From 53c48e51cf2649b17177f165b5813c598e4435a6 Mon Sep 17 00:00:00 2001 From: CoolBoy <2269097679@qq.com> Date: Sat, 24 Oct 2026 08:34:56 +0000 Subject: [PATCH] state: generation 33360 (intent) --- .../architecture_compatibility_blacklist.json | 2 +- .modelhub_state/market_intelligence.json | 296 ++++++------- .modelhub_state/official_capabilities.json | 6 +- .modelhub_state/outcome_checkpoint.json | 388 ++++++++---------- .modelhub_state/recent_outcomes.jsonl | 4 +- .modelhub_state/recovery_intents.jsonl | 12 + manifest.json | 20 +- outcomes/submissions.jsonl | 12 +- 8 files changed, 352 insertions(+), 388 deletions(-) diff --git a/.modelhub_state/architecture_compatibility_blacklist.json b/.modelhub_state/architecture_compatibility_blacklist.json index b08a06cde2..ec2aa2cfd0 100644 --- a/.modelhub_state/architecture_compatibility_blacklist.json +++ b/.modelhub_state/architecture_compatibility_blacklist.json @@ -485,7 +485,7 @@ "taskType": "text-generation" } }, - "generatedAt": "2026-10-24T08:33:17.457541+00:00", + "generatedAt": "2026-10-24T08:34:54.661316+00:00", "summary": { "activeBlockCount": 24, "byGpuFramework": { diff --git a/.modelhub_state/market_intelligence.json b/.modelhub_state/market_intelligence.json index 561f1d886b..e8cb2ebe71 100644 --- a/.modelhub_state/market_intelligence.json +++ b/.modelhub_state/market_intelligence.json @@ -452,320 +452,320 @@ } }, "frameworkUpdatedAt": null, - "generatedAt": "2026-10-24T08:33:17.555845+00:00", + "generatedAt": "2026-10-24T08:34:54.757376+00:00", "gpuStats": { "Ascend_910-b3": { "available": true, - "backlogHours": 1142.6712328767123, + "backlogHours": 1105.0728476821191, "canVerify": true, "error": null, "gpu": "Ascend_910-b3", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 0.9435663403043747, - "queueFactor": 0.9698400551777764, - "queueWeight": 0.9698400551777764, - "recentSuccess": 35, - "recentSuccessRate": 0.23972602739726026, - "recentTerminal": 146, - "recentWilsonLowerBound": 0.1777170167737743, + "qualityFactor": 1.1076340879919553, + "queueFactor": 0.9729138782583919, + "queueWeight": 0.9729138782583919, + "recentSuccess": 37, + "recentSuccessRate": 0.24503311258278146, + "recentTerminal": 151, + "recentWilsonLowerBound": 0.1833173565388925, "running": 8, - "selectionWeight": 0.9151084315446872, + "selectionWeight": 1.07763257623945, "stale": false, "submissionEligible": true, - "throughputPerHour": 24.333333333333332, - "waiting": 27805 + "throughputPerHour": 25.166666666666668, + "waiting": 27811 }, "Ascend_910-b4": { "available": true, - "backlogHours": 1333.6438356164383, + "backlogHours": 1371.4225352112676, "canVerify": true, "error": null, "gpu": "Ascend_910-b4", "healthFactor": 1.0, "maxConcurrentTasks": 8, "qualityFactor": 2.5, - "queueFactor": 0.9476158837696318, - "queueWeight": 0.9476158837696318, - "recentSuccess": 51, - "recentSuccessRate": 0.3493150684931507, - "recentTerminal": 146, - "recentWilsonLowerBound": 0.2767438059072339, - "running": 10, - "selectionWeight": 2.3690397094240794, + "queueFactor": 0.9419055208984024, + "queueWeight": 0.9419055208984024, + "recentSuccess": 48, + "recentSuccessRate": 0.3380281690140845, + "recentTerminal": 142, + "recentWilsonLowerBound": 0.26540265673385566, + "running": 8, + "selectionWeight": 2.354763802246006, "stale": false, "submissionEligible": true, - "throughputPerHour": 24.333333333333332, - "waiting": 32452 + "throughputPerHour": 23.666666666666668, + "waiting": 32457 }, "Biren_166m": { "available": true, - "backlogHours": 140.83870967741936, + "backlogHours": 140.93548387096774, "canVerify": true, "error": null, "gpu": "Biren_166m", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 0.0566352090170211, + "qualityFactor": 0.07417361017328492, "queueFactor": 1.3, "queueWeight": 1.3, - "recentSuccess": 15, - "recentSuccessRate": 0.08064516129032258, + "recentSuccess": 16, + "recentSuccessRate": 0.08602150537634409, "recentTerminal": 186, - "recentWilsonLowerBound": 0.04947857997536768, - "running": 9, - "selectionWeight": 0.07362577172212743, + "recentWilsonLowerBound": 0.05364144294105562, + "running": 8, + "selectionWeight": 0.09642569322527039, "stale": false, - "submissionEligible": false, + "submissionEligible": true, "throughputPerHour": 31.0, - "waiting": 4366 + "waiting": 4369 }, "Cambricon_mlu-370-x4": { "available": true, - "backlogHours": 1672.3384615384614, + "backlogHours": 1698.09375, "canVerify": true, "error": null, "gpu": "Cambricon_mlu-370-x4", "healthFactor": 1.0, "maxConcurrentTasks": 7, - "qualityFactor": 1.3461402658946358, - "queueFactor": 0.9159877892360604, - "queueWeight": 0.9159877892360604, - "recentSuccess": 20, - "recentSuccessRate": 0.3076923076923077, - "recentTerminal": 65, - "recentWilsonLowerBound": 0.20886876704271462, - "running": 10, - "selectionWeight": 1.2330480461584699, + "qualityFactor": 1.3275937651368896, + "queueFactor": 0.9121973057535331, + "queueWeight": 0.9121973057535331, + "recentSuccess": 19, + "recentSuccessRate": 0.296875, + "recentTerminal": 64, + "recentWilsonLowerBound": 0.19904999589075245, + "running": 7, + "selectionWeight": 1.2110274556930596, "stale": false, "submissionEligible": true, - "throughputPerHour": 10.833333333333334, - "waiting": 18117 + "throughputPerHour": 10.666666666666666, + "waiting": 18113 }, "Cambricon_mlu-370-x8": { "available": true, - "backlogHours": 365.8026315789474, + "backlogHours": 370.64, "canVerify": true, "error": null, "gpu": "Cambricon_mlu-370-x8", "healthFactor": 1.0, "maxConcurrentTasks": 7, - "qualityFactor": 0.22257512883158467, - "queueFactor": 1.1505388477859815, - "queueWeight": 1.1505388477859815, - "recentSuccess": 21, - "recentSuccessRate": 0.13815789473684212, - "recentTerminal": 152, - "recentWilsonLowerBound": 0.09217105465530898, + "qualityFactor": 0.22038462914248258, + "queueFactor": 1.146146655974239, + "queueWeight": 1.146146655974239, + "recentSuccess": 20, + "recentSuccessRate": 0.13333333333333333, + "recentTerminal": 150, + "recentWilsonLowerBound": 0.08799732892586416, "running": 7, - "selectionWeight": 0.2560813322717078, + "selectionWeight": 0.2525931057197792, "stale": false, "submissionEligible": true, - "throughputPerHour": 25.333333333333332, - "waiting": 9267 + "throughputPerHour": 25.0, + "waiting": 9266 }, "Iluvatar_bi-100": { "available": true, - "backlogHours": 86.4950495049505, + "backlogHours": 82.73186119873817, "canVerify": true, "error": null, "gpu": "Iluvatar_bi-100", "healthFactor": 1.0, "maxConcurrentTasks": 24, - "qualityFactor": 0.8449769580698208, + "qualityFactor": 0.7422318083310562, "queueFactor": 1.3, "queueWeight": 1.3, - "recentSuccess": 64, - "recentSuccessRate": 0.21122112211221122, - "recentTerminal": 303, - "recentWilsonLowerBound": 0.16902220132009294, - "running": 26, - "selectionWeight": 1.098470045490767, + "recentSuccess": 61, + "recentSuccessRate": 0.19242902208201892, + "recentTerminal": 317, + "recentWilsonLowerBound": 0.15281915367932825, + "running": 24, + "selectionWeight": 0.9649013508303731, "stale": false, "submissionEligible": true, - "throughputPerHour": 50.5, - "waiting": 4368 + "throughputPerHour": 52.833333333333336, + "waiting": 4371 }, "Iluvatar_bi-150": { "available": true, - "backlogHours": 371.3538461538461, + "backlogHours": 338.9577464788732, "canVerify": true, "error": null, "gpu": "Iluvatar_bi-150", "healthFactor": 1.0, "maxConcurrentTasks": 50, "qualityFactor": 0.05, - "queueFactor": 1.1479424657841926, - "queueWeight": 1.1479424657841926, + "queueFactor": 1.161612295070773, + "queueWeight": 1.161612295070773, "recentSuccess": 5, - "recentSuccessRate": 0.038461538461538464, - "recentTerminal": 130, - "recentWilsonLowerBound": 0.01653818245445794, - "running": 25, - "selectionWeight": 0.05739712328920963, + "recentSuccessRate": 0.035211267605633804, + "recentTerminal": 142, + "recentWilsonLowerBound": 0.015131966133144728, + "running": 4, + "selectionWeight": 0.05808061475353865, "stale": false, "submissionEligible": false, - "throughputPerHour": 21.666666666666668, - "waiting": 8046 + "throughputPerHour": 23.666666666666668, + "waiting": 8022 }, "Iluvatar_mrv-100": { "available": true, - "backlogHours": 1962.3673469387757, + "backlogHours": 1962.122448979592, "canVerify": true, "error": null, "gpu": "Iluvatar_mrv-100", "healthFactor": 1.0, "maxConcurrentTasks": 2, - "qualityFactor": 0.9526699074427509, - "queueFactor": 0.8942753597208658, - "queueWeight": 0.8942753597208658, + "qualityFactor": 1.044533233834132, + "queueFactor": 0.8926354260715572, + "queueWeight": 0.8926354260715572, "recentSuccess": 14, "recentSuccessRate": 0.2857142857142857, "recentTerminal": 49, "recentWilsonLowerBound": 0.1784943493972417, "running": 2, - "selectionWeight": 0.85194922417361, + "selectionWeight": 0.9323873682294319, "stale": false, "submissionEligible": true, "throughputPerHour": 8.166666666666666, - "waiting": 16026 + "waiting": 16024 }, "Kunlunxin_p-800": { "available": true, - "backlogHours": 400.33082706766913, + "backlogHours": 406.3969465648855, "canVerify": true, "error": null, "gpu": "Kunlunxin_p-800", "healthFactor": 1.0, "maxConcurrentTasks": 8, - "qualityFactor": 0.2291649467529952, - "queueFactor": 1.1350773455599208, - "queueWeight": 1.1350773455599208, + "qualityFactor": 0.2599719701235536, + "queueFactor": 1.130421656984759, + "queueWeight": 1.130421656984759, "recentSuccess": 19, - "recentSuccessRate": 0.14285714285714285, - "recentTerminal": 133, - "recentWilsonLowerBound": 0.09340160831673865, - "running": 9, - "selectionWeight": 0.2601199394557704, + "recentSuccessRate": 0.1450381679389313, + "recentTerminal": 131, + "recentWilsonLowerBound": 0.09485952711844413, + "running": 8, + "selectionWeight": 0.2938779452366597, "stale": false, "submissionEligible": true, - "throughputPerHour": 22.166666666666668, - "waiting": 8874 + "throughputPerHour": 21.833333333333332, + "waiting": 8873 }, "MetaX_c-500": { "available": true, - "backlogHours": 664.9514563106795, + "backlogHours": 705.9587628865979, "canVerify": true, "error": null, "gpu": "MetaX_c-500", "healthFactor": 1.0, "maxConcurrentTasks": 4, - "qualityFactor": 0.7683586267240747, - "queueFactor": 1.0518887727774076, - "queueWeight": 1.0518887727774076, - "recentSuccess": 24, - "recentSuccessRate": 0.23300970873786409, - "recentTerminal": 103, - "recentWilsonLowerBound": 0.16187497360880485, - "running": 5, - "selectionWeight": 0.8082278129177212, + "qualityFactor": 0.7637467528701039, + "queueFactor": 1.0405576219176138, + "queueWeight": 1.0405576219176138, + "recentSuccess": 22, + "recentSuccessRate": 0.2268041237113402, + "recentTerminal": 97, + "recentWilsonLowerBound": 0.15481698841986685, + "running": 4, + "selectionWeight": 0.7947225049138148, "stale": false, "submissionEligible": true, - "throughputPerHour": 17.166666666666668, - "waiting": 11415 + "throughputPerHour": 16.166666666666668, + "waiting": 11413 }, "Mthreads_s4000": { "available": true, - "backlogHours": 1924.3170731707319, + "backlogHours": 1901.2048192771083, "canVerify": true, "error": null, "gpu": "Mthreads_s4000", "healthFactor": 1.0, "maxConcurrentTasks": 4, - "qualityFactor": 1.0229038093534413, - "queueFactor": 0.8969057660005577, - "queueWeight": 0.8969057660005577, + "qualityFactor": 1.0907629347070718, + "queueFactor": 0.8968683509700356, + "queueWeight": 0.8968683509700356, "recentSuccess": 22, - "recentSuccessRate": 0.2682926829268293, - "recentTerminal": 82, - "recentWilsonLowerBound": 0.18435989365284997, + "recentSuccessRate": 0.26506024096385544, + "recentTerminal": 83, + "recentWilsonLowerBound": 0.18204284443216528, "running": 4, - "selectionWeight": 0.9174483246730367, + "selectionWeight": 0.978270754549968, "stale": false, "submissionEligible": true, - "throughputPerHour": 13.666666666666666, - "waiting": 26299 + "throughputPerHour": 13.833333333333334, + "waiting": 26300 }, "Sunrise_pt-200-x1": { "available": true, - "backlogHours": 2669.4285714285716, + "backlogHours": 2547.9545454545455, "canVerify": true, "error": null, "gpu": "Sunrise_pt-200-x1", "healthFactor": 1.0, "maxConcurrentTasks": 2, - "qualityFactor": 0.11091606021159674, - "queueFactor": 0.8539364767784398, - "queueWeight": 0.8539364767784398, + "qualityFactor": 0.10948946715135936, + "queueFactor": 0.8583299826583709, + "queueWeight": 0.8583299826583709, "recentSuccess": 6, - "recentSuccessRate": 0.14285714285714285, - "recentTerminal": 42, - "recentWilsonLowerBound": 0.06715875684189934, + "recentSuccessRate": 0.13636363636363635, + "recentTerminal": 44, + "recentWilsonLowerBound": 0.06402867407860051, "running": 2, - "selectionWeight": 0.0947152696752362, + "selectionWeight": 0.09397809244130055, "stale": false, "submissionEligible": true, - "throughputPerHour": 7.0, - "waiting": 18686 + "throughputPerHour": 7.333333333333333, + "waiting": 18685 }, "Vastai_va16": { "available": true, - "backlogHours": 720.64, + "backlogHours": 735.3469387755102, "canVerify": true, "error": null, "gpu": "Vastai_va16", "healthFactor": 1.0, "maxConcurrentTasks": 16, - "qualityFactor": 0.4939583621069696, - "queueFactor": 1.0392751817064962, - "queueWeight": 1.0392751817064962, - "recentSuccess": 28, - "recentSuccessRate": 0.18666666666666668, - "recentTerminal": 150, - "recentWilsonLowerBound": 0.13242330549709996, - "running": 18, - "selectionWeight": 0.5133586665341641, + "qualityFactor": 0.6219241622953293, + "queueFactor": 1.0342110922031098, + "queueWeight": 1.0342110922031098, + "recentSuccess": 29, + "recentSuccessRate": 0.19727891156462585, + "recentTerminal": 147, + "recentWilsonLowerBound": 0.1410157852422743, + "running": 16, + "selectionWeight": 0.6432008671549566, "stale": false, "submissionEligible": true, - "throughputPerHour": 25.0, + "throughputPerHour": 24.5, "waiting": 18016 }, "hygon_k100-ai": { "available": true, - "backlogHours": 1256.4915254237287, + "backlogHours": 1267.2820512820513, "canVerify": true, "error": null, "gpu": "hygon_k100-ai", "healthFactor": 1.0, "maxConcurrentTasks": 6, - "qualityFactor": 0.30003762525746636, - "queueFactor": 0.9561243449641801, - "queueWeight": 0.9561243449641801, - "recentSuccess": 19, - "recentSuccessRate": 0.16101694915254236, - "recentTerminal": 118, - "recentWilsonLowerBound": 0.10557198487865982, + "qualityFactor": 0.2893225998253437, + "queueFactor": 0.9531297867558345, + "queueWeight": 0.9531297867558345, + "recentSuccess": 18, + "recentSuccessRate": 0.15384615384615385, + "recentTerminal": 117, + "recentWilsonLowerBound": 0.09958576028690375, "running": 6, - "selectionWeight": 0.28687327791390316, + "selectionWeight": 0.2757619878751735, "stale": false, "submissionEligible": true, - "throughputPerHour": 19.666666666666668, - "waiting": 24711 + "throughputPerHour": 19.5, + "waiting": 24712 } }, - "queueAttemptedAt": "2026-10-24T08:23:26.057211+00:00", + "queueAttemptedAt": "2026-10-24T08:34:54.757376+00:00", "queueError": null, - "queueUpdatedAt": "2026-10-24T08:23:26.057211+00:00", + "queueUpdatedAt": "2026-10-24T08:34:54.757376+00:00", "supportedGpus": [ "Cambricon_mlu-370-x4", "Vastai_va16", diff --git a/.modelhub_state/official_capabilities.json b/.modelhub_state/official_capabilities.json index f51212a5dc..36e09db800 100644 --- a/.modelhub_state/official_capabilities.json +++ b/.modelhub_state/official_capabilities.json @@ -1,5 +1,5 @@ { - "catalogUpdatedAt": "2026-10-24T08:33:17.555845+00:00", + "catalogUpdatedAt": "2026-10-24T08:34:54.757376+00:00", "configuredTaskTypes": [ "text-generation" ], @@ -56,7 +56,7 @@ "time-series-forecasting" ], "errors": [], - "generatedAt": "2026-10-24T08:33:17.555845+00:00", + "generatedAt": "2026-10-24T08:34:54.757376+00:00", "gpuCatalog": { "Ascend_910-b3": { "canVerify": true, @@ -6813,6 +6813,6 @@ "updateTime": "2025-12-22 08:59:53" } ], - "taskTreeUpdatedAt": "2026-10-24T08:33:17.555845+00:00", + "taskTreeUpdatedAt": "2026-10-24T08:34:54.757376+00:00", "version": 1 } diff --git a/.modelhub_state/outcome_checkpoint.json b/.modelhub_state/outcome_checkpoint.json index 8fb352c89d..b27182ef12 100644 --- a/.modelhub_state/outcome_checkpoint.json +++ b/.modelhub_state/outcome_checkpoint.json @@ -1,6 +1,6 @@ { - "generatedAt": "2026-10-23T21:28:24.829744+00:00", - "lastSyncTime": "2026-10-23T21:28:24.747670+00:00", + "generatedAt": "2026-10-24T08:34:54.548913+00:00", + "lastSyncTime": "2026-10-24T08:34:54.442509+00:00", "recentLimit": 300, "report": { "architectureCompatibilityBlocks": { @@ -487,31 +487,10 @@ ], "targetGpu": "Mthreads_s4000", "taskType": "text-generation" - }, - "sunrise_pt-200-x1|vllm_fix_tokenizer|text-generation|architectures:plamo3forcausallm": { - "architectureSignature": "architectures:plamo3forcausallm", - "architectures": [ - "plamo3forcausallm" - ], - "evidenceCount": 1, - "expiresAt": "2026-10-24T01:54:08+00:00", - "framework": "vllm_fix_tokenizer", - "latestFailureAt": "2026-09-24T01:54:08+00:00", - "latestSuccessfulAt": null, - "matchType": "architectures", - "modelType": null, - "sourceModelIds": [ - "pfnet/plamo-3-nict-8b-base" - ], - "sourceTaskIds": [ - "4458019" - ], - "targetGpu": "Sunrise_pt-200-x1", - "taskType": "text-generation" } }, "architectureCompatibilitySummary": { - "activeBlockCount": 25, + "activeBlockCount": 24, "byGpuFramework": { "Ascend_910-b3|vllm": 1, "Ascend_910-b3|vllm_tokenizer_patch": 2, @@ -523,7 +502,6 @@ "MetaX_c-500|vllm": 1, "MetaX_c-500|vllm_tokenizer_patch": 4, "Mthreads_s4000|vllm": 3, - "Sunrise_pt-200-x1|vllm_fix_tokenizer": 1, "hygon_k100-ai|vllm": 1, "hygon_k100-ai|vllm-patch-tokenizer": 2 }, @@ -939,9 +917,9 @@ "failureBreakdown": { "ambiguous_runtime": 155, "memory_capacity": 1, - "参数/模板问题": 6 + "参数/模板问题": 7 }, - "failureCount": 162, + "failureCount": 163, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, @@ -951,8 +929,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 162, - "unresolvedFailureCount": 161 + "total": 163, + "unresolvedFailureCount": 162 }, "Biren_166m|vllm|text-generation": { "attributableFailureCount": 51, @@ -1090,21 +1068,21 @@ "framework_architecture_unsupported": 33, "model_load": 4, "platform_infrastructure": 1, - "参数/模板问题": 5, + "参数/模板问题": 6, "验证失败": 3 }, - "failureCount": 101, - "failureRate": 0.9182, + "failureCount": 102, + "failureRate": 0.9189, "framework": "vllm-mlu", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 9, - "successRate": 0.0818, + "successRate": 0.0811, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", - "total": 110, - "unresolvedFailureCount": 63 + "total": 111, + "unresolvedFailureCount": 64 }, "Cambricon_mlu-370-x4|vllm|text-generation": { "attributableFailureCount": 25, @@ -2171,9 +2149,9 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 198, - "参数/模板问题": 10 + "参数/模板问题": 11 }, - "failureCount": 208, + "failureCount": 209, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "pendingCount": 0, @@ -2183,8 +2161,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 208, - "unresolvedFailureCount": 208 + "total": 209, + "unresolvedFailureCount": 209 }, "Kunlunxin_p-800|vllm_tokenizer_patch|text-generation": { "attributableFailureCount": 61, @@ -2716,9 +2694,9 @@ "repository_structure": 75, "runtime_memory": 1, "tokenizer_compatibility": 182, - "参数/模板问题": 10 + "参数/模板问题": 11 }, - "failureCount": 978, + "failureCount": 979, "failureRate": 0.9889, "framework": "vllm", "pendingCount": 0, @@ -2728,8 +2706,8 @@ "successRate": 0.0111, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 989, - "unresolvedFailureCount": 119 + "total": 990, + "unresolvedFailureCount": 120 }, "Sunrise_pt-200-x1|vllm|unknown": { "attributableFailureCount": 2, @@ -3248,17 +3226,17 @@ "repository_structure": 470, "runtime_memory": 66, "tokenizer_compatibility": 425, - "参数/模板问题": 102 + "参数/模板问题": 103 }, - "failureCount": 6318, + "failureCount": 6319, "failureRate": 0.9827, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 888, "successCount": 111, "successRate": 0.0173, - "total": 6429, - "unresolvedFailureCount": 1712 + "total": 6430, + "unresolvedFailureCount": 1713 }, "vllm-customized": { "attributableFailureCount": 16, @@ -3294,18 +3272,18 @@ "model_load": 7, "platform_infrastructure": 1, "tokenizer_compatibility": 1, - "参数/模板问题": 47, + "参数/模板问题": 48, "验证失败": 3 }, - "failureCount": 228, - "failureRate": 0.912, + "failureCount": 229, + "failureRate": 0.9124, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 22, - "successRate": 0.088, - "total": 250, - "unresolvedFailureCount": 164 + "successRate": 0.0876, + "total": 251, + "unresolvedFailureCount": 165 }, "vllm-patch-tokenizer": { "attributableFailureCount": 69, @@ -3367,17 +3345,17 @@ "model_load": 13, "platform_infrastructure": 36, "tokenizer_compatibility": 99, - "参数/模板问题": 33 + "参数/模板问题": 35 }, - "failureCount": 700, + "failureCount": 702, "failureRate": 0.9901, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 36, "successCount": 7, "successRate": 0.0099, - "total": 707, - "unresolvedFailureCount": 471 + "total": 709, + "unresolvedFailureCount": 473 }, "vllm_tokenizer_patch": { "attributableFailureCount": 177, @@ -3408,7 +3386,7 @@ "unresolvedFailureCount": 341 } }, - "generatedAt": "2026-10-23T21:28:24.813411+00:00", + "generatedAt": "2026-10-24T08:34:54.500489+00:00", "gpuSummaries": { "Ascend_910-b3": { "attributableFailureCount": 133, @@ -3482,19 +3460,19 @@ "repository_structure": 18, "runtime_memory": 2, "tokenizer_compatibility": 8, - "参数/模板问题": 220, + "参数/模板问题": 221, "日志缺失": 62, "验证失败": 27 }, - "failureCount": 804, - "failureRate": 0.9698, + "failureCount": 805, + "failureRate": 0.9699, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 2, "successCount": 25, - "successRate": 0.0302, - "total": 829, - "unresolvedFailureCount": 608 + "successRate": 0.0301, + "total": 830, + "unresolvedFailureCount": 609 }, "Cambricon_mlu-370-x4": { "attributableFailureCount": 771, @@ -3511,19 +3489,19 @@ "platform_infrastructure": 