diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index 98a478282e..da94eeb5a3 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -3280,7 +3280,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-09-28T08:47:47.751432+00:00", + "generatedAt": "2026-09-28T08:59:35.382528+00:00", "summary": { "activeBlockCount": 165, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 3d92bff548..f2aae171db 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -3,37 +3,37 @@ "communityError": null, "communitySample": {}, "communityUpdatedAt": "2026-09-28T08:55:57.173495+00:00", - "frameworkAttemptedAt": "2026-09-28T05:29:38.757504+00:00", + "frameworkAttemptedAt": "2026-09-28T09:02:33.955118+00:00", "frameworkError": null, "frameworkStats": { "text-generation": { "Ascend_910-b4": { "llamacpp": { "framework": "llamacpp", - "modelCount": 34416, + "modelCount": 34437, "officialConfigError": null, "officialConfigValid": true, - "successCount": 15620, - "successRate": 0.453858670385867, - "wilsonLowerBound": 0.4486040752665093 + "successCount": 15637, + "successRate": 0.45407555826581875, + "wilsonLowerBound": 0.44882232783777953 }, "vllm": { "framework": "vllm", - "modelCount": 38323, + "modelCount": 38352, "officialConfigError": null, "officialConfigValid": true, - "successCount": 10805, - "successRate": 0.2819455679357044, - "wilsonLowerBound": 0.2774626710671131 + "successCount": 10809, + "successRate": 0.2818366708385482, + "wilsonLowerBound": 0.27735599994304144 }, "vllm_tokenizer_patch": { "framework": "vllm_tokenizer_patch", - "modelCount": 10520, + "modelCount": 10541, "officialConfigError": null, "officialConfigValid": true, - "successCount": 4418, - "successRate": 0.4199619771863118, - "wilsonLowerBound": 0.41056135629944535 + "successCount": 4427, + "successRate": 0.4199791291148847, + "wilsonLowerBound": 0.4105877852368915 } }, "Biren_166m": { @@ -48,32 +48,32 @@ }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", - "modelCount": 22599, + "modelCount": 22694, "officialConfigError": null, "officialConfigValid": true, - "successCount": 4666, - "successRate": 0.2064693128014514, - "wilsonLowerBound": 0.20124200126174852 + "successCount": 4685, + "successRate": 0.20644223142680884, + "wilsonLowerBound": 0.20122602733579256 }, "vllm_tokenizer_patch": { "framework": "vllm_tokenizer_patch", - "modelCount": 6889, + "modelCount": 6892, "officialConfigError": null, "officialConfigValid": true, "successCount": 75, - "successRate": 0.010886921178690665, - "wilsonLowerBound": 0.008694589504160381 + "successRate": 0.010882182240278584, + "wilsonLowerBound": 0.00869080114139639 } }, "Cambricon_mlu-370-x4": { "vllm": { "framework": "vllm", - "modelCount": 26438, + "modelCount": 26440, "officialConfigError": null, "officialConfigValid": true, "successCount": 3249, - "successRate": 0.1228912928360693, - "wilsonLowerBound": 0.11898841531930271 + "successRate": 0.12288199697428139, + "wilsonLowerBound": 0.11897939502674176 }, "vllm-customized": { "framework": "vllm-customized", @@ -86,23 +86,23 @@ }, "vllm-mlu": { "framework": "vllm-mlu", - "modelCount": 12803, + "modelCount": 12843, "officialConfigError": null, "officialConfigValid": true, - "successCount": 5281, - "successRate": 0.41248144966023587, - "wilsonLowerBound": 0.40398160818369533 + "successCount": 5292, + "successRate": 0.41205325858444286, + "wilsonLowerBound": 0.40356806663747236 } }, "Cambricon_mlu-370-x8": { "vllm": { "framework": "vllm", - "modelCount": 24435, + "modelCount": 24437, "officialConfigError": null, "officialConfigValid": true, "successCount": 3796, - "successRate": 0.15535093104153877, - "wilsonLowerBound": 0.15086316357720062 + "successRate": 0.15533821663870362, + "wilsonLowerBound": 0.15085078423640036 }, "vllm-customized": { "framework": "vllm-customized", @@ -115,106 +115,106 @@ }, "vllm-mlu": { "framework": "vllm-mlu", - "modelCount": 46444, + "modelCount": 46521, "officialConfigError": null, "officialConfigValid": true, - "successCount": 11572, - "successRate": 0.24916027904573249, - "wilsonLowerBound": 0.24524740578263718 + "successCount": 11582, + "successRate": 0.24896283398895122, + "wilsonLowerBound": 0.2450542402100504 } }, "Iluvatar_bi-100": { "transformers": { "framework": "transformers", - "modelCount": 23535, + "modelCount": 23537, "officialConfigError": null, "officialConfigValid": true, "successCount": 3093, - "successRate": 0.13142128744423198, - "wilsonLowerBound": 0.1271648270960522 + "successRate": 0.1314101202362238, + "wilsonLowerBound": 0.12715399559715393 }, "vllm": { "framework": "vllm", - "modelCount": 86785, + "modelCount": 86787, "officialConfigError": null, "officialConfigValid": true, "successCount": 9764, - "successRate": 0.11250792187590021, - "wilsonLowerBound": 0.11042268813228984 + "successRate": 0.11250532913915678, + "wilsonLowerBound": 0.11042014049167657 }, "vllm-patch-tokenizer": { "framework": "vllm-patch-tokenizer", - "modelCount": 42718, + "modelCount": 42751, "officialConfigError": null, "officialConfigValid": true, - "successCount": 5236, - "successRate": 0.12257128142703311, - "wilsonLowerBound": 0.11949524285426359 + "successCount": 5237, + "successRate": 0.12250005847816425, + "wilsonLowerBound": 0.119425977739279 }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", - "modelCount": 37515, + "modelCount": 37655, "officialConfigError": null, "officialConfigValid": true, - "successCount": 