-09T17:58:01.576792+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g8-v2_C", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030882272, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": 1015108684, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039244968}, "outcome": "failed", "status": "success", "submitTime": "2026-09-22T05:52:13.652441+00:00", "targetGpu": "Biren_166m", "taskId": "5013306", "taskType": "text-generation", "verifyResult": -1}

View File

@@ -3318,6 +3318,7 @@
{"batchId": "abc53a8316714ce8becfa5477f135ff7", "completedAt": "2026-10-09T19:02:14.031882+00:00", "configFingerprint": "05ede70cae27525d29b4c44e2be02476a5362f2e8a93365f5c82cd3c918aa123", "configSource": "modelhub_live", "createdAt": "2026-10-09T18:59:58.090507+00:00", "framework": "llamacpp", "intentId": "dae6cefd4b7047c78598723c046bba48", "lastModified": "2026-10-09T18:44:32+00:00", "modelAddress": "https://modelscope.cn/models/lightonai/colgrep-agent-2B-GGUF", "reason": null, "reconciledAt": "2026-10-10T08:07:09.485762+00:00", "repoId": "lightonai/colgrep-agent-2B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "hygon_k100-ai", "taskId": "5407638", "taskType": "text-generation"}
{"batchId": "ac5ecfbc052e4d75ae8bb21455be4827", "completedAt": "2026-10-09T19:18:44.322464+00:00", "configFingerprint": "3b82836fb5958ba363655971ed1f15d8109ab96526648b59a9c28586a1d7b2d6", "configSource": "modelhub_live", "createdAt": "2026-10-09T19:18:43.117096+00:00", "framework": "llamacpp", "intentId": "55603b708d5147198368764ac965ec48", "lastModified": "2026-10-09T18:44:32+00:00", "modelAddress": "https://modelscope.cn/models/lightonai/colgrep-agent-2B-GGUF", "reason": null, "reconciledAt": "2026-10-10T08:07:09.485760+00:00", "repoId": "lightonai/colgrep-agent-2B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "recovered_active", "targetGpu": "Mthreads_s4000", "taskId": "5407882", "taskType": "text-generation"}
{"batchId": "c4d7127a6ea84951995f6e5212e513a9", "completedAt": "2026-10-09T22:09:52.931701+00:00", "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configSource": "modelhub_live", "createdAt": "2026-10-09T22:07:56.306226+00:00", "framework": "vllm_fix_tokenizer", "intentId": "bc805f26f779445388d9b6fd5c613a65", "lastModified": "2026-10-09T18:42:19+00:00", "modelAddress": "https://modelscope.cn/models/IQuestLab/SAIL", "reason": null, "reconciledAt": "2026-10-10T08:07:09.485757+00:00", "repoId": "IQuestLab/SAIL", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Kunlunxin_p-800", "taskId": "5410223", "taskType": "text-generation"}
{"batchId": "64ef2259965a4a47875e42e124456e7a", "configFingerprint": "014e4c7848d2739d8b20b385d6b85827a2fc5723d3b5a17c03afbd67c56275d9", "configSource": "modelhub_live", "createdAt": "2026-10-10T08:19:42.281118+00:00", "framework": "llamacpp", "intentId": "1c4c57e0fcb04deda8bccda4d928eff0", "lastModified": "2026-09-21T18:38:30+00:00", "modelAddress": "https://modelscope.cn/models/GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF", "repoId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "pending", "targetGpu": "Iluvatar_bi-150", "taskType": "text-generation"}
{"batchId": "04247231908a4293bb90fcfb6ceb1b21", "completedAt": "2026-10-10T03:37:10.311161+00:00", "configFingerprint": "41b32e99f4cd3b280f48beb66666c48e543570dbfdee61682247438440dae4f3", "configSource": "modelhub_live", "createdAt": "2026-10-10T03:35:16.235834+00:00", "framework": "llamacpp", "intentId": "7ec4fc2708014d83955beed36401eb73", "repoId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "uniqueness_rejected", "targetGpu": "Mthreads_s4000", "taskId": null, "taskType": "text-generation"}
{"batchId": "defc40efc99547dea797f26d6a4c1a65", "completedAt": "2026-10-10T03:33:51.337890+00:00", "configFingerprint": "b6b49b497726342799df1608aa88399dc2d2712f97d7f1eb9fbc89c5b78f2c4c", "configSource": "modelhub_live", "createdAt": "2026-10-10T03:32:02.289053+00:00", "framework": "llamacpp", "intentId": "4dc3d20711774633bcaa193b5c6032ab", "repoId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "Ascend_910-b4", "taskId": null, "taskType": "text-generation"}
{"batchId": "ad33979b5e404afbb2ad0be08c37f443", "completedAt": "2026-10-10T03:31:23.028422+00:00", "configFingerprint": "06134b5c2d8da0d467ef6d880ff8129b92f59c94ad3aaef465cb20bc54d364f3", "configSource": "modelhub_live", "createdAt": "2026-10-10T03:29:38.282173+00:00", "framework": "llamacpp", "intentId": "9fa52c5991d94baabeea36a1deff7284", "repoId": "GnLOLot/MiniCPM5-2B-Claude-Fable5-1-Thinking-Agentic-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "uniqueness_rejected", "targetGpu": "hygon_k100-ai", "taskId": null, "taskType": "text-generation"}