16, "repository_structure": 85, "tokenizer_compatibility": 35, - "参数/模板问题": 315, + "参数/模板问题": 316, "日志缺失": 13, "验证失败": 42 }, - "failureCount": 1677, - "failureRate": 0.9577, + "failureCount": 1678, + "failureRate": 0.9578, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 16, "successCount": 74, - "successRate": 0.0423, - "total": 1751, - "unresolvedFailureCount": 890 + "successRate": 0.0422, + "total": 1752, + "unresolvedFailureCount": 891 }, "Cambricon_mlu-370-x8": { "attributableFailureCount": 72, @@ -3650,19 +3628,19 @@ "repository_structure": 2, "runtime_memory": 3, "tokenizer_compatibility": 1, - "参数/模板问题": 54, + "参数/模板问题": 55, "日志缺失": 1, "验证失败": 23 }, - "failureCount": 465, + "failureCount": 466, "failureRate": 0.9852, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 1, "successCount": 7, "successRate": 0.0148, - "total": 472, - "unresolvedFailureCount": 365 + "total": 473, + "unresolvedFailureCount": 366 }, "Kunlunxin_r-200-8f": { "attributableFailureCount": 0, @@ -3760,18 +3738,18 @@ "repository_structure": 83, "runtime_memory": 1, "tokenizer_compatibility": 284, - "参数/模板问题": 233, + "参数/模板问题": 234, "验证失败": 32 }, - "failureCount": 1489, - "failureRate": 0.9335, + "failureCount": 1490, + "failureRate": 0.9336, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 260, "successCount": 106, - "successRate": 0.0665, - "total": 1595, - "unresolvedFailureCount": 431 + "successRate": 0.0664, + "total": 1596, + "unresolvedFailureCount": 432 }, "Vastai_va16": { "attributableFailureCount": 471, @@ -7838,9 +7816,9 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 19, - "参数/模板问题": 1 + "参数/模板问题": 2 }, - "failureCount": 20, + "failureCount": 21, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", @@ -7852,8 +7830,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 20, - "unresolvedFailureCount": 20 + "total": 21, + "unresolvedFailureCount": 21 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, @@ -9887,10 +9865,10 @@ "decisionTotal": 10, "failureBreakdown": { "framework_architecture_unsupported": 10, - "参数/模板问题": 1, + "参数/模板问题": 2, "验证失败": 1 }, - "failureCount": 12, + "failureCount": 13, "failureRate": 1.0, "framework": "vllm-mlu", "modelType": "qwen3_5", @@ -9902,8 +9880,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", - "total": 12, - "unresolvedFailureCount": 2 + "total": 13, + "unresolvedFailureCount": 3 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_vl|none": { "attributableFailureCount": 0, @@ -17961,9 +17939,9 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 22, - "参数/模板问题": 2 + "参数/模板问题": 3 }, - "failureCount": 24, + "failureCount": 25, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "modelType": "qwen3_5", @@ -17975,8 +17953,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 24, - "unresolvedFailureCount": 24 + "total": 25, + "unresolvedFailureCount": 25 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_moe|none": { "attributableFailureCount": 0, @@ -23010,9 +22988,9 @@ "failureBreakdown": { "framework_architecture_unsupported": 8, "platform_infrastructure": 8, - "参数/模板问题": 1 + "参数/模板问题": 2 }, - "failureCount": 17, + "failureCount": 18, "failureRate": 1.0, "framework": "vllm", "modelType": "qwen3_5", @@ -23024,8 +23002,8 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 17, - "unresolvedFailureCount": 1 + "total": 18, + "unresolvedFailureCount": 2 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3|none": { "attributableFailureCount": 0, @@ -25665,14 +25643,14 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 11, - "参数/模板问题": 4 + "ambiguous_runtime": 10, + "参数/模板问题": 5 }, "failureCount": 15, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastPlatformFailureAt": null, - "lastTerminalAt": "2026-10-06T19:00:42.266417+00:00", + "lastTerminalAt": "2026-10-24T08:34:54.442474+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, @@ -25978,9 +25956,9 @@ "decisionTotal": 2, "failureBreakdown": { "backend_operator": 2, - "参数/模板问题": 5 + "参数/模板问题": 4 }, - "failureCount": 7, + "failureCount": 6, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastPlatformFailureAt": null, @@ -25992,8 +25970,8 @@ "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", - "total": 7, - "unresolvedFailureCount": 5 + "total": 6, + "unresolvedFailureCount": 4 }, "MetaX_c-500|vllm|text-generation": { "attributableFailureCount": 1, @@ -26108,13 +26086,13 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "参数/模板问题": 1 + "参数/模板问题": 2 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm", "lastPlatformFailureAt": null, - "lastTerminalAt": "2026-10-20T12:39:15.571332+00:00", + "lastTerminalAt": "2026-10-24T08:34:54.442493+00:00", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, @@ -26122,8 +26100,8 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 + "total": 2, + "unresolvedFailureCount": 2 }, "Vastai_va16|unknown|text-generation": { "attributableFailureCount": 0, @@ -26406,31 +26384,6 @@ "total": 1, "unresolvedFailureCount": 1 }, - "Biren_166m|vllm_fix_tokenizer|text-generation|gemma4|modelopt": { - "attributableFailureCount": 0, - "consecutiveFailures": 0, - "decisionFailureRate": 0.0, - "decisionSuccessRate": 0.0, - "decisionTotal": 0, - "failureBreakdown": { - "ambiguous_runtime": 1 - }, - "failureCount": 1, - "failureRate": 1.0, - "framework": "vllm_fix_tokenizer", - "lastTerminalAt": "2026-10-21T21:16:24.481190+00:00", - "modelType": "gemma4", - "pendingCount": 0, - "pendingRate": 0.0, - "platformFailureCount": 0, - "quantizationMethod": "modelopt", - "successCount": 0, - "successRate": 0.0, - "targetGpu": "Biren_166m", - "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 - }, "Biren_166m|vllm_fix_tokenizer|text-generation|gpt_oss|none": { "attributableFailureCount": 0, "consecutiveFailures": 0, @@ -26615,12 +26568,12 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 1, - "参数/模板问题": 1 + "参数/模板问题": 2 }, - "failureCount": 2, + "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", - "lastTerminalAt": "2026-10-21T12:34:33.758775+00:00", + "lastTerminalAt": "2026-10-24T08:34:54.442474+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, @@ -26630,8 +26583,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 2, - "unresolvedFailureCount": 2 + "total": 3, + "unresolvedFailureCount": 3 }, "Biren_166m|vllm_fix_tokenizer|text-generation|spark2_5|compressed-tensors": { "attributableFailureCount": 0, @@ -27892,12 +27845,12 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "参数/模板问题": 1 + "参数/模板问题": 2 }, - "failureCount": 1, + "failureCount": 2, "failureRate": 1.0, "framework": "vllm", - "lastTerminalAt": "2026-10-20T12:39:15.571332+00:00", + "lastTerminalAt": "2026-10-24T08:34:54.442493+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, @@ -27907,8 +27860,8 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 1, - "unresolvedFailureCount": 1 + "total": 2, + "unresolvedFailureCount": 2 }, "hygon_k100-ai|vllm-patch-tokenizer|text-generation|cagliostro|none": { "attributableFailureCount": 0, @@ -34734,9 +34687,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": { - "ambiguous_runtime": 10 + "ambiguous_runtime": 10, + "参数/模板问题": 1 }, - "failureCount": 10, + "failureCount": 11, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, @@ -34749,8 +34703,8 @@ "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", - "total": 10, - "unresolvedFailureCount": 10 + "total": 11, + "unresolvedFailureCount": 11 }, "Biren_166m|vllm_fix_tokenizer|text-generation|qwen3_5|none|35": { "attributableFailureCount": 0, @@ -37775,9 +37729,10 @@ "decisionSuccessRate": 0.0, "decisionTotal": 3, "failureBreakdown": { - "framework_architecture_unsupported": 3 + "framework_architecture_unsupported": 3, + "参数/模板问题": 1 }, - "failureCount": 3, + "failureCount": 4, "failureRate": 1.0, "framework": "vllm-mlu", "loadSizeLog2Bucket": 34, @@ -37790,8 +37745,8 @@ "successRate": 0.0, "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation", - "total": 3, - "unresolvedFailureCount": 0 + "total": 4, + "unresolvedFailureCount": 1 }, "Cambricon_mlu-370-x4|vllm-mlu|text-generation|qwen3_vl|none|34": { "attributableFailureCount": 0, @@ -49723,9 +49678,9 @@ "decisionTotal": 0, "failureBreakdown": { "ambiguous_runtime": 10, - "参数/模板问题": 1 + "参数/模板问题": 2 }, - "failureCount": 11, + "failureCount": 12, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "loadSizeLog2Bucket": 34, @@ -49738,8 +49693,8 @@ "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", - "total": 11, - "unresolvedFailureCount": 11 + "total": 12, + "unresolvedFailureCount": 12 }, "Kunlunxin_p-800|vllm_fix_tokenizer|text-generation|qwen3_5|none|35": { "attributableFailureCount": 0, @@ -57386,9 +57341,10 @@ "decisionTotal": 5, "failureBreakdown": { "framework_architecture_unsupported": 5, - "platform_infrastructure": 3 + "platform_infrastructure": 3, + "参数/模板问题": 1 }, - "failureCount": 8, + "failureCount": 9, "failureRate": 1.0, "framework": "vllm", "loadSizeLog2Bucket": 34, @@ -57401,8 +57357,8 @@ "successRate": 0.0, "targetGpu": "Sunrise_pt-200-x1", "taskType": "text-generation", - "total": 8, - "unresolvedFailureCount": 0 + "total": 9, + "unresolvedFailureCount": 1 }, "Sunrise_pt-200-x1|vllm|text-generation|qwen3|none|13": { "attributableFailureCount": 0, @@ -61150,8 +61106,8 @@ "unresolvedFailureCount": 0 } }, - "terminalRecords": 17998, - "totalRecords": 18542, + "terminalRecords": 18002, + "totalRecords": 18546, "totals": { "attributableFailureCount": 6372, "decisionFailureRate": 0.866, @@ -61170,81 +61126,81 @@ "repository_structure": 742, "runtime_memory": 101, "tokenizer_compatibility": 698, - "参数/模板问题": 3600, + "参数/模板问题": 3604, "日志缺失": 719, "验证失败": 676 }, - "failureCount": 17012, + "failureCount": 17016, "failureRate": 0.9452, "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 972, "successCount": 986, "successRate": 0.0548, - "total": 17998, - "unresolvedFailureCount": 9668 + "total": 18002, + "unresolvedFailureCount": 9672 }, "warnings": [ - "GPU Ascend_910-b4 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 MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", - "GPU Iluvatar_bi-100 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 Sunrise_pt-200-x1 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 Biren_166m 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 hygon_k100-ai 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。", - "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 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 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 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|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|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|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 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 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 Iluvatar_bi-150|vllm_0_17_0_corex_4_4_0|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", - "组合 