3534, - "successRate": 0.09420231907237105, - "wilsonLowerBound": 0.09128775868903354 + "successCount": 3537, + "successRate": 0.09393174877174346, + "wilsonLowerBound": 0.09102636181874274 } }, "Iluvatar_bi-150": { "llamacpp": { "framework": "llamacpp", - "modelCount": 90109, + "modelCount": 90162, "officialConfigError": null, "officialConfigValid": true, - "successCount": 21842, - "successRate": 0.2423953212220755, - "wilsonLowerBound": 0.2396082915408655 + "successCount": 21858, + "successRate": 0.2424302921408132, + "wilsonLowerBound": 0.2396439397927536 }, "transformers": { "framework": "transformers", - "modelCount": 5371, + "modelCount": 5376, "officialConfigError": null, "officialConfigValid": true, "successCount": 579, - "successRate": 0.10780115434742134, - "wilsonLowerBound": 0.0997855670958526 + "successRate": 0.10770089285714286, + "wilsonLowerBound": 0.09969236203067001 }, "vllm": { "framework": "vllm", - "modelCount": 112739, + "modelCount": 112744, "officialConfigError": null, "officialConfigValid": true, "successCount": 16525, - "successRate": 0.14657749314789026, - "wilsonLowerBound": 0.1445249416624312 + "successRate": 0.14657099269140708, + "wilsonLowerBound": 0.14451852458938483 }, "vllm_0_17_0_corex_4_4_0": { "framework": "vllm_0_17_0_corex_4_4_0", - "modelCount": 19902, + "modelCount": 19944, "officialConfigError": null, "officialConfigValid": true, - "successCount": 3698, - "successRate": 0.18581047130941614, - "wilsonLowerBound": 0.1804674092709296 + "successCount": 3699, + "successRate": 0.18546931407942238, + "wilsonLowerBound": 0.18013570930201453 }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", - "modelCount": 43205, + "modelCount": 43220, "officialConfigError": null, "officialConfigValid": true, - "successCount": 5621, - "successRate": 0.1301006827913436, - "wilsonLowerBound": 0.12696131987585094 + "successCount": 5623, + "successRate": 0.13010180472003702, + "wilsonLowerBound": 0.1269629692050001 }, "vllm_tokenizer_patch": { "framework": "vllm_tokenizer_patch", - "modelCount": 7269, + "modelCount": 7281, "officialConfigError": null, "officialConfigValid": true, - "successCount": 637, - "successRate": 0.08763241161095062, - "wilsonLowerBound": 0.08134795712848727 + "successCount": 639, + "successRate": 0.08776266996291718, + "wilsonLowerBound": 0.0814787962129998 } }, "Iluvatar_mrv-100": { @@ -229,85 +229,85 @@ }, "vllm": { "framework": "vllm", - "modelCount": 32281, + "modelCount": 32305, "officialConfigError": null, "officialConfigValid": true, - "successCount": 6063, - "successRate": 0.1878194603636814, - "wilsonLowerBound": 0.18359601611509577 + "successCount": 6073, + "successRate": 0.18798947531341897, + "wilsonLowerBound": 0.18376608520516255 } }, "Kunlunxin_p-800": { "vllm": { "framework": "vllm", - "modelCount": 61227, + "modelCount": 61232, "officialConfigError": null, "officialConfigValid": true, - "successCount": 12401, - "successRate": 0.20254136247080537, - "wilsonLowerBound": 0.19937663843856054 + "successCount": 12402, + "successRate": 0.20254115495165925, + "wilsonLowerBound": 0.19937656059636483 }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", - "modelCount": 10470, + "modelCount": 10526, "officialConfigError": null, "officialConfigValid": true, - "successCount": 3083, - "successRate": 0.2944603629417383, - "wilsonLowerBound": 0.28580616991767743 + "successCount": 3094, + "successRate": 0.2939388181645449, + "wilsonLowerBound": 0.28531215731205956 }, "vllm_tokenizer_patch": { "framework": "vllm_tokenizer_patch", - "modelCount": 14159, + "modelCount": 14173, "officialConfigError": null, "officialConfigValid": true, - "successCount": 3560, - "successRate": 0.251430185747581, - "wilsonLowerBound": 0.24435223333484743 + "successCount": 3567, + "successRate": 0.2516757214421788, + "wilsonLowerBound": 0.24459885165059186 } }, "MetaX_c-500": { "vllm": { "framework": "vllm", - "modelCount": 63967, + "modelCount": 64007, "officialConfigError": null, "officialConfigValid": true, - "successCount": 17525, - "successRate": 0.2739693904669595, - "wilsonLowerBound": 0.2705267799759555 + "successCount": 17540, + "successRate": 0.27403252769228365, + "wilsonLowerBound": 0.27059073716342863 }, "vllm_tokenizer_patch": { "framework": "vllm_tokenizer_patch", - "modelCount": 241, + "modelCount": 255, "officialConfigError": null, "officialConfigValid": true, - "successCount": 155, - "successRate": 0.6431535269709544, - "wilsonLowerBound": 0.5808570824452765 + "successCount": 163, + "successRate": 0.6392156862745098, + "wilsonLowerBound": 0.5786089057576913 } }, "Mthreads_s4000": { "llamacpp": { "framework": "llamacpp", - "modelCount": 47274, + "modelCount": 47289, "officialConfigError": null, "officialConfigValid": true, - "successCount": 20891, - "successRate": 0.4419131023395524, - "wilsonLowerBound": 0.4374412371417048 + "successCount": 20902, + "successRate": 0.442005540400516, + "wilsonLowerBound": 0.43753427881902085 }, "vllm": { "framework": "vllm", - "modelCount": 37673, + "modelCount": 37712, "officialConfigError": null, "officialConfigValid": true, - "successCount": 3953, - "successRate": 0.10492925968200037, - "wilsonLowerBound": 0.10187474171470277 + "successCount": 3965, + "successRate": 0.10513894781501909, + "wilsonLowerBound": 0.10208324190530232 }, "vllm_tokenizer_patch": { "framework": "vllm_tokenizer_patch", - "modelCount": 