View File

@@ -2,24 +2,24 @@
"agentVersion": "2026.09.22.1",
"checksums": {
".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1",
".modelhub_state/architecture_compatibility_blacklist.json": "576108af61b6ad2e3b59af7a6bf12f74a8d05bbc2a9d0ff4df7efee222844a95",
".modelhub_state/architecture_compatibility_blacklist.json": "0f4e0447cb0a6de3f81fbfe3e8ae16a4769d8e1cd105aefcdca0465401271b0c",
".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab",
".modelhub_state/market_intelligence.json": "90a09eb0dbaedb8409fd959561c708148106292a31d238e19a6f5df12ce72c49",
".modelhub_state/official_capabilities.json": "b4918e8b37fad496b4a4bc1a9dc7393a07eb082e54a59bcdeead477c8dad7b45",
".modelhub_state/outcome_checkpoint.json": "6711c1b1c1674721b65eeff638beaa4bbb530b35404410d857bac014ac047a5a",
".modelhub_state/market_intelligence.json": "c4c08985023331ca2413c08850dd56c476a8ce4392b48926401a3fcefccf1601",
".modelhub_state/official_capabilities.json": "e12504d10027c4cd1342094e7e09b93c876bbfeb6ff1908a0893ec5ec5783c14",
".modelhub_state/outcome_checkpoint.json": "ab62421a00bb591f3ba685f783279626a7b2e8b700d0147d6a46ef601c63bf7f",
".modelhub_state/queue_cleanup_latest.json": "479eeff66efc0333efe15f88578ae4a41d1437eba223ca0c5098d4114c04e8cd",
".modelhub_state/recent_outcomes.jsonl": "e37c6a30edd813a620ab701506e1074880cdca66f2b206de17ce26bc8020ca47",
".modelhub_state/recent_outcomes.jsonl": "023faf119d9e24a49ff746f9b143adda1617d926adb6e82ae4c3029fdfab37f9",
".modelhub_state/recovery_active_tasks.jsonl": "ba0a42ad7a4278dcb45dbc19055fb7ce96409bd63800107a6e5ab7b2f6f7b627",
".modelhub_state/recovery_intents.jsonl": "2b48f7d98beed1ede25a17f320f20f4e1a2ecf0ff934ccc84a9dfdeee00d22cf",
".modelhub_state/recovery_intents.jsonl": "e047e1eba72cde4e51278e5aca23f75fb57b204f5afc3e665e9333942fa586e4",
".modelhub_state/routing_intelligence.json": "94b2db56167982b1b727ce34457b1d37556f3ce037602c951db8a51a3e64b6a6",
".modelhub_state/submission_exclusions.jsonl": "2269e9d4ab33cc7afbf93b4a49c7f3833d35511505655e324e5937b07a97bd31",
".modelhub_state/worker_crashes.jsonl": "b321ea3648ae6b322601ed30ef8c3b1da0f13612af1bde3a64b0d41dc18a7b9f",
"ledger/submissions.jsonl": "b621189fc18eb354bde0bb1d863fe48248e09ed9b389c24be82760d731db201e",
"outcomes/submissions.jsonl": "4ef6463fd5a35056b3a6f79596d3df584e87e0c08f9f832a48c3cab63106d42f"
"outcomes/submissions.jsonl": "e4c42a39eca7a0b6ca478235406484a4f1d9eb962ca908e733ffac2a932aab7f"
},
"generation": 22912,
"phase": "cycle",
"generation": 22913,
"phase": "intent",
"schemaVersion": 1,
"updatedAt": "2026-10-10T08:14:46.358086+00:00",
"updatedAt": "2026-10-10T08:19:42.420542+00:00",
"writerId": "43462b8a22de474db5c83d43b475a356"
}