Iluvatar_bi-150|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_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 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 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 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 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|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-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|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_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_mrv-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 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 Ascend_910-b3|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-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 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 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 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 MetaX_c-500|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。", + "GPU Mthreads_s4000 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Iluvatar_bi-150 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU MetaX_c-500 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Sunrise_pt-200-x1 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Kunlunxin_p-800 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU hygon_k100-ai 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Cambricon_mlu-370-x8 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 Ascend_910-b4 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 Vastai_va16 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Biren_166m 本地统计失败率偏高（≥50%），建议重点关注。", + "GPU Ascend_910-b3 本地统计失败率偏高（≥50%），建议重点关注。", "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 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 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 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 Cambricon_mlu-370-x4|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 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 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 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 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 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 Ascend_910-b3|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|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 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 MetaX_c-500|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-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 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 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 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 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 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 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 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 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-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 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|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|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-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 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_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 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 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 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 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-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|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 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 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 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 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-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-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_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 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|transformers|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Cambricon_mlu-370-x8|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 Biren_166m|vllm|text-generation 近期失败集中，建议降低该 GPU+框架的提交优先级。", + "组合 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。" ] }, "storageMode": "decision_state_only", - "summarizedRecords": 18542, + "summarizedRecords": 18546, "version": 1 } diff --git a/.modelhub_state/recent_outcomes.jsonl b/.modelhub_state/recent_outcomes.jsonl index 04c3b62979..2143b8df06 100644 --- a/.modelhub_state/recent_outcomes.jsonl +++ b/.modelhub_state/recent_outcomes.jsonl @@ -15,6 +15,7 @@ {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "missing_structured_error_code", "failureCode": null, "failureDetectedFramework": "llamacpp", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "llamacpp", "lastSyncTime": "2026-10-16T08:44:58.249327+00:00", "modelId": "DavidAU/DarkSapling-V2-Ultra-Quality-7B-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "a7159961e1848fd33948f09e6020f02399009945e81bc356b0f9fcd8e43bdd29", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8080881376, "estimatedRequiredGiB": 55.473, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 49636846090, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:creative", "custom_tag:story", "custom_tag:roleplay", "custom_tag:rp", "custom_tag:32 bit upscale", "custom_tag:remastered", "custom_tag:writing", "custom_tag:gguf", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 49636846090}, "outcome": "failed", "status": "success", "submitTime": "2026-10-15T20:46:16.830124+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5569369", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-22T05:17:40.370463+00:00", "modelId": "StartLuxAI/Qwen3.6-35B-A3B-OptiQ-4bit", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-14T14:36:16.300431+00:00", "targetGpu": "MetaX_c-500", "taskId": "5536994", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-16T17:41:11.941285+00:00", "modelId": "inclusionAI/Ring-mini-2.0", "modelProfile": {"architectures": ["BailingMoeV2ForCausalLM"], "configFingerprint": "2e9cebc01b20081f0839fa18fe9ca4f7d059509f235699027201fe328177b304", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 32513135016, "estimatedRequiredGiB": 36.346, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "bailing_moe", "modelscopeFileSize": 32522223867, "modelscopeLicense": "mit", "modelscopeParams": 16255643392, "modelscopeTags": ["license:mit", "model_type:bailing_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 32522223867}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T21:53:35.357776+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520150", "taskType": "text-generation", "verifyResult": null} +{"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-24T08:34:54.442493+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981021}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T21:53:35.260730+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520147", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm", "lastSyncTime": "2026-10-20T12:39:15.571332+00:00", "modelId": "mlx-community/MiMo-V2.6-Distill-Qwen-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120897697, "modelscopeLicense": "mit", "modelscopeParams": 1915564544, "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": "failed", "status": "failed", "submitTime": "2026-10-13T21:52:38.758920+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520133", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-13T22:17:18.970452+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T13:12:18.147765+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5513114", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-13T22:17:18.970462+00:00", "modelId": "XingChen-AGI/Xing4.0-29B-A4B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-13T12:52:58.552750+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5512698", "taskType": "text-generation", "verifyResult": null} @@ -274,6 +275,7 @@ {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164485+00:00", "modelId": "prithivMLmods/Qwen-Image-2.1-PE-T2I-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:15:22.868041+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320517", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164473+00:00", "modelId": "LessThanThreeAI/Qwen3.8-27B-Humanlike-Chat-2.0-GPTQ-Int4", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:15:22.866391+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320518", "taskType": "text-generation", "verifyResult": null} {"failReason": "参数/模板问题", "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T11:42:31.164580+00:00", "modelId": "ukisai/Swift-1.5-5bit-MLX", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:15:22.761540+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320515", "taskType": "text-generation", "verifyResult": null} +{"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-24T08:34:54.442474+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 20473981021}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T09:15:22.650807+00:00", "targetGpu": "Biren_166m", "taskId": "5320513", "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": "2026-10-06T19:00:42.266417+00:00", "modelId": "mlx-community/gpt-oss-20b-OptiQ-4bit", "modelProfile": {"architectures": ["GptOssForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11623702006, "estimatedRequiredGiB": 13.022, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gpt_oss", "modelscopeFileSize": 11651702017, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3982569024, "modelscopeTags": ["license:apache-2.0", "model_type:gpt_oss", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:openai", "custom_tag:gpt-oss", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:optiq", "custom_tag:moe", "custom_tag:apple-silicon", "custom_tag:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11651702017}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:22.648982+00:00", "targetGpu": "Biren_166m", "taskId": "5320514", "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": "2026-10-08T11:54:51.560590+00:00", "modelId": "Youssofal/Qwen3.6-35B-A3B-MTPLX-Optimized-Balance", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 29644061610, "estimatedRequiredGiB": 33.16, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 29671037772, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8030801776, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:qwen", "custom_tag:qwen3", "custom_tag:qwen3-next", "custom_tag:mtp", "custom_tag:mtplx", "custom_tag:local-ai", "custom_tag:mixture-of-experts", "custom_tag:6-bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 