773, + "modelCount": 781, "officialConfigError": null, "officialConfigValid": true, "successCount": 0, @@ -336,159 +336,159 @@ }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", - "modelCount": 6424, + "modelCount": 6433, "officialConfigError": null, "officialConfigValid": true, - "successCount": 2775, - "successRate": 0.4319738480697385, - "wilsonLowerBound": 0.41990465208429023 + "successCount": 2779, + "successRate": 0.4319912948857454, + "wilsonLowerBound": 0.4199304422146353 } }, "Vastai_va16": { "vllm": { "framework": "vllm", - "modelCount": 7394, + "modelCount": 7395, "officialConfigError": null, "officialConfigValid": true, "successCount": 241, - "successRate": 0.03259399513118745, - "wilsonLowerBound": 0.028782966020733367 + "successRate": 0.032589587559161595, + "wilsonLowerBound": 0.02877906662631195 }, "vllm_fix_tokenizer": { "framework": "vllm_fix_tokenizer", - "modelCount": 14072, + "modelCount": 14125, "officialConfigError": null, "officialConfigValid": true, - "successCount": 4569, - "successRate": 0.3246873223422399, - "wilsonLowerBound": 0.3169992428851391 + "successCount": 4587, + "successRate": 0.3247433628318584, + "wilsonLowerBound": 0.3170692665129332 } }, "hygon_k100-ai": { "llamacpp": { "framework": "llamacpp", - "modelCount": 27173, + "modelCount": 27181, "officialConfigError": null, "officialConfigValid": true, - "successCount": 13841, - "successRate": 0.5093659146947337, - "wilsonLowerBound": 0.5034209796217549 + "successCount": 13847, + "successRate": 0.5094367388984953, + "wilsonLowerBound": 0.5034926846499258 }, "vllm": { "framework": "vllm", - "modelCount": 64263, + "modelCount": 64294, "officialConfigError": null, "officialConfigValid": true, - "successCount": 6619, - "successRate": 0.10299861506621229, - "wilsonLowerBound": 0.1006721885436488 + "successCount": 6631, + "successRate": 0.10313559585653405, + "wilsonLowerBound": 0.10080833425392248 }, "vllm-patch-tokenizer": { "framework": "vllm-patch-tokenizer", - "modelCount": 12942, + "modelCount": 12946, "officialConfigError": null, "officialConfigValid": true, - "successCount": 1967, - "successRate": 0.15198578272291763, - "wilsonLowerBound": 0.14590384284296412 + "successCount": 1969, + "successRate": 0.152093310675112, + "wilsonLowerBound": 0.14601046860595066 } } } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-09-28T08:55:57.173495+00:00", + "generatedAt": "2026-09-28T09:02:33.955118+00:00", "gpuStats": { "Ascend_910-b4": { "available": true, - "backlogHours": 1310.9323308270675, + "backlogHours": 1301.1492537313434, "canVerify": true, "error": null, "gpu": "Ascend_910-b4", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 2.4696753794328545, - "queueFactor": 0.920204731725834, - "queueWeight": 0.920204731725834, + "qualityFactor": 2.5, + "queueFactor": 0.9254147317065049, + "queueWeight": 0.9254147317065049, "recentSuccess": 53, - "recentSuccessRate": 0.39849624060150374, - "recentTerminal": 133, - "recentWilsonLowerBound": 0.3192652583897698, + "recentSuccessRate": 0.39552238805970147, + "recentTerminal": 134, + "recentWilsonLowerBound": 0.3167537760660782, "running": 8, - "selectionWeight": 2.2726069699809073, + "selectionWeight": 2.3135368292662624, "stale": false, "submissionEligible": true, - "throughputPerHour": 22.166666666666668, + "throughputPerHour": 22.333333333333332, "waiting": 29059 }, "Biren_166m": { "available": true, - "backlogHours": 118.76855895196508, + "backlogHours": 115.71063829787235, "canVerify": true, "error": null, "gpu": "Biren_166m", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 0.16501834526800918, + "qualityFactor": 0.16041248746569292, "queueFactor": 1.3, "queueWeight": 1.3, "recentSuccess": 30, - "recentSuccessRate": 0.13100436681222707, - "recentTerminal": 229, - "recentWilsonLowerBound": 0.0933279709685841, + "recentSuccessRate": 0.1276595744680851, + "recentTerminal": 235, + "recentWilsonLowerBound": 0.09090433685484224, "running": 8, - "selectionWeight": 0.21452384884841194, + "selectionWeight": 0.2085362337054008, "stale": false, "submissionEligible": false, - "throughputPerHour": 38.166666666666664, - "waiting": 4533 + "throughputPerHour": 39.166666666666664, + "waiting": 4532 }, "Cambricon_mlu-370-x4": { "available": true, - "backlogHours": 1191.3076923076924, + "backlogHours": 1206.7012987012986, "canVerify": true, "error": null, "gpu": "Cambricon_mlu-370-x4", "healthFactor": 1.0, "maxConcurrentTasks": 7, - "qualityFactor": 0.47737603385453053, - "queueFactor": 0.9335077145757795, - "queueWeight": 0.9335077145757795, + "qualityFactor": 0.5064231188062643, + "queueFactor": 0.935934614112673, + "queueWeight": 0.935934614112673, "recentSuccess": 18, - "recentSuccessRate": 0.23076923076923078, - "recentTerminal": 78, - "recentWilsonLowerBound": 0.15125388693827768, - "running": 8, - "selectionWeight": 0.44563421035679274, + "recentSuccessRate": 0.23376623376623376, + "recentTerminal": 77, + "recentWilsonLowerBound": 0.1532949838383708, + "running": 7, + "selectionWeight": 0.47397892627767735, "stale": false, "submissionEligible": true, - "throughputPerHour": 13.0, - "waiting": 15487 + "throughputPerHour": 12.833333333333334, + "waiting": 15486 }, "Cambricon_mlu-370-x8": { "available": true, - "backlogHours": 542.2424242424242, + "backlogHours": 497.05555555555554, "canVerify": true, "error": null, "gpu": "Cambricon_mlu-370-x8", "healthFactor": 