View File

@@ -211,8 +211,6 @@
{"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-22T13:46:14.276964+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:42:55.602315+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5013164", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-22T13:58:31.356521+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": null, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:55:01.182755+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5013341", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-22T13:58:31.356490+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "533968aac3b9c90272dfbe2866791f782e077f0dceee5b6ffffce48ba6674a10", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": null, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:58:14.744160+00:00", "targetGpu": "MetaX_c-500", "taskId": "5013402", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T14:01:24.063895+00:00", "modelId": "nkkbr/Mini-K3-1H-decay-g4-v2_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2030769952, "estimatedRequiredGiB": 2.279, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:linear-attention", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2039132310}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:59:41.753031+00:00", "targetGpu": "Biren_166m", "taskId": "5013417", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T14:01:24.063918+00:00", "modelId": "nkkbr/Mini-K3-1H-mamba2-n64-g4-v1_B", "modelProfile": {"architectures": [], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2009388256, "estimatedRequiredGiB": 2.25, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "mini_k3", "modelscopeFileSize": null, "modelscopeLicense": null, "modelscopeParams": null, "modelscopeTags": ["model_type:mini_k3", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:kimi-k3", "custom_tag:mamba2", "custom_tag:pretraining", "custom_tag:mixture-of-experts", "custom_tag:architecture-ablation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2012995244}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T05:59:41.751599+00:00", "targetGpu": "Biren_166m", "taskId": "5013416", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T14:29:11.661447+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": null, "modelscopeTags": ["license:mit", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:mixed-precision", "custom_tag:4bit", "custom_tag:8bit", "custom_tag:optiq", "custom_tag:apple-silicon", "custom_tag:text-generation", "custom_tag:qwen3.5", "custom_tag:mimo_v2", "custom_tag:agentic", "custom_tag:tool-use"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120897697}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T06:26:57.046313+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5013726", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-22T14:29:11.661394+00:00", "modelId": "amd/Instella-MoE-16B-A3B-SFT-w4a16-llmcompressor", "modelProfile": {"architectures": ["InstellaMoEForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 30350903424, "estimatedRequiredGiB": 33.932, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v3", "modelscopeFileSize": 30361724387, "modelscopeLicense": "other", "modelscopeParams": 5134171936, "modelscopeTags": ["license:other", "model_type:deepseek_v3", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:quantized", "custom_tag:int4", "custom_tag:w4a16", "custom_tag:weight-only", "custom_tag:4-bit", "custom_tag:llm-compressor", "custom_tag:zendnn", "custom_tag:compressed-tensors", "custom_tag:amd", "custom_tag:cpu-inference"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 30361724387}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T06:26:57.044876+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5013725", "taskType": "text-generation", "verifyResult": null}
{"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-22T20:29:13.756800+00:00", "modelId": "z-lab/Muse-Glimmer-30B-DFlash2-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "b8a926f4d98c4c17ed728affade2dfee1910e905840c16a7c6d35cdf073f1b9a", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2959518912, "estimatedRequiredGiB": 11.359, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 10163561928, "modelscopeLicense": "apache-2.0", "modelscopeParams": 81, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:gguf", "custom_tag:dflash2", "custom_tag:speculative-decoding", "custom_tag:draft-model", "custom_tag:llama.cpp", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 10163561928}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-22T12:28:01.206856+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5018933", "taskType": "text-generation", "verifyResult": null}