29671037772}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:22.643859+00:00", "targetGpu": "Biren_166m", "taskId": "5320512", "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": "2026-10-21T15:05:44.878416+00:00", "modelId": "bench-labs/tinctura-v1", "modelProfile": {"architectures": ["CagliostroForCausalLM"], "configFingerprint": "d8df464812ff2fd3c46dc89b0fc6a96370e694fab8e52179f1ada2cdd0ea92b9", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 384820248, "estimatedRequiredGiB": 1.739, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "cagliostro", "modelscopeFileSize": 1556071699, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:cagliostro", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1556071699}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T09:15:22.367421+00:00", "targetGpu": "Biren_166m", "taskId": "5320496", "taskType": "text-generation", "verifyResult": -1} @@ -296,5 +298,3 @@ {"failReason": "framework_architecture_unsupported", "failureAction": "block_gpu_framework_architecture", "failureCategory": "framework_architecture_unsupported", "failureClassificationReason": "explicit_framework_model_unsupported", "failureCode": "MODEL_NOT_SUPPORTED", "failureDetectedFramework": "vllm", "failureDeterministic": true, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": false, "failureScope": "model_gpu_framework", "failureUnsupportedModelTypes": ["qwen3_5"], "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-07T03:59:02.973639+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293475486, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320427112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320427112}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.471074+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320018", "taskType": "text-generation", "verifyResult": -1} {"failReason": "参数/模板问题", "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-22T00:14:09.777799+00:00", "modelId": "shisa-ai/shisa-de-1-FP8-dynamic", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 27165329828, "estimatedRequiredGiB": 30.398, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 27200059979, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1144510513, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:decision-engine", "custom_tag:system-one", "custom_tag:text-classification", "custom_tag:gemma", "custom_tag:fp8", "custom_tag:compressed-tensors", "custom_tag:llm-compressor"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 27200059979}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:27.465361+00:00", "targetGpu": "Biren_166m", "taskId": "5320017", "taskType": "text-generation", "verifyResult": null} {"failReason": "ambiguous_runtime", "failureAction": "send_compact_profile_and_root_exception_to_llm", "failureCategory": "ambiguous_runtime", "failureClassificationReason": "driver_error", "failureCode": "DRIVER_ERROR", "failureDetectedFramework": "vllm", "failureDeterministic": false, "failureEnrichmentAttempts": 1, "failureEnrichmentError": null, "failureNeedsLlm": true, "failureScope": "unknown", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-10T09:26:43.784451+00:00", "modelId": "mlx-community/LFM2.5-1.2B-Instruct-8bit", "modelProfile": {"architectures": ["Lfm2ForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1243645809, "estimatedRequiredGiB": 1.395, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "lfm2", "modelscopeFileSize": 1248409915, "modelscopeLicense": "other", "modelscopeParams": 329251584, "modelscopeTags": ["license:other", "model_type:lfm2", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:liquid", "custom_tag:lfm2.5", "custom_tag:edge", "custom_tag:mlx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1248409915}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.159752+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5320008", "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": "2026-10-21T21:16:24.481190+00:00", "modelId": "juspay/Xor-26B-A4B-NVFP4", "modelProfile": {"architectures": ["Gemma4ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18788485588, "estimatedRequiredGiB": 21.039, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "gemma4", "modelscopeFileSize": 18825737204, "modelscopeLicense": "apache-2.0", "modelscopeParams": 14386943566, "modelscopeTags": ["license:apache-2.0", "model_type:gemma4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification", "custom_tag:gemma4", "custom_tag:nvfp4", "custom_tag:modelopt", "custom_tag:quantized"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "modelopt", "repositoryOnDiskBytes": 18825737204}, "outcome": "failed", "status": "success", "submitTime": "2026-10-06T08:52:27.158144+00:00", "targetGpu": "Biren_166m", "taskId": "5320010", "taskType": "text-generation", "verifyResult": -1} -{"failReason": "参数/模板问题", "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-07T14:09:53.041515+00:00", "modelId": "mlx-community/XYZ-Aquila-mini-OptiQ-4bit-REAP-18B", "modelProfile": {}, "outcome": "failed", "status": "failed", "submitTime": "2026-10-06T08:52:26.657696+00:00", "targetGpu": "MetaX_c-500", "taskId": "5319990", "taskType": "text-generation", "verifyResult": null} diff --git a/.modelhub_state/recovery_intents.jsonl b/.modelhub_state/recovery_intents.jsonl index e70a06b9f2..2f27856a63 100644 --- a/.modelhub_state/recovery_intents.jsonl +++ b/.modelhub_state/recovery_intents.jsonl @@ -3761,6 +3761,18 @@ {"batchId": "4f076984108b490aa5f8cb591aff42a5", "completedAt": "2026-10-24T07:32:58.032375+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-24T07:32:55.101904+00:00", "framework": "vllm_tokenizer_patch", "intentId": "e578c7f6b5da4552b3feea46702fce26", "lastModified": "2026-10-24T04:12:02+00:00", "modelAddress": "https://modelscope.cn/models/kakarotter/calix", "reason": null, "reconciledAt": "2026-10-24T08:33:22.988487+00:00", "repoId": "kakarotter/calix", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5756254", "taskType": "text-generation"} {"batchId": "76893df1980d4655ba5bf6efd0928613", "completedAt": "2026-10-24T07:34:00.329714+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-24T07:33:57.605158+00:00", "framework": "vllm_tokenizer_patch", "intentId": "84a5e8ee0ba8496aa2dc3c39862c59d2", "lastModified": "2026-10-21T15:32:58+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/OmniCoder-9B-AWQ-BF16-INT4", "reason": null, "reconciledAt": "2026-10-24T08:33:22.987344+00:00", "repoId": "cyankiwi/OmniCoder-9B-AWQ-BF16-INT4", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5756274", "taskType": "text-generation"} {"batchId": "5f5e109d72304547829828f35142533a", "completedAt": "2026-10-24T07:34:58.021309+00:00", "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configSource": "modelhub_live", "createdAt": "2026-10-24T07:34:55.318898+00:00", "framework": "vllm_tokenizer_patch", "intentId": "d3918ba5bc7f473eaf7c602020f44fb4", "lastModified": "2026-10-21T16:43:24+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Kimi-Dev-72B-AWQ-4bit", "reason": null, "reconciledAt": "2026-10-24T08:33:22.987329+00:00", "repoId": "cyankiwi/Kimi-Dev-72B-AWQ-4bit", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 4096}, "status": "recovered_active", "targetGpu": "Ascend_910-b3", "taskId": "5756286", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "167e80c9a74f5acd91819ac9a661546c8992cc5beb0bdd0a1dc9fc9659a5e778", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.671745+00:00", "framework": "vllm_tokenizer_patch", "intentId": "0c61863762bf4ff3b4eac046d93167dd", "lastModified": "2026-10-21T15:53:43+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "repoId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-4bit", "safeConfigVector": {"gpuNum": 1}, "status": "pending", "targetGpu": "Ascend_910-b4", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "ab71f5b6f1f951bd7138e3540ab336b83cc96a774071c9d567b977c2e909eec3", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.671850+00:00", "framework": "llamacpp", "intentId": "40d5a74d8daa4e3482a5e55f4bc09c80", "lastModified": "2026-10-21T18:27:55+00:00", "modelAddress": "https://modelscope.cn/models/prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "repoId": "prithivMLmods/XHToken-Spark-X2.6-4B-GGUF", "safeConfigVector": {"gpuNum": 1, "maxModelLen": 2048}, "status": "pending", "targetGpu": "Mthreads_s4000", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.671910+00:00", "framework": "vllm-mlu", "intentId": "6f4764aa2a664c40a8fd90873a68f580", "lastModified": "2026-10-21T17:03:19+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/MiniCPM-SALA-AWQ-4bit", "repoId": "cyankiwi/MiniCPM-SALA-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.671963+00:00", "framework": "vllm-mlu", "intentId": "8d47777239444ee992dbf72d98e7a6e4", "lastModified": "2026-10-21T15:40:57+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Explore-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Explore-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.672014+00:00", "framework": "vllm-mlu", "intentId": "8100708393e54e5a968836de0be2bac1", "lastModified": "2026-10-21T16:56:28+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "repoId": "cyankiwi/Tongyi-DeepResearch-30B-A3B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.672064+00:00", "framework": "vllm-mlu", "intentId": "c36a6997ff5843c791b59f1c963b6b6f", "lastModified": "2026-10-21T16:21:36+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/AgentCPM-Report-AWQ-8bit", "repoId": "cyankiwi/AgentCPM-Report-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.672114+00:00", "framework": "vllm-mlu", "intentId": "f7824947b43849f9a1ad455f2d0320c8", "lastModified": "2026-10-21T16:19:53+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "repoId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.672162+00:00", "framework": "vllm-mlu", "intentId": "3ea11e5ff3344e4ba0966450042a5c19", "lastModified": "2026-10-21T16:56:31+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "repoId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.672223+00:00", "framework": "vllm-mlu", "intentId": "9f87e6666c864fe3b5aaea8328dfe06a", "lastModified": "2026-10-24T04:12:02+00:00", "modelAddress": "https://modelscope.cn/models/kakarotter/calix", "repoId": "kakarotter/calix", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.672272+00:00", "framework": "vllm-mlu", "intentId": "1f58cb92acfd42b3ba69c6c528ac15e4", "lastModified": "2026-10-21T15:59:12+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.672321+00:00", "framework": "vllm-mlu", "intentId": "eca27e7f39044e59869c936bff8ca3b9", "lastModified": "2026-10-21T17:24:35+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/Orchestrator-8B-AWQ-4bit", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} +{"batchId": "a5615f8a3c844141b156525fdeb1e65b", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:34:56.672370+00:00", "framework": "vllm-mlu", "intentId": "712e54ed48664d0081d32fa36b192722", "lastModified": "2026-10-21T16:38:25+00:00", "modelAddress": "https://modelscope.cn/models/cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "pending", "targetGpu": "Cambricon_mlu-370-x4", "taskType": "text-generation"} {"batchId": "dcaf6d0db9524e6da11ab0729bd039cd", "completedAt": "2026-10-24T08:33:20.990643+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:33:18.558986+00:00", "framework": "vllm-mlu", "intentId": "4536513730ad44b4a414e4b293448441", "repoId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "dcaf6d0db9524e6da11ab0729bd039cd", "completedAt": "2026-10-24T08:33:20.990640+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:33:18.558938+00:00", "framework": "vllm-mlu", "intentId": "8b9dc5c500dc4b148d82175dfd540d0e", "repoId": "cyankiwi/Orchestrator-8B-AWQ-4bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} {"batchId": "dcaf6d0db9524e6da11ab0729bd039cd", "completedAt": "2026-10-24T08:33:20.990637+00:00", "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configSource": "modelhub_live", "createdAt": "2026-10-24T08:33:18.558889+00:00", "framework": "vllm-mlu", "intentId": "a4560d7bfa4e4a65af9ae3846826ef71", "repoId": "cyankiwi/Nemotron-Cascade-8B-Thinking-AWQ-8bit", "safeConfigVector": {"dtype": "-", "gpuNum": 