1.0, "maxConcurrentTasks": 7, - "qualityFactor": 0.7522001182833639, - "queueFactor": 1.0504913466320005, - "queueWeight": 1.0504913466320005, - "recentSuccess": 26, - "recentSuccessRate": 0.26262626262626265, - "recentTerminal": 99, - "recentWilsonLowerBound": 0.18598028163201125, + "qualityFactor": 0.7024519025862277, + "queueFactor": 1.06911577201543, + "queueWeight": 1.06911577201543, + "recentSuccess": 27, + "recentSuccessRate": 0.25, + "recentTerminal": 108, + "recentWilsonLowerBound": 0.17787718518702555, "running": 7, - "selectionWeight": 0.790179715192241, + "selectionWeight": 0.7510024081371824, "stale": false, "submissionEligible": true, - "throughputPerHour": 16.5, + "throughputPerHour": 18.0, "waiting": 8947 }, "Iluvatar_bi-100": { "available": true, - "backlogHours": 28.261802575107293, + "backlogHours": 28.577586206896555, "canVerify": true, "error": null, "gpu": "Iluvatar_bi-100", @@ -497,197 +497,197 @@ "qualityFactor": 0.05, "queueFactor": 1.3, "queueWeight": 1.3, - "recentSuccess": 26, - "recentSuccessRate": 0.055793991416309016, - "recentTerminal": 466, - "recentWilsonLowerBound": 0.03835631404667277, + "recentSuccess": 25, + "recentSuccessRate": 0.05387931034482758, + "recentTerminal": 464, + "recentWilsonLowerBound": 0.03675788006483595, "running": 24, "selectionWeight": 0.065, "stale": false, "submissionEligible": false, - "throughputPerHour": 77.66666666666667, - "waiting": 2195 + "throughputPerHour": 77.33333333333333, + "waiting": 2210 }, "Iluvatar_bi-150": { "available": true, - "backlogHours": 99.42857142857143, + "backlogHours": 104.64583333333333, "canVerify": true, "error": null, "gpu": "Iluvatar_bi-150", "healthFactor": 1.0, "maxConcurrentTasks": 50, - "qualityFactor": 0.33252051368620966, + "qualityFactor": 0.37816362925507174, "queueFactor": 1.3, "queueWeight": 1.3, "recentSuccess": 50, - "recentSuccessRate": 0.16611295681063123, - "recentTerminal": 301, - "recentWilsonLowerBound": 0.1283286837630807, - "running": 7, - "selectionWeight": 0.4322766677920726, + "recentSuccessRate": 0.1736111111111111, + "recentTerminal": 288, + "recentWilsonLowerBound": 0.1342382346121869, + "running": 4, + "selectionWeight": 0.4916127180315933, "stale": false, "submissionEligible": false, - "throughputPerHour": 50.166666666666664, - "waiting": 4988 + "throughputPerHour": 48.0, + "waiting": 5023 }, "Iluvatar_mrv-100": { "available": true, - "backlogHours": 2439.75, + "backlogHours": 2439.15, "canVerify": true, "error": null, "gpu": "Iluvatar_mrv-100", "healthFactor": 1.0, "maxConcurrentTasks": 2, - "qualityFactor": 0.8908236977924627, - "queueFactor": 0.8383390656231103, - "queueWeight": 0.8383390656231103, + "qualityFactor": 0.9175665930816584, + "queueFactor": 0.8421698704125342, + "queueWeight": 0.8421698704125342, "recentSuccess": 13, "recentSuccessRate": 0.325, "recentTerminal": 40, "recentWilsonLowerBound": 0.20084316962661727, "running": 2, - "selectionWeight": 0.7468123064422573, + "selectionWeight": 0.7727469387904508, "stale": false, "submissionEligible": true, "throughputPerHour": 6.666666666666667, - "waiting": 16265 + "waiting": 16261 }, "Kunlunxin_p-800": { "available": true, - "backlogHours": 389.3469387755102, + "backlogHours": 386.47297297297297, "canVerify": true, "error": null, "gpu": "Kunlunxin_p-800", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 0.33872764329827976, - "queueFactor": 1.1040048685301478, - "queueWeight": 1.1040048685301478, + "qualityFactor": 0.343596077685184, + "queueFactor": 1.1102418839940094, + "queueWeight": 1.1102418839940094, "recentSuccess": 27, - "recentSuccessRate": 0.1836734693877551, - "recentTerminal": 147, - "recentWilsonLowerBound": 0.12941205654415947, + "recentSuccessRate": 0.18243243243243243, + "recentTerminal": 148, + "recentWilsonLowerBound": 0.12851469675493063, "running": 8, - "selectionWeight": 0.37395696730704414, + "selectionWeight": 0.3814747566221507, "stale": false, "submissionEligible": false, - "throughputPerHour": 24.5, - "waiting": 9539 + "throughputPerHour": 24.666666666666668, + "waiting": 9533 }, "MetaX_c-500": { "available": true, - "backlogHours": 748.4285714285714, + "backlogHours": 776.074074074074, "canVerify": true, "error": null, "gpu": "MetaX_c-500", "healthFactor": 1.0, "maxConcurrentTasks": 4, - "qualityFactor": 1.0974411420929435, - "queueFactor": 1.0009190371880254, - "queueWeight": 1.0009190371880254, - "recentSuccess": 26, - "recentSuccessRate": 0.30952380952380953, - "recentTerminal": 84, - "recentWilsonLowerBound": 0.22081781137605916, + "qualityFactor": 0.990182867800329, + "queueFactor": 1.0, + "queueWeight": 1.0, + "recentSuccess": 24, + "recentSuccessRate": 0.2962962962962963, + "recentTerminal": 81, + "recentWilsonLowerBound": 0.207918166563683, "running": 4, - "selectionWeight": 1.098449731314196, + "selectionWeight": 0.990182867800329, "stale": false, "submissionEligible": true, - "throughputPerHour": 14.0, - "waiting": 10478 + "throughputPerHour": 13.5, + "waiting": 10477 }, "Mthreads_s4000": { "available": true, - "backlogHours": 1978.5671641791046, + "backlogHours": 2039.4461538461537, "canVerify": true, "error": null, "gpu": "Mthreads_s4000", "healthFactor": 1.0, "maxConcurrentTasks": 4, - "qualityFactor": 2.5, - "queueFactor": 0.8651051226098867, - "queueWeight": 0.8651051226098867, - "recentSuccess": 29, - "recentSuccessRate": 0.43283582089552236, - "recentTerminal": 67, - "recentWilsonLowerBound": 0.32104123341736546, + "qualityFactor": 2.27728654630456, + "queueFactor": 0.8650847173366992, + "queueWeight": 0.8650847173366992, + "recentSuccess": 27, + "recentSuccessRate": 0.4153846153846154, + "recentTerminal": 65, + "recentWilsonLowerBound": 0.3036005547380231, "running": 4, - "selectionWeight": 2.1627628065247166, + "selectionWeight": 1.9700457882045483, "stale": false, "submissionEligible": true, - "throughputPerHour": 11.166666666666666, + "throughputPerHour": 10.833333333333334, "waiting": 22094 }, "Sunrise_pt-200-x1": { "available": true, - "backlogHours": 2749.459459459459, + "backlogHours": 2906.4, "canVerify": true, "error": null, "gpu": "Sunrise_pt-200-x1", "healthFactor": 1.0, "maxConcurrentTasks": 2, - "qualityFactor": 0.25559622347892824, - "queueFactor": 0.8234446366201926, - "queueWeight": 0.8234446366201926, - "recentSuccess": 8, - "recentSuccessRate": 0.21621621621621623, - "recentTerminal": 37, - "recentWilsonLowerBound": 0.11386376851955585, + "qualityFactor": 0.19970407070904983, + "queueFactor": 0.8203178627385829, + "queueWeight": 0.8203178627385829, + "recentSuccess": 7, + "recentSuccessRate": 0.2, + "recentTerminal": 35, + "recentWilsonLowerBound": 0.10042319445900805, "running": 2, - "selectionWeight": 0.21046933936409962, + "selectionWeight": 0.1638208164642426, "stale": false, "submissionEligible": false, - "throughputPerHour": 6.166666666666667, - "waiting": 16955 + "throughputPerHour": 5.833333333333333, + "waiting": 16954 }, "Vastai_va16": { "available": true, - "backlogHours": 753.0260869565217, + "backlogHours": 773.25, "canVerify": true, "error": null, "gpu": "Vastai_va16", "healthFactor": 1.0, "maxConcurrentTasks": 16, - "qualityFactor": 0.4812245624720861, - "queueFactor": 1.0, - "queueWeight": 1.0, - "recentSuccess": 25, - "recentSuccessRate": 0.21739130434782608, - "recentTerminal": 115, - "recentWilsonLowerBound": 0.15180693897797626, + "qualityFactor": 0.6465202663420805, + "queueFactor": 1.0005469835925072, + "queueWeight": 1.0005469835925072, + "recentSuccess": 27, + "recentSuccessRate": 0.24107142857142858, + "recentTerminal": 112, + "recentWilsonLowerBound": 0.17129352746057167, "running": 16, - "selectionWeight": 0.4812245624720861, + "selectionWeight": 0.646873902319993, "stale": false, "submissionEligible": true, - "throughputPerHour": 19.166666666666668, - "waiting": 14433 + "throughputPerHour": 18.666666666666668, + "waiting": 14434 }, "hygon_k100-ai": { "available": true, - "backlogHours": 830.8181818181819, + "backlogHours": 824.6616541353383, "canVerify": true, "error": null, "gpu": "hygon_k100-ai", "healthFactor": 1.0, "maxConcurrentTasks": 6, - "qualityFactor": 0.43209517695863775, - "queueFactor": 0.9853615337758047, - "queueWeight": 0.9853615337758047, - "recentSuccess": 27, - "recentSuccessRate": 0.20454545454545456, - "recentTerminal": 132, - "recentWilsonLowerBound": 0.14455505203887561, - "running": 7, - "selectionWeight": 0.42576996630509106, + "qualityFactor": 0.4818179765245765, + "queueFactor": 0.9909325771671088, + "queueWeight": 0.9909325771671088, + "recentSuccess": 28, + "recentSuccessRate": 0.21052631578947367, + "recentTerminal": 133, + "recentWilsonLowerBound": 0.14986350566500917, + "running": 6, + "selectionWeight": 0.4774491292029401, "stale": false, "submissionEligible": false, - "throughputPerHour": 22.0, - "waiting": 18278 + "throughputPerHour": 22.166666666666668, + "waiting": 18280 } }, - "queueAttemptedAt": "2026-09-28T08:49:43.359509+00:00", + "queueAttemptedAt": "2026-09-28T09:02:33.955118+00:00", "queueError": null, - "queueUpdatedAt": "2026-09-28T08:49:43.359509+00:00", + "queueUpdatedAt": "2026-09-28T09:02:33.955118+00:00", "supportedGpus": [ "Vastai_va16", "Cambricon_mlu-370-x4", diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index 0531d4f054..4b3558bf74 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-09-28T08:55:57.173495+00:00", + "catalogUpdatedAt": "2026-09-28T09:02:33.955118+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-09-28T08:55:57.173495+00:00", + "generatedAt": "2026-09-28T09:02:33.955118+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6556,6 +6556,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-09-28T08:55:57.173495+00:00", + "taskTreeUpdatedAt": "2026-09-28T09:02:33.955118+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 6dd686f51a..48951ed413 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-09-28T06:26:41.614385+00:00", - "lastSyncTime": "2026-09-28T06:26:41.357416+00:00", + "generatedAt": "2026-09-28T08:59:35.309297+00:00", + "lastSyncTime": "2026-09-28T08:59:35.046906+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -3585,18 +3585,18 @@ "unresolvedFailureCount": 17 }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation": { - "attributableFailureCount": 25, + "attributableFailureCount": 26, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, - "decisionTotal": 25, + "decisionTotal": 26, "failureBreakdown": { "ambiguous_runtime": 97, - "framework_architecture_unsupported": 24, + "framework_architecture_unsupported": 25, "platform_infrastructure": 1, "repository_structure": 1, "参数/模板问题": 6 }, - "failureCount": 129, + "failureCount": 130, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "pendingCount": 0, @@ -3606,7 +3606,7 @@ "successRate": 0.0, "targetGpu": "Ascend_910-b4", "taskType": "text-generation", - "total": 