1}, "status": "capacity_deferred", "targetGpu": "Cambricon_mlu-370-x4", "taskId": null, "taskType": "text-generation"} diff --git a/manifest.json b/manifest.json index a705a69ab0..d72c822930 100644 --- a/manifest.json +++ b/manifest.json @@ -2,24 +2,24 @@ "agentVersion": "2026.09.04.4", "checksums": { ".modelhub_state/account_capacity.json": "0e400fa9ded3c9a9cee4cbfb56811c7a90071f9ba56f9d8fdfd89ae03ca3ee32", - ".modelhub_state/architecture_compatibility_blacklist.json": "61315c2101152b47b8bf48b463d0d4343a01cf207d3827f656bac97a73a1843c", + ".modelhub_state/architecture_compatibility_blacklist.json": "9efa2427cd08bb61b4a79a46fdbbe0de386ea928871afc033bc38ac66cdaf104", ".modelhub_state/architecture_history_backfill.json": "a92348206605da04f75c9e26e7c818b76f259e0b28983f18b6375ef94802f0ab", - ".modelhub_state/market_intelligence.json": "2d4601dcfe2b90d4ef57548f9c6df4001e8076c75b2f6e3a0d94532d10e33876", - ".modelhub_state/official_capabilities.json": "697091568428796bf9f4cc7404100575f7dd9c0630ceceabbb8f493ac561799a", - ".modelhub_state/outcome_checkpoint.json": "975aca991daf3a83cbce3798fdf80cdda0a441d794616d1b05ff570663cf26ce", + ".modelhub_state/market_intelligence.json": "2806b3b9eef90dbb40805e35017efd26a64f433050a9960444c71d86fa31f48a", + ".modelhub_state/official_capabilities.json": "0db3b9abf64f7369b2e9b12daa83fccb2fd812247a6765e12794f3b7e392155d", + ".modelhub_state/outcome_checkpoint.json": "41815f5035ef845c429c70acae80f59913c817f86d31946b3616950579116958", ".modelhub_state/queue_cleanup_latest.json": "cc3b0af9e05691c2dd023f6d341b0dac54227402903fb065f7f7010bc11179a2", - ".modelhub_state/recent_outcomes.jsonl": "c86864152c81680d9b52f2d8dd585fb6b34855b70cf47c5ce1024b7c37e05c03", + ".modelhub_state/recent_outcomes.jsonl": "1a8ea1a72fe8ff1f9a8de5469a72b885c6969862b533fdc0b3f879fd4629f707", ".modelhub_state/recovery_active_tasks.jsonl": "a9cf03541f5568c7360b5cca9fa88f49bcbd60fe8ea6f4ec8e295d30f1582b04", - ".modelhub_state/recovery_intents.jsonl": "922b4c976577f07a7b9f955bd533fa6421fa20ff21b6d9248e90c9101d411033", + ".modelhub_state/recovery_intents.jsonl": "c8c2e50cd6928cdaebc5a81ae482d2c90a7638ae2a3ab832c6975e553f0a2ec9", ".modelhub_state/routing_intelligence.json": "a0a718ef699e5a1c42962e618a4bb2c6e0d848ba1bd10e7335d4ea060b22797d", ".modelhub_state/submission_exclusions.jsonl": "3bb99a0a703cee6767cdaeed2e3d26480ebf6d1cb44552f40bf65c94d9ed58b1", ".modelhub_state/worker_crashes.jsonl": "420815fdc492b8e10445c82e3688a8a007acc9958c44b879b420768158b50deb", "ledger/submissions.jsonl": "746ddcde2507fe7f480996c76811eef781fee23a6361e211e43fb80f47fbd31f", - "outcomes/submissions.jsonl": "5c0c3982c57319e9b0529c7cfc9ead8f479bffa8ea511005799a4378c5620d01" + "outcomes/submissions.jsonl": "2c29892e105236040c67b62099f46f98ed4b83bdf3b303d715c8b7d38314b8c0" }, - "generation": 33359, - "phase": "cycle", + "generation": 33360, + "phase": "intent", "schemaVersion": 1, - "updatedAt": "2026-10-24T08:33:23.244384+00:00", + "updatedAt": "2026-10-24T08:34:56.839285+00:00", "writerId": "0b3ec6eb8d2f4d0595f6b37ff80185c2" } diff --git a/outcomes/submissions.jsonl b/outcomes/submissions.jsonl index 26113c1693..19e501dadf 100644 --- a/outcomes/submissions.jsonl +++ b/outcomes/submissions.jsonl @@ -173,8 +173,6 @@ {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T14:24:00.455827+00:00", "modelId": "groxaxo/Hemmingway-1-AutoRound-W4G128", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 18626278816, "estimatedRequiredGiB": 20.839, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_text", "modelscopeFileSize": 18646443738, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1696097792, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:quantized", "custom_tag:auto-round", "custom_tag:awq", "custom_tag:qwen3.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "auto-round", "repositoryOnDiskBytes": 18646443738}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T06:21:33.668586+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5054819", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-09-24T19:28:25.557808+00:00", "modelId": "primitive-ai/DeepSeek-V4-Flash-Vision-Exp-REAP-145B", "modelProfile": {"architectures": ["DeepseekV4ForCausalLM"], "configFingerprint": "1c0a4f69628b2a0ad37a6eee139a4c98afed7d8c93529a9ef42a90756e4e1940", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 83322353204, "estimatedRequiredGiB": 93.133, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "deepseek_v4", "modelscopeFileSize": 83334245282, "modelscopeLicense": "mit", "modelscopeParams": 145799322711, "modelscopeTags": ["license:mit", "model_type:deepseek_v4", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:deepseek_v4", "custom_tag:reap", "custom_tag:expert-pruning", "custom_tag:mxfp4", "custom_tag:vllm", "custom_tag:single-gpu"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "fp8", "repositoryOnDiskBytes": 83334245282}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T11:26:47.190154+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5060689", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T20:02:26.569106+00:00", "modelId": "juspay/xor", "modelProfile": {"architectures": ["Qwen3_5MoeForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 70214495944, "estimatedRequiredGiB": 78.493, "gpuMemoryEvidence": {"memoryGiB": 100.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 100.0, "maximumRepositorySizeGiB": 83.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5_moe", "modelscopeFileSize": 70234635423, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5_moe", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:sglang", "custom_tag:mixture-of-experts", "custom_tag:typed-classification"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-23T21:42:41.557218+00:00", "modelType": "qwen3_5_moe", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Kunlunxin_p-800", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 1}, "repositoryOnDiskBytes": 70234635423}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T12:00:45.395392+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5061116", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-24T21:29:59.059868+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "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": 20473981039, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981039}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T13:26:56.157380+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5062101", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-09-24T21:29:59.059896+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "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": 20473981039, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981039}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T13:27:05.147174+00:00", "targetGpu": "Kunlunxin_p-800", "taskId": "5062103", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-25T02:40:12.563314+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-FP8", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11055458328, "estimatedRequiredGiB": 12.381, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 11077974096}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T18:38:40.460747+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5066681", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-25T02:40:12.563290+00:00", "modelId": "burtenshaw/nanochat", "modelProfile": {"architectures": ["NanoChatForCausalLM"], "configFingerprint": "b3ef6bcf57e6bb4fc9ede989e67a765b0e40b19fbd407f1f8452833c12bd5c38", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8583142248, "estimatedRequiredGiB": 9.603, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nanochat", "modelscopeFileSize": null, "modelscopeLicense": "mit", "modelscopeParams": 161546240, "modelscopeTags": ["license:mit", "model_type:nanochat", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 8592610065}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T18:38:40.459049+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5066680", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-mlu", "lastSyncTime": "2026-09-25T02:40:12.563322+00:00", "modelId": "cyankiwi/K2-Horizon-7B-AWQ-INT4", "modelProfile": {"architectures": ["K2HorizonForCausalLM"], "configFingerprint": "36ec94e289a8da5fd70b98a2f401fc5159740daf9e2a076da4fd490f34bcbc0b", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 8122473440, "estimatedRequiredGiB": 9.103, "gpuMemoryEvidence": {"memoryGiB": 24.