129, + "total": 130, "unresolvedFailureCount": 103 }, "Ascend_910-b4|vllm|text-generation": { @@ -6125,15 +6125,15 @@ "unresolvedFailureCount": 333 }, "vllm_tokenizer_patch": { - "attributableFailureCount": 128, - "decisionFailureRate": 0.9343, - "decisionSuccessRate": 0.0657, - "decisionTotal": 137, + "attributableFailureCount": 129, + "decisionFailureRate": 0.9348, + "decisionSuccessRate": 0.0652, + "decisionTotal": 138, "failureBreakdown": { "ambiguous_runtime": 168, "backend_operator": 15, "context_length": 4, - "framework_architecture_unsupported": 76, + "framework_architecture_unsupported": 77, "memory_capacity": 2, "model_load": 23, "platform_infrastructure": 2, @@ -6142,18 +6142,18 @@ "tokenizer_compatibility": 2, "参数/模板问题": 29 }, - "failureCount": 327, - "failureRate": 0.9732, + "failureCount": 328, + "failureRate": 0.9733, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 9, - "successRate": 0.0268, - "total": 336, + "successRate": 0.0267, + "total": 337, "unresolvedFailureCount": 197 } }, - "generatedAt": "2026-09-28T06:26:41.601640+00:00", + "generatedAt": "2026-09-28T08:59:35.295775+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 102, @@ -6182,14 +6182,14 @@ "unresolvedFailureCount": 192 }, "Ascend_910-b4": { - "attributableFailureCount": 323, - "decisionFailureRate": 0.8346, - "decisionSuccessRate": 0.1654, - "decisionTotal": 387, + "attributableFailureCount": 324, + "decisionFailureRate": 0.8351, + "decisionSuccessRate": 0.1649, + "decisionTotal": 388, "failureBreakdown": { "ambiguous_runtime": 247, "context_length": 1, - "framework_architecture_unsupported": 179, + "framework_architecture_unsupported": 180, "memory_capacity": 19, "model_load": 85, "platform_infrastructure": 3, @@ -6199,14 +6199,14 @@ "日志缺失": 14, "验证失败": 175 }, - "failureCount": 1030, - "failureRate": 0.9415, + "failureCount": 1031, + "failureRate": 0.9416, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 3, "successCount": 64, - "successRate": 0.0585, - "total": 1094, + "successRate": 0.0584, + "total": 1095, "unresolvedFailureCount": 704 }, "Biren_166m": { @@ -8479,6 +8479,29 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "framework_architecture_unsupported": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "modelType": "spark2_5", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|fp8": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -29779,6 +29802,30 @@ "total": 1, "unresolvedFailureCount": 1 }, + "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|compressed-tensors|32": { + "attributableFailureCount": 1, + "decisionFailureRate": 1.0, + "decisionSuccessRate": 0.0, + "decisionTotal": 1, + "failureBreakdown": { + "framework_architecture_unsupported": 1 + }, + "failureCount": 1, + "failureRate": 1.0, + "framework": "vllm_tokenizer_patch", + "loadSizeLog2Bucket": 32, + "modelType": "spark2_5", + "pendingCount": 0, + "pendingRate": 0.0, + "platformFailureCount": 0, + "quantizationMethod": "compressed-tensors", + "successCount": 0, + "successRate": 0.0, + "targetGpu": "Ascend_910-b4", + "taskType": "text-generation", + "total": 1, + "unresolvedFailureCount": 0 + }, "Ascend_910-b4|vllm_tokenizer_patch|text-generation|spark2_5|fp8|32": { "attributableFailureCount": 1, "decisionFailureRate": 1.0, @@ -51666,20 +51713,20 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 17074, - "totalRecords": 17295, + "terminalRecords": 17075, + "totalRecords": 17296, "totals": { - "attributableFailureCount": 6121, + "attributableFailureCount": 6122, "decisionFailureRate": 0.8637, "decisionSuccessRate": 0.1363, - "decisionTotal": 7087, + "decisionTotal": 7088, "failureBreakdown": { "ambiguous_runtime": 4426, "architecture_compatibility": 212, "attention_backend": 3, "backend_operator": 128, "context_length": 322, - "framework_architecture_unsupported": 2177, + "framework_architecture_unsupported": 2178, "memory_capacity": 1206, "model_load": 550, "platform_infrastructure": 938, @@ -51690,72 +51737,72 @@ "日志缺失": 719, "验证失败": 676 }, - "failureCount": 16108, + "failureCount": 16109, "failureRate": 0.9434, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 938, "successCount": 966, "successRate": 0.0566, - "total": 17074, + "total": 17075, "unresolvedFailureCount": 9049 }, "warnings": [ - "GPU Iluvatar_mrv-100 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Cambricon_mlu-370-x8 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 Cambricon_mlu-370-x4 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 Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Biren_166m 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 Ascend_910-b4 本地统计失败率偏高（≥50%），建议重点关注。", "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Iluvatar_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Sunrise_pt-200-x1 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_bi-100 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Cambricon_mlu-370-x8 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。", - "组合 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Ascend_910-b3|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|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 MetaX_c-500|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|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-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 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 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|vllm_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 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 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 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 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 Biren_166m|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 Iluvatar_mrv-100|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 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 Cambricon_mlu-370-x4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 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 Vastai_va16|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_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-100|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|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|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-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-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Cambricon_mlu-370-x4|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 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Biren_166m|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 hygon_k100-ai|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-150|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|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 Cambricon_mlu-370-x8|vllm-customized|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", "组合 Kunlunxin_p-800|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" + "组合 Ascend_910-b4|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_mrv-100|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 MetaX_c-500|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Ascend_910-b4|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-150|vllm_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 MetaX_c-500|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 Mthreads_s4000|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 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-x4|unknown|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Ascend_910-b3|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-150|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Sunrise_pt-200-x1|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Ascend_910-b4|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 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 Iluvatar_bi-150|llamacpp|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Vastai_va16|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_mrv-100|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 Mthreads_s4000|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-100|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-150|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Iluvatar_bi-150|vllm|visual-multi-modal 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x4|vllm-mlu|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Sunrise_pt-200-x1|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 Cambricon_mlu-370-x4|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 Ascend_910-b3|vllm_tokenizer_patch|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 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 Kunlunxin_p-800|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。" ] }, "storageMode": "decision_state_only", - "summarizedRecords": 17295, + "summarizedRecords": 17296, "version": 1 } diff --git a/.modelhub_state/queue_cleanup_latest.json b/.modelhub_state/queue_cleanup_latest.json index c0dc1a86a3..be961102e9 100644 --- a/.modelhub_state/queue_cleanup_latest.json +++ b/.modelhub_state/queue_cleanup_latest.json @@ -14,7 +14,7 @@ 100 ], "accounts": 12, - "activeScanned": 927, + "activeScanned": 930, "ageCleanupMode": "admission_only", "agePolicySkipped": { "cleanupDisabled": true, @@ -126,7 +126,7 @@ "frameworkCatalogUnknown": 0, "frameworkContextUnknown": 51, "modelArchitectureUnknown": 145, - "noMatchingBlock": 764, + "noMatchingBlock": 767, "partiallyBlockedFrameworkSet": 18, "runningMatchedProtected": 0, "submissionContextMismatch": 0, @@ -169,12 +169,12 @@ "repositorySizeErrors": { "empero-ai/Qwen3.8-9B-GGUF": "recursive_repository_size_incomplete" }, - "repositorySizesComplete": 345, + "repositorySizesComplete": 346, "skipped": { - "fitsKnownCapacity": 925, + "fitsKnownCapacity": 928, "gpuCapacityUnknown": 0, "repositorySizeUnknown": 2 }, "stopErrors": [], - "uniqueModels": 346 + "uniqueModels": 347 } diff --git a/manifest.json b/manifest.json index cdd13afd5b..8717036f29 100644 --- a/manifest.json +++ b/manifest.json @@ -2,12 +2,12 @@ "agentVersion": "2026.09.22.1", "checksums": { ".modelhub_state/account_capacity.json": "930f9869793c3d1aa071c53f05b7cf82a4e372f002be88361d6d6189e27c12a1", - ".modelhub_state/architecture_compatibility_blacklist.json": "dba6ea62190fc130d50b7fafebf90c0ded2a076d573764663c827badb7ceee7d", + ".modelhub_state/architecture_compatibility_blacklist.json": "e8dae18f757ace6b00f9ce299b649ddc82be03c7159de242efcbb4801d455adf", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "2176f1de3bb0d68ce69db02c66be4f50355136ddf84d4cc5382168120821dec0", - ".modelhub_state/official_capabilities.json": "0f09ba8ba1fa86b2e5192676a77319d7819481aaa5cb830ee5d598b151901447", - ".modelhub_state/outcome_checkpoint.json": "e4d4d8f12d3ecd452d2c61b377ba4d3ff3a6e0deced0110bc33d92502fa4d3ed", - ".modelhub_state/queue_cleanup_latest.json": "e557ed3dc713e441b689ce8cc7bdc2b4e6f41ed1f75f2750fab491d148312d32", + ".modelhub_state/market_intelligence.json": "fa0cf257e64c979c71f8d6f41b65b810b8eb97145ed145e6632b9943066d7638", + ".modelhub_state/official_capabilities.json": "bda8e3b466bcc3b00aff8a82a08c3621d9e145295e9a3b06ad464bbfe5ae8227", + ".modelhub_state/outcome_checkpoint.json": "28ce04eae302c67f68911effa55ece3f3d743d7006947cb6bb75f99bb3c3790e", + ".modelhub_state/queue_cleanup_latest.json": "f07dbfca00cbe695c81b0b78ae715d619ca73c708b3ceede44a58a76a37c7136", ".modelhub_state/recent_outcomes.jsonl": "1dbde9c4996b0dbc395b2b06ede89ee01d228323012054151eb598a3995b826e", ".modelhub_state/recovery_active_tasks.jsonl": "6bb2dbe964cb27b3ad0d096cedd699ae32c3ec92d68a27c60126b3f54f297593", ".modelhub_state/recovery_intents.jsonl": "701766394fbcef5d75a65e79a280a1331a3be9747c42edf4fc8b7af204b26a5b", @@ -15,11 +15,11 @@ ".modelhub_state/submission_exclusions.jsonl": "2cd0731cd4d31bc6d844f4f0a1e510e2fc839ca66f2ce07d2664110b33374799", ".modelhub_state/worker_crashes.jsonl": "05bcde79076023fd20785b8270312f776430b95a2d4322ee53ef24e354c39f06", "ledger/submissions.jsonl": "ee1f9160177e4749089827c6d3c3107294d28dfffd901fbbc3d0e6ba87bc4f55", - "outcomes/submissions.jsonl": "9810562b6ece59e52da1fd7cb935022b79013888fdd2c33549dbe18bcdbf575e" + "outcomes/submissions.jsonl": "3bd98bc03e90ec5e15d899b51b70b6c9464362a51dbffd8754c063e5fba1c2ae" }, - "generation": 17816, - "phase": "startup", + "generation": 17817, + "phase": "cycle", "schemaVersion": 1, - "updatedAt": "2026-09-28T08:59:33.603999+00:00", + "updatedAt": "2026-09-28T09:03:59.554804+00:00", "writerId": "9d958b95ce4146c9939da0f14b9201ff" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 43c1dc8502..4d79314879 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -122,7 +122,6 @@ {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-13T01:55:03.245431+00:00", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "1e79b01d449f51953bad4aed5c8fa69cb99c8886275d952e7bc8585bd98fa275", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2405581632, "estimatedRequiredGiB": 17.589, "gpuMemoryEvidence": {"memoryGiB": 48.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 48.0, "maximumRepositorySizeGiB": 40.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 15737975890, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark-x2.5", "custom_tag:long-context", "custom_tag:1m-context", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15737975890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-12T17:53:40.152278+00:00", "targetGpu": "Mthreads_s4000", "taskId": "4805869", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": "2026-09-13T12:45:24.349519+00:00", "modelId": "cloudlnk/Spark-X2.5-4B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "79ee05d2f9945abf429c945f84a314444c4004617b3dd41343d3404019c31d6c", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2405581632, "estimatedRequiredGiB": 17.589, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "modelhub_preflight_oom:24"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 15737975890, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4112079360, "modelscopeTags": ["license:apache-2.0", "library:gguf", "task:text-generation", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:spark-x2.5", "custom_tag:long-context", "custom_tag:1m-context", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 15737975890}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T04:41:29.954503+00:00", "targetGpu": "Iluvatar_bi-150", "taskId": "4817350", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-13T13:00:14.407763+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T04:51:53.062775+00:00", "targetGpu": "Ascend_910-b3", "taskId": "4817454", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-13T13:17:31.149592+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:10:44.864092+00:00", "targetGpu": "Ascend_910-b4", "taskId": "4817675", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-13T13:34:15.409837+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:29:18.044774+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "4817992", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-09-13T13:43:30.144236+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "71d6e16091ba0289f01acffc8e39bb8c25703488dc49b9e390e08951fe1f2b33", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T05:34:18.006195+00:00", "targetGpu": "Iluvatar_mrv-100", "taskId": "4818284", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-09-13T14:08:03.641274+00:00", "modelId": "XHToken/Spark-X2.5-4B-INT8", "modelProfile": {"architectures": ["Spark2_5ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 4454282952, "estimatedRequiredGiB": 4.995, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "spark2_5", "modelscopeFileSize": 4469587176, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:spark2_5", "library:safetensors", "library:", "task:text-generation", "custom_tag:llm", "custom_tag:sparkx2_5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 4469587176}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-13T06:03:08.407319+00:00", "targetGpu": "hygon_k100-ai", "taskId": "4819935", "taskType": "text-generation", "verifyResult": null}