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 24.0, "maximumRepositorySizeGiB": 20.0, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "k2_horizon", "modelscopeFileSize": null, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1605333250, "modelscopeTags": ["license:apache-2.0", "model_type:k2_horizon", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:k2-horizon", "custom_tag:7b", "custom_tag:dense", "custom_tag:open-weights", "custom_tag:ifm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 8145035684}, "outcome": "pending", "status": "waiting", "submitTime": "2026-09-24T18:38:40.464823+00:00", "targetGpu": "Cambricon_mlu-370-x4", "taskId": "5066682", "taskType": "text-generation", "verifyResult": null} @@ -407,7 +405,6 @@ {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.953099+00:00", "modelId": "RWKV/RWKV7-G1k-2.9B-20260930", "modelProfile": {"architectures": ["Rwkv7ForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 5896236664, "estimatedRequiredGiB": 6.592, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "rwkv7", "modelscopeFileSize": 5898355154, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:rwkv7", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:rwkv", "custom_tag:rwkv7", "custom_tag:recurrent", "custom_tag:causal-lm", "custom_tag:conversational"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 5898355154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.559066+00:00", "targetGpu": "Biren_166m", "taskId": "5320505", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.951869+00:00", "modelId": "danish-foundation-models/DFM-Mimir-v1.5", "modelProfile": {"architectures": ["HrmTextForCausalLM"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 3573566200, "estimatedRequiredGiB": 4.03, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "hrm_text", "modelscopeFileSize": 3606214195, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1786775040, "modelscopeTags": ["license:apache-2.0", "model_type:hrm_text", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:danish", "custom_tag:english", "custom_tag:hrm-text", "custom_tag:instruction-tuned", "custom_tag:prefix-lm"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 3606214195}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.575480+00:00", "targetGpu": "Biren_166m", "taskId": "5320506", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952328+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.573876+00:00", "targetGpu": "Biren_166m", "taskId": "5320504", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_fix_tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952981+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "16f74ea0f409861ab0c8169a25d9484cb482e27d6a3ad7c529a70b7cdbfabee3", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "recentProfileFeedback": {"attributableFailureCount": 0, "consecutiveFailures": 0, "decisionFailureRate": 0.0, "decisionSuccessRate": 0.0, "decisionTotal": 0, "failureBreakdown": {"ambiguous_runtime": 3}, "failureCount": 3, "failureRate": 1.0, "framework": "vllm_fix_tokenizer", "lastTerminalAt": "2026-09-22T16:15:27.384896+00:00", "modelType": "qwen3_5", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "none", "successCount": 0, "successRate": 0.0, "targetGpu": "Biren_166m", "taskType": "text-generation", "total": 3, "unresolvedFailureCount": 3}, "repositoryOnDiskBytes": 20473981021}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.650807+00:00", "targetGpu": "Biren_166m", "taskId": "5320513", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952657+00:00", "modelId": "primitive-ai/Kolibri-1-mixed-NVFP4-FP8", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 45807306768, "estimatedRequiredGiB": 51.228, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": 45837930112, "modelscopeLicense": "apache-2.0", "modelscopeParams": 44223812896, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 45837930112}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.660536+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320511", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952222+00:00", "modelId": "primitive-ai/Kolibri-1-NVFP4", "modelProfile": {"architectures": ["Kolibri1ForCausalLM"], "configFingerprint": "0d5bc82787a89d4313672808d1a8629a1fc675c91aa6a08865f770aa24447fbc", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 47707345296, "estimatedRequiredGiB": 53.351, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kolibri1", "modelscopeFileSize": 47737939154, "modelscopeLicense": "apache-2.0", "modelscopeParams": 42896496000, "modelscopeTags": ["license:apache-2.0", "model_type:kolibri1", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:vllm", "custom_tag:compressed-tensors", "custom_tag:nvfp4", "custom_tag:quantized", "custom_tag:moe", "custom_tag:kolibri", "custom_tag:reasoning", "custom_tag:agentic", "custom_tag:tool-calling", "custom_tag:single-gpu", "custom_tag:blackwell"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 47737939154}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.654477+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320508", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm-patch-tokenizer", "lastSyncTime": "2026-10-06T18:06:36.952539+00:00", "modelId": "bench-labs/pulvis-v1", "modelProfile": {"architectures": ["PulvisForCausalLM"], "configFingerprint": "03db37da84f8ca79b8ab2a771eab38713ae74b1a74b47d7451ab360bbdb99462", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11853976, "estimatedRequiredGiB": 0.123, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "pulvis", "modelscopeFileSize": 109820987, "modelscopeLicense": "apache-2.0", "modelscopeParams": 8886720, "modelscopeTags": ["license:apache-2.0", "model_type:pulvis", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:causal-lm", "custom_tag:language-model", "custom_tag:base-model", "custom_tag:pretrained-from-scratch", "custom_tag:small-language-model"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 109820987}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-06T09:15:22.659018+00:00", "targetGpu": "hygon_k100-ai", "taskId": "5320509", "taskType": "text-generation", "verifyResult": null} @@ -864,7 +861,6 @@ {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051536+00:00", "modelId": "ConwayResearch/Underdog-Woof-4B-1.1", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 2367237149, "estimatedRequiredGiB": 2.668, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 2387334789, "modelscopeLicense": "apache-2.0", "modelscopeParams": null, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:4bit"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 2387334789}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:52:38.757249+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520137", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051821+00:00", "modelId": "rapid-mlx/Qwen3.8-27B-4bit-MTP-fp16-MLX", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 16293474195, "estimatedRequiredGiB": 18.239, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 16320426300, "modelscopeLicense": "apache-2.0", "modelscopeParams": 4665462000, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:rapid-mlx", "custom_tag:qwen3.8", "custom_tag:qwen3.8-27b", "custom_tag:4-bit", "custom_tag:fp16", "custom_tag:mtp", "custom_tag:speculative-decoding"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 16320426300}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:52:38.761959+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520134", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051450+00:00", "modelId": "ukisai/Swift-1.5-3bit-MLX-TextOnly", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 11771374457, "estimatedRequiredGiB": 13.184, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 11796740983, "modelscopeLicense": "other", "modelscopeParams": 301338560, "modelscopeTags": ["license:other", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:quantized", "custom_tag:3-bit", "custom_tag:affine", "custom_tag:text-only", "custom_tag:qwen3_8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 11796740983}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:52:38.770987+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520135", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051488+00:00", "modelId": "Youssofal/Qwen3.6-27B-MTPLX-Optimized", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 20443542279, "estimatedRequiredGiB": 22.881, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 20473981021, "modelscopeLicense": "apache-2.0", "modelscopeParams": 5678320880, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:apple-silicon", "custom_tag:speculative-decoding", "custom_tag:mtp", "custom_tag:multi-token-prediction", "custom_tag:qwen3", "custom_tag:qwen", "custom_tag:mtplx"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 20473981021}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:53:35.260730+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520147", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051692+00:00", "modelId": "tsinghua-sigs-robot-lab/VeriLoop-E2", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 55655301924, "estimatedRequiredGiB": 62.227, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 55679383091, "modelscopeLicense": "apache-2.0", "modelscopeParams": 27872753616, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:safetensors", "task:text-generation", "custom_tag:conversational", "custom_tag:veriloop", "custom_tag:post-training", "custom_tag:coding-agent", "custom_tag:software-engineering", "custom_tag:mathematical-reasoning", "custom_tag:scientific-reasoning", "custom_tag:tool-use", "custom_tag:long-context", "custom_tag:safetensors", "custom_tag:vllm", "custom_tag:apache-2.0"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 55679383091}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:53:35.444787+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520152", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051530+00:00", "modelId": "groxaxo/Hemmingway-1-oQ5-MLX", "modelProfile": {"architectures": ["Qwen3_5ForCausalLM"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19535961539, "estimatedRequiredGiB": 21.856, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 19556195466, "modelscopeLicense": "cc-by-nc-4.0", "modelscopeParams": null, "modelscopeTags": ["license:cc-by-nc-4.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:omlx", "custom_tag:quantized", "custom_tag:mtp", "custom_tag:qwen3.8"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 19556195466}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:53:35.258202+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520145", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm", "lastSyncTime": "2026-10-14T05:54:00.051442+00:00", "modelId": "mlx-community/Ornith-1.5-9B-OptiQ-4bit", "modelProfile": {"architectures": ["Qwen3_5ForConditionalGeneration"], "configFingerprint": "1557c77dfe4d3dc1a68ae6b8349e7d094da7eec7752d29442a9d6d27e5f13121", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 7100710126, "estimatedRequiredGiB": 7.958, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_5", "modelscopeFileSize": 7120900461, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1915564544, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_5", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:optiq", "custom_tag:quantized", "custom_tag:4bit", "custom_tag:mixed-precision", "custom_tag:qwen3.5", "custom_tag:reasoning", "custom_tag:long-context", "custom_tag:function-calling", "custom_tag:tool-use", "custom_tag:agentic", "custom_tag:apple-silicon"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 7120900461}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-13T21:53:35.485909+00:00", "targetGpu": "Sunrise_pt-200-x1", "taskId": "5520155", "taskType": "text-generation", "verifyResult": null} @@ -1088,10 +1084,10 @@ {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-23T17:40:01.945822+00:00", "modelId": "cyankiwi/Kimi-Linear-48B-A3B-Instruct-AWQ-8bit", "modelProfile": {"architectures": ["KimiLinearForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 54087705936, "estimatedRequiredGiB": 60.459, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "kimi_linear", "modelscopeFileSize": 54097373275, "modelscopeLicense": "mit", "modelscopeParams": 49122681728, "modelscopeTags": ["license:mit", "model_type:kimi_linear", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 54097373275}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T09:25:23.728480+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5735872", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-23T19:15:40.473459+00:00", "modelId": "RecursiveSI/flint-int4", "modelProfile": {"architectures": ["FlintForCausalLM"], "configFingerprint": "7b5500238d52e9e2a21471d722bc1636ca047e1a12ba49c491593b86bec602b8", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22568912600, "estimatedRequiredGiB": 25.235, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "flint", "modelscopeFileSize": 22580274594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3572482016, "modelscopeTags": ["license:apache-2.0", "model_type:flint", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:int4", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22580274594}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T11:15:27.958590+00:00", "targetGpu": "Ascend_910-b3", "taskId": "5737151", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-23T21:28:24.747626+00:00", "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-4bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 14278393080, "estimatedRequiredGiB": 15.973, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 14292651057, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 14292651057}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-23T13:28:00.360187+00:00", "targetGpu": "MetaX_c-500", "taskId": "5738981", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6691066608, "estimatedRequiredGiB": 7.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 6709196808, "modelscopeLicense": "other", "modelscopeParams": 2381547248, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6709196808}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T00:34:03.752902+00:00", "targetGpu": "MetaX_c-500", "taskId": "5749181", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19609154304, "estimatedRequiredGiB": 21.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "olmo3", "modelscopeFileSize": 19619082384, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32233522176, "modelscopeTags": ["license:apache-2.0", "model_type:olmo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19619082384}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T00:34:03.761745+00:00", "targetGpu": "MetaX_c-500", "taskId": "5749178", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24682886272, "estimatedRequiredGiB": 27.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 24697709852, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 24697709852}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T00:34:03.758725+00:00", "targetGpu": "MetaX_c-500", "taskId": "5749179", "taskType": "text-generation", "verifyResult": null} -{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 23.921, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 21404443971, "modelscopeLicense": "other", "modelscopeParams": 14768307200, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:nemotron-cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-23T01:38:31.560801+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 21404443971}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T00:34:03.769556+00:00", "targetGpu": "MetaX_c-500", "taskId": "5749180", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T08:34:54.442500+00:00", "modelId": "cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit", "modelProfile": {"architectures": ["NemotronHForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 6691066608, "estimatedRequiredGiB": 7.498, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "nemotron_h", "modelscopeFileSize": 6709196808, "modelscopeLicense": "other", "modelscopeParams": 2381547248, "modelscopeTags": ["license:other", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:nvidia", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 6709196808}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T00:34:03.752902+00:00", "targetGpu": "MetaX_c-500", "taskId": "5749181", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T08:34:54.442484+00:00", "modelId": "cyankiwi/Olmo-3.1-32B-Think-AWQ-4bit", "modelProfile": {"architectures": ["Olmo3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 19609154304, "estimatedRequiredGiB": 21.926, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "olmo3", "modelscopeFileSize": 19619082384, "modelscopeLicense": "apache-2.0", "modelscopeParams": 32233522176, "modelscopeTags": ["license:apache-2.0", "model_type:olmo3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 19619082384}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T00:34:03.761745+00:00", "targetGpu": "MetaX_c-500", "taskId": "5749178", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T08:34:54.442426+00:00", "modelId": "cyankiwi/ERNIE-4.5-21B-A3B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Ernie4_5_MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 24682886272, "estimatedRequiredGiB": 27.602, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "ernie4_5_moe", "modelscopeFileSize": 24697709852, "modelscopeLicense": "apache-2.0", "modelscopeParams": 22090203328, "modelscopeTags": ["license:apache-2.0", "model_type:ernie4_5_moe", "library:pytorch", "library:transformer", "library:safetensors", "task:text-generation", "custom_tag:ERNIE4.5"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 24697709852}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T00:34:03.758725+00:00", "targetGpu": "MetaX_c-500", "taskId": "5749179", "taskType": "text-generation", "verifyResult": null} +{"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": "2026-10-24T08:34:54.442464+00:00", "modelId": "cyankiwi/Nemotron-Cascade-14B-Thinking-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3ForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 17150429576, "estimatedRequiredGiB": 23.921, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3", "modelscopeFileSize": 21404443971, "modelscopeLicense": "other", "modelscopeParams": 14768307200, "modelscopeTags": ["license:other", "model_type:qwen3", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:nvidia", "custom_tag:nemotron-cascade", "custom_tag:reasoning", "custom_tag:general-purpose", "custom_tag:SFT", "custom_tag:RL", "custom_tag:pytorch"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "recentProfileFeedback": {"attributableFailureCount": 1, "consecutiveFailures": 1, "decisionFailureRate": 1.0, "decisionSuccessRate": 0.0, "decisionTotal": 1, "failureBreakdown": {"backend_operator": 1}, "failureCount": 1, "failureRate": 1.0, "framework": "vllm_tokenizer_patch", "lastTerminalAt": "2026-10-23T01:38:31.560801+00:00", "modelType": "qwen3", "pendingCount": 0, "pendingRate": 0.0, "platformFailureCount": 0, "quantizationMethod": "compressed-tensors", "successCount": 0, "successRate": 0.0, "targetGpu": "MetaX_c-500", "taskType": "text-generation", "total": 1, "unresolvedFailureCount": 0}, "repositoryOnDiskBytes": 21404443971}, "outcome": "pending", "status": "waiting", "submitTime": "2026-10-24T00:34:03.769556+00:00", "targetGpu": "MetaX_c-500", "taskId": "5749180", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "RecursiveSI/flint-int4", "modelProfile": {"architectures": ["FlintForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 22568912600, "estimatedRequiredGiB": 25.235, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "flint", "modelscopeFileSize": 22580274594, "modelscopeLicense": "apache-2.0", "modelscopeParams": 3572482016, "modelscopeTags": ["license:apache-2.0", "model_type:flint", "library:mlx", "library:safetensors", "library:pytorch", "task:text-generation", "custom_tag:mlx", "custom_tag:int4", "custom_tag:safetensors"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 22580274594}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T04:21:55.480388+00:00", "targetGpu": "MetaX_c-500", "taskId": "5753373", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "vllm_tokenizer_patch", "lastSyncTime": null, "modelId": "cyankiwi/DASD-30B-A3B-Thinking-Preview-AWQ-8bit", "modelProfile": {"architectures": ["Qwen3MoeForCausalLM"], "configFingerprint": "8be5b78bdba5c4413c1e4ab91a46e27c34642b25d5dc059ad3a11d50d7e33593", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 33043010296, "estimatedRequiredGiB": 36.952, "gpuMemoryEvidence": {"memoryGiB": 64.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 64.0, "maximumRepositorySizeGiB": 53.333, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": "qwen3_moe", "modelscopeFileSize": 33064405564, "modelscopeLicense": "apache-2.0", "modelscopeParams": 30532122624, "modelscopeTags": ["license:apache-2.0", "model_type:qwen3_moe", "library:transformer", "library:safetensors", "library:pytorch", "task:text-generation"], "modelscopeTasks": ["text-generation"], "quantizationMethod": "compressed-tensors", "repositoryOnDiskBytes": 33064405564}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T04:21:55.470643+00:00", "targetGpu": "MetaX_c-500", "taskId": "5753380", "taskType": "text-generation", "verifyResult": null} {"failReason": null, "framework": "llamacpp", "lastSyncTime": null, "modelId": "AtomicChat/Qwen3.5-9B-DFlash-GGUF", "modelProfile": {"architectures": [], "configFingerprint": "705b8b3614c86a1ac722c97f43e177e84ca20282e9799fffb1b890510d641728", "configOptimization": {"applied": false, "source": "official"}, "configSource": "modelhub_live", "estimatedLoadBytes": 1383768224, "estimatedRequiredGiB": 1.547, "gpuMemoryEvidence": {"memoryGiB": 32.0, "source": "local_modelhub_preflight_oom"}, "gpuMemoryGiB": 32.0, "maximumRepositorySizeGiB": 26.667, "memorySizingBasis": "recursive_repository_on_disk", "modelCard": {}, "modelType": null, "modelscopeFileSize": 1384215789, "modelscopeLicense": "apache-2.0", "modelscopeParams": 1291904512, "modelscopeTags": ["license:apache-2.0", "library:gguf", "library:pytorch", "task:text-generation", "custom_tag:atomic-chat", "custom_tag:qwen3.5", "custom_tag:z-lab", "custom_tag:gguf", "custom_tag:llama.cpp", "custom_tag:quantized", "deploy:swingdeploy"], "modelscopeTasks": ["text-generation"], "quantizationMethod": null, "repositoryOnDiskBytes": 1384215789}, "outcome": "pending", "status": "pending", "submitTime": "2026-10-24T04:21:55.478585+00:00", "targetGpu": "Ascend_910-b4", "taskId": "5753374", "taskType": "text-generation", "verifyResult": null}